enumerate_charges: dimorphite

annotate dimorphite_dl.py @ 1:d84dc786ccb9 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 09b22cceacb34dd4c6c1b42890f93232df128208"

author	bgruening
date	Sat, 21 Mar 2020 18:01:47 +0000
parents	759010d2e9cd
children	9a2b0af78abc

rev	line source
0 759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1 # Copyright 2018 Jacob D. Durrant
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	2 #
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	3 # Licensed under the Apache License, Version 2.0 (the "License");
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	4 # you may not use this file except in compliance with the License.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	5 # You may obtain a copy of the License at
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	6 #
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	7 # http://www.apache.org/licenses/LICENSE-2.0
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	8 #
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	9 # Unless required by applicable law or agreed to in writing, software
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	10 # distributed under the License is distributed on an "AS IS" BASIS,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	12 # See the License for the specific language governing permissions and
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	13 # limitations under the License.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	14
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	15 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	16 This script identifies and enumerates the possible protonation sites of SMILES
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	17 strings.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	18 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	19
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	20 from __future__ import print_function
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	21 import copy
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	22 import os
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	23 import argparse
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	24 import sys
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	25
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	26 try:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	27 # Python2
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	28 from StringIO import StringIO
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	29 except ImportError:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	30 # Python3
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	31 from io import StringIO
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	32
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	33 # Always let the user know a help file is available.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	34 print("\nFor help, use: python dimorphite_dl.py --help")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	35
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	36 # And always report citation information.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	37 print("\nIf you use Dimorphite-DL in your research, please cite:")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	38 print("Ropp PJ, Kaminsky JC, Yablonski S, Durrant JD (2019) Dimorphite-DL: An")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	39 print("open-source program for enumerating the ionization states of drug-like small")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	40 print("molecules. J Cheminform 11:14. doi:10.1186/s13321-019-0336-9.\n")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	41
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	42 try:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	43 import rdkit
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	44 from rdkit import Chem
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	45 from rdkit.Chem import AllChem
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	46 except:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	47 msg = "Dimorphite-DL requires RDKit. See https://www.rdkit.org/"
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	48 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	49 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	50
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	51 def main(params=None):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	52 """The main definition run when you call the script from the commandline.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	53
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	54 :param params: The parameters to use. Entirely optional. If absent,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	55 defaults to None, in which case argments will be taken from
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	56 those given at the command line.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	57 :param params: dict, optional
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	58 :return: Returns a list of the SMILES strings return_as_list parameter is
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	59 True. Otherwise, returns None.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	60 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	61
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	62 parser = ArgParseFuncs.get_args()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	63 args = vars(parser.parse_args())
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	64
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	65 # Add in any parameters in params.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	66 if params is not None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	67 for k, v in params.items():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	68 args[k] = v
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	69
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	70 # If being run from the command line, print out all parameters.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	71 if __name__ == "__main__":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	72 print("\nPARAMETERS:\n")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	73 for k in sorted(args.keys()):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	74 print(k.rjust(13) + ": " + str(args[k]))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	75 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	76
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	77 if args["test"]:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	78 # Run tests.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	79 TestFuncs.test()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	80 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	81 # Run protonation
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	82 if "output_file" in args and args["output_file"] is not None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	83 # An output file was specified, so write to that.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	84 with open(args["output_file"], "w") as file:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	85 for protonated_smi in Protonate(args):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	86 file.write(protonated_smi + "\n")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	87 elif "return_as_list" in args and args["return_as_list"] == True:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	88 return list(Protonate(args))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	89 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	90 # No output file specified. Just print it to the screen.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	91 for protonated_smi in Protonate(args):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	92 print(protonated_smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	93
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	94 class MyParser(argparse.ArgumentParser):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	95 """Overwrite default parse so it displays help file on error. See
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	96 https://stackoverflow.com/questions/4042452/display-help-message-with-python-argparse-when-script-is-called-without-any-argu"""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	97
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	98 def error(self, message):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	99 """Overwrites the default error message.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	100
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	101 :param message: The default error message.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	102 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	103
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	104 self.print_help()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	105 msg = "ERROR: %s\n\n" % message
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	106 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	107 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	108
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	109 def print_help(self, file=None):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	110 """Overwrite the default print_help function
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	111
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	112 :param file: Output file, defaults to None
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	113 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	114
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	115 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	116
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	117 if file is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	118 file = sys.stdout
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	119 self._print_message(self.format_help(), file)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	120 print("""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	121 examples:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	122 python dimorphite_dl.py --smiles_file sample_molecules.smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	123 python dimorphite_dl.py --smiles "CCC(=O)O" --min_ph -3.0 --max_ph -2.0
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	124 python dimorphite_dl.py --smiles "CCCN" --min_ph -3.0 --max_ph -2.0 --output_file output.smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	125 python dimorphite_dl.py --smiles_file sample_molecules.smi --pka_precision 2.0 --label_states
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	126 python dimorphite_dl.py --test""")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	127 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	128
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	129 class ArgParseFuncs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	130 """A namespace for storing functions that are useful for processing
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	131 command-line arguments. To keep things organized."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	132
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	133 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	134 def get_args():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	135 """Gets the arguments from the command line.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	136
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	137 :return: A parser object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	138 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	139
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	140 parser = MyParser(description="Dimorphite 1.2: Creates models of " +
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	141 "appropriately protonated small moleucles. " +
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	142 "Apache 2.0 License. Copyright 2018 Jacob D. " +
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	143 "Durrant.")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	144 parser.add_argument('--min_ph', metavar='MIN', type=float, default=6.4,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	145 help='minimum pH to consider (default: 6.4)')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	146 parser.add_argument('--max_ph', metavar='MAX', type=float, default=8.4,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	147 help='maximum pH to consider (default: 8.4)')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	148 parser.add_argument('--pka_precision', metavar='PRE', type=float, default=1.0,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	149 help='pKa precision factor (number of standard devations, default: 1.0)')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	150 parser.add_argument('--smiles', metavar='SMI', type=str,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	151 help='SMILES string to protonate')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	152 parser.add_argument('--smiles_file', metavar="FILE", type=str,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	153 help='file that contains SMILES strings to protonate')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	154 parser.add_argument('--output_file', metavar="FILE", type=str,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	155 help='output file to write protonated SMILES (optional)')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	156 parser.add_argument('--label_states', action="store_true",
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	157 help='label protonated SMILES with target state ' + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	158 '(i.e., "DEPROTONATED", "PROTONATED", or "BOTH").')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	159 parser.add_argument('--test', action="store_true",
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	160 help='run unit tests (for debugging)')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	161
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	162 return parser
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	163
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	164 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	165 def clean_args(args):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	166 """Cleans and normalizes input parameters
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	167
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	168 :param args: A dictionary containing the arguments.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	169 :type args: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	170 :raises Exception: No SMILES in params.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	171 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	172
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	173 defaults = {'min_ph' : 6.4,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	174 'max_ph' : 8.4,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	175 'pka_precision' : 1.0,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	176 'label_states' : False,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	177 'test' : False}
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	178
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	179 for key in defaults:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	180 if key not in args:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	181 args[key] = defaults[key]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	182
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	183 keys = list(args.keys())
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	184 for key in keys:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	185 if args[key] is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	186 del args[key]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	187
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	188 if not "smiles" in args and not "smiles_file" in args:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	189 msg = "Error: No SMILES in params. Use the -h parameter for help."
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	190 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	191 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	192
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	193 # If the user provides a smiles string, turn it into a file-like StringIO
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	194 # object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	195 if "smiles" in args:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	196 if isinstance(args["smiles"], str):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	197 args["smiles_file"] = StringIO(args["smiles"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	198
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	199 args["smiles_and_data"] = LoadSMIFile(args["smiles_file"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	200
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	201 return args
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	202
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	203 class UtilFuncs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	204 """A namespace to store functions for manipulating mol objects. To keep
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	205 things organized."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	206
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	207 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	208 def neutralize_mol(mol):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	209 """All molecules should be neuralized to the extent possible. The user
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	210 should not be allowed to specify the valence of the atoms in most cases.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	211
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	212 :param rdkit.Chem.rdchem.Mol mol: The rdkit Mol objet to be neutralized.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	213 :return: The neutralized Mol object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	214 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	215
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	216 # Get the reaction data
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	217 rxn_data = [
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	218 ['[Ov1-1:1]', '[Ov2+0:1]-[H]'], # To handle O- bonded to only one atom (add hydrogen).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	219 ['[#7v4+1:1]-[H]', '[#7v3+0:1]'], # To handle N+ bonded to a hydrogen (remove hydrogen).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	220 ['[Ov2-:1]', '[Ov2+0:1]'], # To handle O- bonded to two atoms. Should not be Negative.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	221 ['[#7v3+1:1]', '[#7v3+0:1]'], # To handle N+ bonded to three atoms. Should not be positive.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	222 ['[#7v2-1:1]', '[#7+0:1]-[H]'], # To handle N- Bonded to two atoms. Add hydrogen.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	223 # ['[N:1]=[N+0:2]=[N:3]-[H]', '[N:1]=[N+1:2]=[N+0:3]-[H]'], # To
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	224 # handle bad azide. Must be protonated. (Now handled elsewhere, before
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	225 # SMILES converted to Mol object.)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	226 ['[H]-[N:1]-[N:2]#[N:3]', '[N:1]=[N+1:2]=[N:3]-[H]'] # To handle bad azide. R-N-N#N should be R-N=[N+]=N
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	227 ]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	228
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	229 # Add substructures and reactions (initially none)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	230 for i, rxn_datum in enumerate(rxn_data):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	231 rxn_data[i].append(Chem.MolFromSmarts(rxn_datum[0]))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	232 rxn_data[i].append(None)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	233
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	234 # Add hydrogens (respects valence, so incomplete).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	235 # Chem.calcImplicitValence(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	236 mol.UpdatePropertyCache(strict=False)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	237 mol = Chem.AddHs(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	238
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	239 while True: # Keep going until all these issues have been resolved.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	240 current_rxn = None # The reaction to perform.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	241 current_rxn_str = None
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	242
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	243 for i, rxn_datum in enumerate(rxn_data):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	244 reactant_smarts, product_smarts, substruct_match_mol, rxn_placeholder = rxn_datum
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	245 if mol.HasSubstructMatch(substruct_match_mol):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	246 if rxn_placeholder is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	247 current_rxn_str = reactant_smarts + '>>' + product_smarts
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	248 current_rxn = AllChem.ReactionFromSmarts(current_rxn_str)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	249 rxn_data[i][3] = current_rxn # Update the placeholder.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	250 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	251 current_rxn = rxn_data[i][3]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	252 break
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	253
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	254 # Perform the reaction if necessary
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	255 if current_rxn is None: # No reaction left, so break out of while loop.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	256 break
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	257 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	258 mol = current_rxn.RunReactants((mol,))[0][0]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	259 mol.UpdatePropertyCache(strict=False) # Update valences
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	260
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	261 # The mols have been altered from the reactions described above, we need
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	262 # to resanitize them. Make sure aromatic rings are shown as such This
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	263 # catches all RDKit Errors. without the catchError and sanitizeOps the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	264 # Chem.SanitizeMol can crash the program.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	265 sanitize_string = Chem.SanitizeMol(
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	266 mol,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	267 sanitizeOps=rdkit.Chem.rdmolops.SanitizeFlags.SANITIZE_ALL,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	268 catchErrors = True
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	269 )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	270
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	271 return mol if sanitize_string.name == "SANITIZE_NONE" else None
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	272
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	273 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	274 def convert_smiles_str_to_mol(smiles_str):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	275 """Given a SMILES string, check that it is actually a string and not a
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	276 None. Then try to convert it to an RDKit Mol Object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	277
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	278 :param string smiles_str: The SMILES string.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	279 :return: A rdkit.Chem.rdchem.Mol object, or None if it is the wrong type or
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	280 if it fails to convert to a Mol Obj
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	281 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	282
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	283 # Check that there are no type errors, ie Nones or non-string
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	284 # A non-string type will cause RDKit to hard crash
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	285 if smiles_str is None or type(smiles_str) is not str:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	286 return None
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	287
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	288 # Try to fix azides here. They are just tricky to deal with.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	289 smiles_str = smiles_str.replace("N=N=N", "N=[N+]=N")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	290 smiles_str = smiles_str.replace("NN#N", "N=[N+]=N")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	291
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	292 # Now convert to a mol object. Note the trick that is necessary to
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	293 # capture RDKit error/warning messages. See
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	294 # https://stackoverflow.com/questions/24277488/in-python-how-to-capture-the-stdout-from-a-c-shared-library-to-a-variable
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	295 stderr_fileno = sys.stderr.fileno()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	296 stderr_save = os.dup(stderr_fileno)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	297 stderr_pipe = os.pipe()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	298 os.dup2(stderr_pipe[1], stderr_fileno)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	299 os.close(stderr_pipe[1])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	300
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	301 mol = Chem.MolFromSmiles(smiles_str)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	302
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	303 os.close(stderr_fileno)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	304 os.close(stderr_pipe[0])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	305 os.dup2(stderr_save, stderr_fileno)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	306 os.close(stderr_save)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	307
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	308 # Check that there are None type errors Chem.MolFromSmiles has sanitize on
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	309 # which means if there is even a small error in the SMILES (kekulize,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	310 # nitrogen charge...) then mol=None. ie.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	311 # Chem.MolFromSmiles("C[N]=[N]=[N]") = None this is an example of an
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	312 # nitrogen charge error. It is cased in a try statement to be overly
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	313 # cautious.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	314
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	315 return None if mol is None else mol
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	316
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	317 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	318 def eprint(args, *kwargs):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	319 """Error messages should be printed to STDERR. See
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	320 https://stackoverflow.com/questions/5574702/how-to-print-to-stderr-in-python"""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	321
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	322 print(args, file=sys.stderr, *kwargs)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	323
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	324 class LoadSMIFile(object):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	325 """A generator class for loading in the SMILES strings from a file, one at
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	326 a time."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	327
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	328 def __init__(self, filename):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	329 """Initializes this class.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	330
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	331 :param filename: The filename or file object (i.e., StringIO).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	332 :type filename: str or StringIO
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	333 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	334
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	335 if type(filename) is str:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	336 # It's a filename
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	337 self.f = open(filename, "r")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	338 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	339 # It's a file object (i.e., StringIO)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	340 self.f = filename
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	341
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	342 def __iter__(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	343 """Returns this generator object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	344
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	345 :return: This generator object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	346 :rtype: LoadSMIFile
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	347 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	348
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	349 return self
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	350
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	351 def __next__(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	352 """Ensure Python3 compatibility.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	353
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	354 :return: A dict, where the "smiles" key contains the canonical SMILES
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	355 string and the "data" key contains the remaining information
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	356 (e.g., the molecule name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	357 :rtype: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	358 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	359
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	360 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	361
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	362 def next(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	363 """Get the data associated with the next line.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	364
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	365 :raises StopIteration: If there are no more lines left iin the file.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	366 :return: A dict, where the "smiles" key contains the canonical SMILES
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	367 string and the "data" key contains the remaining information
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	368 (e.g., the molecule name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	369 :rtype: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	370 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	371
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	372 line = self.f.readline()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	373
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	374 if line == "":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	375 # EOF
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	376 self.f.close()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	377 raise StopIteration()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	378 return
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	379
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	380 # Divide line into smi and data
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	381 splits = line.split()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	382 if len(splits) != 0:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	383 # Generate mol object
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	384 smiles_str = splits[0]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	385
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	386 # Convert from SMILES string to RDKIT Mol. This series of tests is
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	387 # to make sure the SMILES string is properly formed and to get it
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	388 # into a canonical form. Filter if failed.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	389 mol = UtilFuncs.convert_smiles_str_to_mol(smiles_str)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	390 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	391 UtilFuncs.eprint("WARNING: Skipping poorly formed SMILES string: " + line)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	392 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	393
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	394 # Handle nuetralizing the molecules. Filter if failed.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	395 mol = UtilFuncs.neutralize_mol(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	396 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	397 UtilFuncs.eprint("WARNING: Skipping poorly formed SMILES string: " + line)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	398 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	399
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	400 # Remove the hydrogens.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	401 try:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	402 mol = Chem.RemoveHs(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	403 except:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	404 UtilFuncs.eprint("WARNING: Skipping poorly formed SMILES string: " + line)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	405 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	406
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	407 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	408 UtilFuncs.eprint("WARNING: Skipping poorly formed SMILES string: " + line)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	409 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	410
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	411 # Regenerate the smiles string (to standardize).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	412 new_mol_string = Chem.MolToSmiles(mol, isomericSmiles=True)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	413
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	414 return {
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	415 "smiles": new_mol_string,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	416 "data": splits[1:]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	417 }
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	418 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	419 # Blank line? Go to next one.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	420 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	421
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	422 class Protonate(object):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	423 """A generator class for protonating SMILES strings, one at a time."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	424
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	425 def __init__(self, args):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	426 """Initialize the generator.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	427
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	428 :param args: A dictionary containing the arguments.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	429 :type args: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	430 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	431
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	432 # Make the args an object variable variable.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	433 self.args = args
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	434
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	435 # A list to store the protonated SMILES strings associated with a
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	436 # single input model.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	437 self.cur_prot_SMI = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	438
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	439 # Clean and normalize the args
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	440 self.args = ArgParseFuncs.clean_args(args)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	441
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	442 # Load the substructures that can be protonated.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	443 self.subs = ProtSubstructFuncs.load_protonation_substructs_calc_state_for_ph(
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	444 self.args["min_ph"], self.args["max_ph"], self.args["pka_precision"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	445 )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	446
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	447 def __iter__(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	448 """Returns this generator object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	449
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	450 :return: This generator object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	451 :rtype: Protonate
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	452 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	453
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	454 return self
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	455
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	456 def __next__(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	457 """Ensure Python3 compatibility.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	458
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	459 :return: A dict, where the "smiles" key contains the canonical SMILES
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	460 string and the "data" key contains the remaining information
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	461 (e.g., the molecule name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	462 :rtype: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	463 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	464
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	465 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	466
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	467 def next(self):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	468 """Get the next protonated SMILES string.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	469
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	470 :raises StopIteration: If there are no more lines left iin the file.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	471 :return: TODO A dict, where the "smiles" key contains the canonical SMILES
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	472 string and the "data" key contains the remaining information
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	473 (e.g., the molecule name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	474 :rtype: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	475 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	476
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	477 # If there are any SMILES strings in self.cur_prot_SMI, just return
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	478 # the first one and update the list to include only the remaining.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	479 if len(self.cur_prot_SMI) > 0:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	480 first, self.cur_prot_SMI = self.cur_prot_SMI[0], self.cur_prot_SMI[1:]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	481 return first
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	482
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	483 # self.cur_prot_SMI is empty, so try to add more to it.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	484
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	485 # Get the next SMILES string from the input file.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	486 try:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	487 smile_and_datum = self.args["smiles_and_data"].next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	488 except StopIteration:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	489 # There are no more input smiles strings...
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	490 raise StopIteration()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	491
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	492 smi = smile_and_datum["smiles"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	493 data = smile_and_datum["data"] # Everything on SMILES line but the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	494 # SMILES string itself (e.g., the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	495 # molecule name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	496
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	497 # Collect the data associated with this smiles (e.g., the molecule
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	498 # name).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	499 tag = " ".join(data)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	500
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	501 # sites is a list of (atom index, "PROTONATED\|DEPROTONATED\|BOTH").
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	502 # Note that the second entry indicates what state the site SHOULD be
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	503 # in (not the one it IS in per the SMILES string). It's calculated
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	504 # based on the probablistic distributions obtained during training.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	505 sites = ProtSubstructFuncs.get_prot_sites_and_target_states(smi, self.subs)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	506
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	507 new_smis = [smi]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	508 for site in sites:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	509 # Make a new smiles with the correct protonation state. Note that
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	510 # new_smis is a growing list. This is how multiple protonation
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	511 # sites are handled.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	512
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	513 # new_smis_to_perhaps_add = ProtSubstructFuncs.protonate_site(new_smis, site)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	514 new_smis = ProtSubstructFuncs.protonate_site(new_smis, site)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	515 # print(site, new_smis) # Good for debugging.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	516
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	517 # Only add new smiles if not already in the list.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	518 # for s in new_smis_to_perhaps_add:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	519 # if not s in new_smis:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	520 # new_smis.append(s)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	521
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	522 # In some cases, the script might generate redundant molecules.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	523 # Phosphonates, when the pH is between the two pKa values and the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	524 # stdev value is big enough, for example, will generate two identical
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	525 # BOTH states. Let's remove this redundancy.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	526 new_smis = list(set(new_smis))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	527
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	528 # Deprotonating protonated aromatic nitrogen gives [nH-]. Change this
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	529 # to [n-]. This is a hack.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	530 new_smis = [s.replace("[nH-]", "[n-]") for s in new_smis]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	531
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	532 # Sometimes Dimorphite-DL generates molecules that aren't actually
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	533 # possible. Simply convert these to mol objects to eliminate the bad
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	534 # ones (that are None).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	535 new_smis = [s for s in new_smis if UtilFuncs.convert_smiles_str_to_mol(s) is not None]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	536
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	537 # If there are no smi left, return the input one at the very least.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	538 # All generated forms have apparently been judged
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	539 # inappropriate/mal-formed.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	540 if len(new_smis) == 0:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	541 new_smis = [smi]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	542
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	543 # If the user wants to see the target states, add those
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	544 # to the ends of each line.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	545 if self.args["label_states"]:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	546 states = '\t'.join([x[1] for x in sites])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	547 new_lines = [x + "\t" + tag + "\t" + states for x in new_smis]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	548 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	549 new_lines = [x + "\t" + tag for x in new_smis]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	550
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	551 self.cur_prot_SMI = new_lines
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	552
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	553 return self.next()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	554
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	555 class ProtSubstructFuncs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	556 """A namespace to store functions for loading the substructures that can
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	557 be protonated. To keep things organized."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	558
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	559 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	560 def load_protonation_substructs_calc_state_for_ph(min_ph=6.4, max_ph=8.4, pka_std_range=1):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	561 """A pre-calculated list of R-groups with protonation sites, with their
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	562 likely pKa bins.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	563
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	564 :param float min_ph: The lower bound on the pH range, defaults to 6.4.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	565 :param float max_ph: The upper bound on the pH range, defaults to 8.4.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	566 :param pka_std_range: Basically the precision (stdev from predicted pKa to
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	567 consider), defaults to 1.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	568 :return: A dict of the protonation substructions for the specified pH
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	569 range.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	570 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	571
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	572 subs = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	573 pwd = os.path.dirname(os.path.realpath(__file__))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	574
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	575 site_structures_file = "{}/{}".format(pwd, "site_substructures.smarts")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	576 with open(site_structures_file, 'r') as substruct:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	577 for line in substruct:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	578 line = line.strip()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	579 sub = {}
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	580 if line is not "":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	581 splits = line.split()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	582 sub["name"] = splits[0]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	583 sub["smart"] = splits[1]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	584 sub["mol"] = Chem.MolFromSmarts(sub["smart"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	585
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	586 # NEED TO DIVIDE THIS BY 3s
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	587 pka_ranges = [splits[i:i+3] for i in range(2, len(splits)-1, 3)]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	588
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	589 prot = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	590 for pka_range in pka_ranges:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	591 site = pka_range[0]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	592 std = float(pka_range[2]) * pka_std_range
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	593 mean = float(pka_range[1])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	594 protonation_state = ProtSubstructFuncs.define_protonation_state(
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	595 mean, std, min_ph, max_ph
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	596 )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	597
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	598 prot.append([site, protonation_state])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	599
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	600 sub["prot_states_for_pH"] = prot
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	601 subs.append(sub)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	602 return subs
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	603
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	604 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	605 def define_protonation_state(mean, std, min_ph, max_ph):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	606 """Updates the substructure definitions to include the protonation state
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	607 based on the user-given pH range. The size of the pKa range is also based
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	608 on the number of standard deviations to be considered by the user param.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	609
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	610 :param float mean: The mean pKa.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	611 :param float std: The precision (stdev).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	612 :param float min_ph: The min pH of the range.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	613 :param float max_ph: The max pH of the range.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	614 :return: A string describing the protonation state.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	615 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	616
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	617 min_pka = mean - std
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	618 max_pka = mean + std
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	619
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	620 # This needs to be reassigned, and 'ERROR' should never make it past the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	621 # next set of checks.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	622 if min_pka <= max_ph and min_ph <= max_pka:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	623 protonation_state = 'BOTH'
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	624 elif mean > max_ph:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	625 protonation_state = 'PROTONATED'
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	626 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	627 protonation_state = 'DEPROTONATED'
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	628
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	629 return protonation_state
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	630
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	631 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	632 def get_prot_sites_and_target_states(smi, subs):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	633 """For a single molecule, find all possible matches in the protonation
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	634 R-group list, subs. Items that are higher on the list will be matched
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	635 first, to the exclusion of later items.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	636
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	637 :param string smi: A SMILES string.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	638 :param list subs: Substructure information.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	639 :return: A list of protonation sites and their pKa bin. ('PROTONATED',
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	640 'BOTH', or 'DEPROTONATED')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	641 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	642
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	643 # Convert the Smiles string (smi) to an RDKit Mol Obj
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	644 mol = UtilFuncs.convert_smiles_str_to_mol(smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	645
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	646 # Check Conversion worked
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	647 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	648 UtilFuncs.eprint("ERROR: ", smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	649 return []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	650
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	651 # Try to Add hydrogens. if failed return []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	652 try:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	653 mol = Chem.AddHs(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	654 except:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	655 UtilFuncs.eprint("ERROR: ", smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	656 return []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	657
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	658 # Check adding Hs worked
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	659 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	660 UtilFuncs.eprint("ERROR: ", smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	661 return []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	662
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	663 ProtectUnprotectFuncs.unprotect_molecule(mol)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	664 protonation_sites = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	665
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	666 for item in subs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	667 smart = item["mol"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	668 if mol.HasSubstructMatch(smart):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	669 matches = ProtectUnprotectFuncs.get_unprotected_matches(mol, smart)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	670 prot = item["prot_states_for_pH"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	671 for match in matches:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	672 # We want to move the site from being relative to the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	673 # substructure, to the index on the main molecule.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	674 for site in prot:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	675 proton = int(site[0])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	676 category = site[1]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	677 new_site = (match[proton], category, item["name"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	678
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	679 if not new_site in protonation_sites:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	680 # Because sites must be unique.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	681 protonation_sites.append(new_site)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	682
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	683 ProtectUnprotectFuncs.protect_molecule(mol, match)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	684
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	685 return protonation_sites
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	686
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	687 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	688 def protonate_site(smis, site):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	689 """Given a list of SMILES strings, we protonate the site.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	690
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	691 :param list smis: The list of SMILES strings.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	692 :param tuple site: Information about the protonation site.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	693 (idx, target_prot_state, prot_site_name)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	694 :return: A list of the appropriately protonated SMILES.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	695 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	696
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	697 # Decouple the atom index and its target protonation state from the site
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	698 # tuple
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	699 idx, target_prot_state, prot_site_name = site
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	700
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	701 # Initialize the output list
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	702 output_smis = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	703
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	704 state_to_charge = {"DEPROTONATED": [-1],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	705 "PROTONATED": [0],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	706 "BOTH": [-1, 0]}
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	707
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	708 charges = state_to_charge[target_prot_state]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	709
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	710 # Now make the actual smiles match the target protonation state.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	711 output_smis = ProtSubstructFuncs.set_protonation_charge(smis, idx, charges, prot_site_name)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	712
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	713 return output_smis
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	714
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	715 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	716 def set_protonation_charge(smis, idx, charges, prot_site_name):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	717 """Sets the atomic charge on a particular site for a set of SMILES.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	718
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	719 :param list smis: A list of the SMILES strings.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	720 :param int idx: The index of the atom to consider.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	721 :param list charges: A list of the charges (ints) to assign at
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	722 this site.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	723 :param string prot_site_name: The name of the protonation site.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	724 :return: A list of the processed SMILES strings.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	725 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	726
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	727 # Sets up the output list and the Nitrogen charge
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	728 output = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	729
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	730 for charge in charges:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	731 # The charge for Nitrogens is 1 higher than others (i.e., protonated
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	732 # state is positively charged).
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	733 nitro_charge = charge + 1
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	734
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	735 # But there are a few nitrogen moieties where the acidic group is the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	736 # neutral one. Amides are a good example. I gave some thought re. how
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	737 # to best flag these. I decided that those nitrogen-containing
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	738 # moieties where the acidic group is neutral (rather than positively
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	739 # charged) will have "*" in the name.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	740 if "*" in prot_site_name:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	741 nitro_charge = nitro_charge - 1 # Undo what was done previously.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	742
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	743 for smi in smis:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	744
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	745 # Convert smilesstring (smi) into a RDKit Mol
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	746 mol = UtilFuncs.convert_smiles_str_to_mol(smi)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	747
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	748 # Check that the conversion worked, skip if it fails
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	749 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	750 continue
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	751
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	752 atom = mol.GetAtomWithIdx(idx)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	753
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	754 # Assign the protonation charge, with special care for Nitrogens
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	755 element = atom.GetAtomicNum()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	756 if element == 7:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	757 atom.SetFormalCharge(nitro_charge)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	758 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	759 atom.SetFormalCharge(charge)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	760
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	761 # Convert back to SMILE and add to output
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	762 out_smile = Chem.MolToSmiles(mol, isomericSmiles=True,canonical=True)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	763 output.append(out_smile)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	764
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	765 return output
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	766
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	767 class ProtectUnprotectFuncs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	768 """A namespace for storing functions that are useful for protecting and
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	769 unprotecting molecules. To keep things organized. We need to identify and
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	770 mark groups that have been matched with a substructure."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	771
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	772 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	773 def unprotect_molecule(mol):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	774 """Sets the protected property on all atoms to 0. This also creates the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	775 property for new molecules.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	776
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	777 :param rdkit.Chem.rdchem.Mol mol: The rdkit Mol object.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	778 :type mol: The rdkit Mol object with atoms unprotected.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	779 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	780
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	781 for atom in mol.GetAtoms():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	782 atom.SetProp('_protected', '0')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	783
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	784 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	785 def protect_molecule(mol, match):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	786 """Given a 'match', a list of molecules idx's, we set the protected status
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	787 of each atom to 1. This will prevent any matches using that atom in the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	788 future.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	789
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	790 :param rdkit.Chem.rdchem.Mol mol: The rdkit Mol object to protect.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	791 :param list match: A list of molecule idx's.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	792 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	793
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	794 for idx in match:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	795 atom = mol.GetAtomWithIdx(idx)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	796 atom.SetProp('_protected', '1')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	797
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	798 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	799 def get_unprotected_matches(mol, substruct):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	800 """Finds substructure matches with atoms that have not been protected.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	801 Returns list of matches, each match a list of atom idxs.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	802
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	803 :param rdkit.Chem.rdchem.Mol mol: The Mol object to consider.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	804 :param string substruct: The SMARTS string of the substructure ot match.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	805 :return: A list of the matches. Each match is itself a list of atom idxs.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	806 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	807
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	808 matches = mol.GetSubstructMatches(substruct)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	809 unprotected_matches = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	810 for match in matches:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	811 if ProtectUnprotectFuncs.is_match_unprotected(mol, match):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	812 unprotected_matches.append(match)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	813 return unprotected_matches
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	814
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	815 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	816 def is_match_unprotected(mol, match):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	817 """Checks a molecule to see if the substructure match contains any
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	818 protected atoms.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	819
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	820 :param rdkit.Chem.rdchem.Mol mol: The Mol object to check.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	821 :param list match: The match to check.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	822 :return: A boolean, whether the match is present or not.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	823 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	824
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	825 for idx in match:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	826 atom = mol.GetAtomWithIdx(idx)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	827 protected = atom.GetProp("_protected")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	828 if protected == "1":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	829 return False
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	830 return True
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	831
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	832 class TestFuncs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	833 """A namespace for storing functions that perform tests on the code. To
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	834 keep things organized."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	835
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	836 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	837 def test():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	838 """Tests all the 38 groups."""
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	839
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	840 smis = [
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	841 # [input smiles, pka, protonated, deprotonated, category]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	842 ["C#CCO", "C#CCO", "C#CC[O-]", "Alcohol"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	843 ["C(=O)N", "NC=O", "[NH-]C=O", "Amide"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	844 ["CC(=O)NOC(C)=O", "CC(=O)NOC(C)=O", "CC(=O)[N-]OC(C)=O", "Amide_electronegative"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	845 ["COC(=N)N", "COC(N)=[NH2+]", "COC(=N)N", "AmidineGuanidine2"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	846 ["Brc1ccc(C2NCCS2)cc1", "Brc1ccc(C2[NH2+]CCS2)cc1", "Brc1ccc(C2NCCS2)cc1", "Amines_primary_secondary_tertiary"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	847 ["CC(=O)[n+]1ccc(N)cc1", "CC(=O)[n+]1ccc([NH3+])cc1", "CC(=O)[n+]1ccc(N)cc1", "Anilines_primary"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	848 ["CCNc1ccccc1", "CC[NH2+]c1ccccc1", "CCNc1ccccc1", "Anilines_secondary"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	849 ["Cc1ccccc1N(C)C", "Cc1ccccc1[NH+](C)C", "Cc1ccccc1N(C)C", "Anilines_tertiary"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	850 ["BrC1=CC2=C(C=C1)NC=C2", "Brc1ccc2[nH]ccc2c1", "Brc1ccc2[n-]ccc2c1", "Indole_pyrrole"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	851 ["O=c1cc[nH]cc1", "O=c1cc[nH]cc1", "O=c1cc[n-]cc1", "Aromatic_nitrogen_protonated"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	852 ["C-N=[N+]=[N@H]", "CN=[N+]=N", "CN=[N+]=[N-]", "Azide"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	853 ["BrC(C(O)=O)CBr", "O=C(O)C(Br)CBr", "O=C([O-])C(Br)CBr", "Carboxyl"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	854 ["NC(NN=O)=N", "NC(=[NH2+])NN=O", "N=C(N)NN=O", "AmidineGuanidine1"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	855 ["C(F)(F)(F)C(=O)NC(=O)C", "CC(=O)NC(=O)C(F)(F)F", "CC(=O)[N-]C(=O)C(F)(F)F", "Imide"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	856 ["O=C(C)NC(C)=O", "CC(=O)NC(C)=O", "CC(=O)[N-]C(C)=O", "Imide2"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	857 ["CC(C)(C)C(N(C)O)=O", "CN(O)C(=O)C(C)(C)C", "CN([O-])C(=O)C(C)(C)C", "N-hydroxyamide"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	858 ["C[N+](O)=O", "C[N+](=O)O", "C[N+](=O)[O-]", "Nitro"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	859 ["O=C1C=C(O)CC1", "O=C1C=C(O)CC1", "O=C1C=C([O-])CC1", "O=C-C=C-OH"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	860 ["C1CC1OO", "OOC1CC1", "[O-]OC1CC1", "Peroxide2"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	861 ["C(=O)OO", "O=COO", "O=CO[O-]", "Peroxide1"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	862 ["Brc1cc(O)cc(Br)c1", "Oc1cc(Br)cc(Br)c1", "[O-]c1cc(Br)cc(Br)c1", "Phenol"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	863 ["CC(=O)c1ccc(S)cc1", "CC(=O)c1ccc(S)cc1", "CC(=O)c1ccc([S-])cc1", "Phenyl_Thiol"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	864 ["C=CCOc1ccc(C(=O)O)cc1", "C=CCOc1ccc(C(=O)O)cc1", "C=CCOc1ccc(C(=O)[O-])cc1", "Phenyl_carboxyl"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	865 ["COP(=O)(O)OC", "COP(=O)(O)OC", "COP(=O)([O-])OC", "Phosphate_diester"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	866 ["CP(C)(=O)O", "CP(C)(=O)O", "CP(C)(=O)[O-]", "Phosphinic_acid"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	867 ["CC(C)OP(C)(=O)O", "CC(C)OP(C)(=O)O", "CC(C)OP(C)(=O)[O-]", "Phosphonate_ester"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	868 ["CC1(C)OC(=O)NC1=O", "CC1(C)OC(=O)NC1=O", "CC1(C)OC(=O)[N-]C1=O", "Ringed_imide1"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	869 ["O=C(N1)C=CC1=O", "O=C1C=CC(=O)N1", "O=C1C=CC(=O)[N-]1", "Ringed_imide2"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	870 ["O=S(OC)(O)=O", "COS(=O)(=O)O", "COS(=O)(=O)[O-]", "Sulfate"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	871 ["COc1ccc(S(=O)O)cc1", "COc1ccc(S(=O)O)cc1", "COc1ccc(S(=O)[O-])cc1", "Sulfinic_acid"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	872 ["CS(N)(=O)=O", "CS(N)(=O)=O", "CS([NH-])(=O)=O", "Sulfonamide"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	873 ["CC(=O)CSCCS(O)(=O)=O", "CC(=O)CSCCS(=O)(=O)O", "CC(=O)CSCCS(=O)(=O)[O-]", "Sulfonate"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	874 ["CC(=O)S", "CC(=O)S", "CC(=O)[S-]", "Thioic_acid"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	875 ["C(C)(C)(C)(S)", "CC(C)(C)S", "CC(C)(C)[S-]", "Thiol"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	876 ["Brc1cc[nH+]cc1", "Brc1cc[nH+]cc1", "Brc1ccncc1", "Aromatic_nitrogen_unprotonated"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	877 ["C=C(O)c1c(C)cc(C)cc1C", "C=C(O)c1c(C)cc(C)cc1C", "C=C([O-])c1c(C)cc(C)cc1C", "Vinyl_alcohol"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	878 ["CC(=O)ON", "CC(=O)O[NH3+]", "CC(=O)ON", "Primary_hydroxyl_amine"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	879 ]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	880
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	881 smis_phos = [
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	882 ["O=P(O)(O)OCCCC", "CCCCOP(=O)(O)O", "CCCCOP(=O)([O-])O", "CCCCOP(=O)([O-])[O-]", "Phosphate"],
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	883 ["CC(P(O)(O)=O)C", "CC(C)P(=O)(O)O", "CC(C)P(=O)([O-])O", "CC(C)P(=O)([O-])[O-]", "Phosphonate"]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	884 ]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	885
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	886 # Load the average pKa values.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	887 average_pkas = {l.split()[0].replace("*", ""):float(l.split()[3]) for l in open("site_substructures.smarts") if l.split()[0] not in ["Phosphate", "Phosphonate"]}
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	888 average_pkas_phos = {l.split()[0].replace("*", ""):[float(l.split()[3]), float(l.split()[6])] for l in open("site_substructures.smarts") if l.split()[0] in ["Phosphate", "Phosphonate"]}
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	889
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	890 print("Running Tests")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	891 print("=============")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	892 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	893
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	894 print("Very Acidic (pH -10000000)")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	895 print("--------------------------")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	896 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	897
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	898 args = {
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	899 "min_ph": -10000000,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	900 "max_ph": -10000000,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	901 "pka_precision": 0.5,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	902 "smiles": "",
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	903 "label_states": True
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	904 }
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	905
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	906 for smi, protonated, deprotonated, category in smis:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	907 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	908 TestFuncs.test_check(args, [protonated], ["PROTONATED"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	909
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	910 for smi, protonated, mix, deprotonated, category in smis_phos:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	911 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	912 TestFuncs.test_check(args, [protonated], ["PROTONATED"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	913
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	914 args["min_ph"] = 10000000
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	915 args["max_ph"] = 10000000
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	916
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	917 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	918 print("Very Basic (pH 10000000)")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	919 print("------------------------")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	920 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	921
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	922 for smi, protonated, deprotonated, category in smis:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	923 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	924 TestFuncs.test_check(args, [deprotonated], ["DEPROTONATED"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	925
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	926 for smi, protonated, mix, deprotonated, category in smis_phos:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	927 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	928 TestFuncs.test_check(args, [deprotonated], ["DEPROTONATED"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	929
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	930 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	931 print("pH is Category pKa")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	932 print("------------------")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	933 print("")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	934
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	935 for smi, protonated, deprotonated, category in smis:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	936 avg_pka = average_pkas[category]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	937
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	938 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	939 args["min_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	940 args["max_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	941
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	942 TestFuncs.test_check(args, [protonated, deprotonated], ["BOTH"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	943
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	944 for smi, protonated, mix, deprotonated, category in smis_phos:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	945 args["smiles"] = smi
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	946
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	947 avg_pka = average_pkas_phos[category][0]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	948 args["min_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	949 args["max_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	950
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	951 TestFuncs.test_check(args, [mix, protonated], ["BOTH"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	952
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	953 avg_pka = average_pkas_phos[category][1]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	954 args["min_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	955 args["max_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	956
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	957 TestFuncs.test_check(args, [mix, deprotonated], ["DEPROTONATED", "DEPROTONATED"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	958
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	959 avg_pka = 0.5 * (average_pkas_phos[category][0] + average_pkas_phos[category][1])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	960 args["min_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	961 args["max_ph"] = avg_pka
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	962 args["pka_precision"] = 5 # Should give all three
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	963
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	964 TestFuncs.test_check(args, [mix, deprotonated, protonated], ["BOTH", "BOTH"])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	965
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	966 @staticmethod
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	967 def test_check(args, expected_output, labels):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	968 """Tests most ionizable groups. The ones that can only loose or gain a single proton.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	969
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	970 :param args: The arguments to pass to protonate()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	971 :param expected_output: A list of the expected SMILES-strings output.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	972 :param labels: The labels. A list containing combo of BOTH, PROTONATED,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	973 DEPROTONATED.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	974 :raises Exception: Wrong number of states produced.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	975 :raises Exception: Unexpected output SMILES.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	976 :raises Exception: Wrong labels.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	977 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	978
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	979 output = list(Protonate(args))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	980 output = [o.split() for o in output]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	981
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	982 num_states = len(expected_output)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	983
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	984 if (len(output) != num_states):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	985 msg = args["smiles"] + " should have " + str(num_states) + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	986 " states at at pH " + str(args["min_ph"]) + ": " + str(output)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	987 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	988 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	989
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	990 if (len(set([l[0] for l in output]) - set(expected_output)) != 0):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	991 msg = args["smiles"] + " is not " + " AND ".join(expected_output) + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	992 " at pH " + str(args["min_ph"]) + " - " + str(args["max_ph"]) + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	993 "; it is " + " AND ".join([l[0] for l in output])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	994 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	995 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	996
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	997 if (len(set([l[1] for l in output]) - set(labels)) != 0):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	998 msg = args["smiles"] + " not labeled as " + " AND ".join(labels) + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	999 "; it is " + " AND ".join([l[1] for l in output])
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1000 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1001 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1002
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1003 ph_range = sorted(list(set([args["min_ph"], args["max_ph"]])))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1004 ph_range_str = "(" + " - ".join("{0:.2f}".format(n) for n in ph_range) + ")"
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1005 print("(CORRECT) " + ph_range_str.ljust(10) + " " + args["smiles"] + " => " + " AND ".join([l[0] for l in output]))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1006
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1007 def run(**kwargs):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1008 """A helpful, importable function for those who want to call Dimorphite-DL
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1009 from another Python script rather than the command line. Note that this
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1010 function accepts keyword arguments that match the command-line parameters
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1011 exactly. If you want to pass and return a list of RDKit Mol objects, import
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1012 run_with_mol_list() instead.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1013
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1014 :param **kwargs: For a complete description, run dimorphite_dl.py from the
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1015 command line with the -h option.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1016 :type kwargs: dict
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1017 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1018
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1019 # Run the main function with the specified arguments.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1020 main(kwargs)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1021
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1022 def run_with_mol_list(mol_lst, **kwargs):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1023 """A helpful, importable function for those who want to call Dimorphite-DL
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1024 from another Python script rather than the command line. Note that this
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1025 function is for passing Dimorphite-DL a list of RDKit Mol objects, together
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1026 with command-line parameters. If you want to use only the same parameters
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1027 that you would use from the command line, import run() instead.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1028
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1029 :param mol_lst: A list of rdkit.Chem.rdchem.Mol objects.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1030 :type mol_lst: list
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1031 :raises Exception: If the **kwargs includes "smiles", "smiles_file",
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1032 "output_file", or "test" parameters.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1033 :return: A list of properly protonated rdkit.Chem.rdchem.Mol objects.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1034 :rtype: list
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1035 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1036
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1037 # Do a quick check to make sure the user input makes sense.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1038 for bad_arg in ["smiles", "smiles_file", "output_file", "test"]:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1039 if bad_arg in kwargs:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1040 msg = "You're using Dimorphite-DL's run_with_mol_list(mol_lst, " + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1041 "**kwargs) function, but you also passed the \"" + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1042 bad_arg + "\" argument. Did you mean to use the " + \
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1043 "run(**kwargs) function instead?"
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1044 print(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1045 raise Exception(msg)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1046
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1047 # Set the return_as_list flag so main() will return the protonated smiles
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1048 # as a list.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1049 kwargs["return_as_list"] = True
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1050
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1051 # Having reviewed the code, it will be very difficult to rewrite it so
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1052 # that a list of Mol objects can be used directly. Intead, convert this
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1053 # list of mols to smiles and pass that. Not efficient, but it will work.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1054 protonated_smiles_and_props = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1055 for m in mol_lst:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1056 props = m.GetPropsAsDict()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1057 kwargs["smiles"] = Chem.MolToSmiles(m, isomericSmiles=True)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1058 protonated_smiles_and_props.extend(
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1059 [(s.split("\t")[0], props) for s in main(kwargs)]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1060 )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1061
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1062 # Now convert the list of protonated smiles strings back to RDKit Mol
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1063 # objects. Also, add back in the properties from the original mol objects.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1064 mols = []
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1065 for s, props in protonated_smiles_and_props:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1066 m = Chem.MolFromSmiles(s)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1067 if m:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1068 for prop, val in props.items():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1069 if type(val) is int:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1070 m.SetIntProp(prop, val)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1071 elif type(val) is float:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1072 m.SetDoubleProp(prop, val)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1073 elif type(val) is bool:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1074 m.SetBoolProp(prop, val)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1075 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1076 m.SetProp(prop, str(val))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1077 mols.append(m)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1078 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1079 UtilFuncs.eprint("WARNING: Could not process molecule with SMILES string " + s + " and properties " + str(props))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1080
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1081 return mols
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1082
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1083 if __name__ == "__main__":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06" bgruening parents: diff changeset	1084 main()

Mercurial > repos > bgruening > enumerate_charges

annotate dimorphite_dl.py @ 1:d84dc786ccb9 draft