Mercurial > repos > bgruening > package_rdkit_2013_03
changeset 1:0275ed826890
Uploaded
| author | bgruening |
|---|---|
| date | Sat, 27 Apr 2013 13:21:08 -0400 |
| parents | c7f8a12d8176 |
| children | c62dbe7147ad |
| files | rdkit_descriptors.py rdkit_descriptors.xml repository_dependencies.xml tool_dependencies.xml |
| diffstat | 4 files changed, 132 insertions(+), 42 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rdkit_descriptors.py Sat Apr 27 13:21:08 2013 -0400 @@ -0,0 +1,77 @@ +#!/usr/bin/env python + +from rdkit.Chem import Descriptors +from rdkit import Chem +import sys, os, re +import argparse +import inspect + +def get_supplier( infile, format = 'smiles' ): + """ + Returns a generator over a SMILES or InChI file. Every element is of RDKit + molecule and has its original string as _Name property. + """ + with open(infile) as handle: + for line in handle: + line = line.strip() + if format == 'smiles': + mol = Chem.MolFromSmiles( line, sanitize=True ) + elif format == 'inchi': + mol = Chem.inchi.MolFromInchi( line, sanitize=True, removeHs=True, logLevel=None, treatWarningAsError=False ) + if mol is None: + yield False + else: + mol.SetProp( '_Name', line.split('\t')[0] ) + yield mol + + +def get_rdkit_descriptor_functions(): + """ + Returns all descriptor functions under the Chem.Descriptors Module as tuple of (name, function) + """ + ret = [ (name, f) for name, f in inspect.getmembers( Descriptors ) if inspect.isfunction( f ) and not name.startswith( '_' ) ] + ret.sort() + return ret + + +def descriptors( mol, functions ): + """ + Calculates the descriptors of a given molecule. + """ + for name, function in functions: + yield (name, function( mol )) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument('-i', '--infile', required=True, help='Path to the input file.') + parser.add_argument("--iformat", help="Specify the input file format.") + + parser.add_argument('-o', '--outfile', type=argparse.FileType('w+'), + default=sys.stdout, help="path to the result file, default it sdtout") + + parser.add_argument("--header", dest="header", action="store_true", + default=False, + help="Write header line.") + + args = parser.parse_args() + + if args.iformat == 'sdf': + supplier = Chem.SDMolSupplier( args.infile ) + elif args.iformat =='smi': + supplier = get_supplier( args.infile, format = 'smiles' ) + elif args.iformat == 'inchi': + supplier = get_supplier( args.infile, format = 'inchi' ) + + functions = get_rdkit_descriptor_functions() + + if args.header: + args.outfile.write( '%s\n' % '\t'.join( [name for name, f in functions] ) ) + + for mol in supplier: + if not mol: + continue + descs = descriptors( mol, functions ) + molecule_id = mol.GetProp("_Name") + args.outfile.write( "%s\n" % '\t'.join( [molecule_id]+ [str(res) for name, res in descs] ) ) +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rdkit_descriptors.xml Sat Apr 27 13:21:08 2013 -0400 @@ -0,0 +1,49 @@ +<tool id="ctb_rdkit_describtors" name="Descriptors" version="0.1"> + <description>calculated with RDKit</description> + <parallelism method="multi" split_inputs="infile" split_mode="to_size" split_size="10000" shared_inputs="" merge_outputs="outfile"></parallelism> + <requirements> + <requirement type="package" version="2012_12_1">rdkit</requirement> + </requirements> + <command interpreter="python">rdkit_descriptors.py -i "${infile}" --iformat "${infile.ext}" -o "${outfile}" $header 2>&1</command> + <inputs> + <param format="smi,sdf" name="infile" type="data" label="Molecule data in SD- or SMILES-format" help="Dataset missing? See TIP below"/> + <param name="header" type="boolean" label="Include the descriptor name as header" truevalue="--header" falsevalue="" checked="false" /> + </inputs> + <outputs> + <data format="tabular" name="outfile" /> + </outputs> + <tests> + </tests> + <help> + +.. class:: infomark + +**TIP:** If your data is not in SD- or SMILES format, use the pencil icon on your dataset to convert your data + +----- + +**Example** + +- Input file:: + + - SD-Format (http://en.wikipedia.org/wiki/Chemical_table_file) + - SMILES Format (http://en.wikipedia.org/wiki/Simplified_molecular_input_line_entry_specification) + +- Result:: + + +http://code.google.com/p/rdkit/wiki/DescriptorsInTheRDKit +http://rdkit.org/Python_Docs/rdkit.Chem.Descriptors-module.html + + +----- + + +**Cite** + +Greg Landrum +[1] RDKit: Open-source cheminformatics; http://www.rdkit.org + + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/repository_dependencies.xml Sat Apr 27 13:21:08 2013 -0400 @@ -0,0 +1,4 @@ +<?xml version="1.0"?> +<repositories description="This requires the Molecule datatype definitions (e.g. SMILES, InChI, SD-format)."> + <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="molecule_datatypes" owner="bgruening" changeset_revision="bc6a7eeb7c32" /> +</repositories>
--- a/tool_dependencies.xml Sat Apr 27 13:09:10 2013 -0400 +++ b/tool_dependencies.xml Sat Apr 27 13:21:08 2013 -0400 @@ -1,45 +1,5 @@ <tool_dependency> - <package name="numpy" version="1.7.1"> - <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="package_numpy_1_7" owner="bgruening" changeset_revision="c3041382815c" prior_installation_required="True" /> - </package> - <package name="boost" version="1.53.0"> - <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="package_boost_1_53" owner="bgruening" changeset_revision="f4209b50c801" prior_installation_required="True" /> - </package> - - <package name="rdkit" version="2013_03_1"> - <install version="1.0"> - <actions> - <!-- first action is always downloading --> - <action type="download_by_url">http://rdkit.googlecode.com/files/RDKit_2013_03_1.tgz</action> - - <!-- populate the environment variables from the dependend repos --> - <action type="set_environment_for_install"> - <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="package_numpy_1_7" owner="bgruening" changeset_revision="c3041382815c"> - <package name="numpy" version="1.7.1" /> - </repository> - </action> - <action type="set_environment_for_install"> - <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="package_boost_1_53" owner="bgruening" changeset_revision="f4209b50c801"> - <package name="boost" version="1.53.0" /> - </repository> - </action> - - <action type="shell_command">export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:`pwd`/lib/ && - export PYTHONPATH=$PYTHONPATH:`pwd`/ && - mkdir build && - cd build && - cmake .. -DBOOST_ROOT=$BOOST_ROOT_DIR -DCMAKE_INSTALL_PREFIX=$INSTALL_DIR/rdkit/ -DRDK_INSTALL_INTREE=OFF</action> - <action type="shell_command">cd ./build && make </action> - <action type="shell_command">cd ./build && make install</action> - - <action type="set_environment"> - <environment_variable name="RDBASE" action="set_to">$INSTALL_DIR/rdkit</environment_variable> - <environment_variable name="LD_LIBRARY_PATH" action="append_to">$INSTALL_DIR/rdkit</environment_variable> - <environment_variable name="PATH" action="prepend_to">$INSTALL_DIR/rdkit/bin</environment_variable> - <environment_variable name="PYTHONPATH" action="prepend_to">$INSTALL_DIR/rdkit/lib/</environment_variable> - </action> - </actions> - </install> - <readme>Compiling rdkit requires cmake, python headers, sqlite3, flex and bison.</readme> + <package name="rdkit" version="2012_12_1"> + <repository toolshed="http://testtoolshed.g2.bx.psu.edu/" name="package_rdkit_2013_03" owner="bgruening" changeset_revision="c7f8a12d8176" prior_installation_required="True" /> </package> </tool_dependency>