Mercurial > repos > bgruening > sucos_clustering

annotate sucos_max.py @ 3:3bf41c6bd356 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
author bgruening
date Mon, 06 Apr 2020 13:07:56 +0000
parents 3120058a3058
children 2b60b2b236a4
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
1 #!/usr/bin/env python
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
2 """
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
3 Assess ligands against a second set of molecules using SuCOS scores.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
4 This is a quite specialised function that is designed to take a set of potential follow up
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
5 compounds and compare them to a set of clustered fragment hits to help identify which follow up
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
6 ligands best map to the binding space of the hits.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
7
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
8 The clustering of the fragment hits is expected to be performed with the sucos_cluster.py module
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
9 and will generate a set of SD files, one for each cluster of hits (presumably corresponding to a
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
10 binding pocket in the protein target).
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
11
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
12 Each molecule in the input ligands is then compared (using SuCOS) to each hit in the clusters. There
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
13 are different modes which determine how the ligand is assessed.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
14
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
15 In mode 'max' the hit with the best SuCOS score is identified. The output is a SD file with each of the ligands,
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
16 with these additional fields for each molecule:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
17 Max_SuCOS_Score - the best score
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
18 Max_SuCOS_FeatureMap_Score - the feature map score for the hit that has the best SuCOS score
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
19 Max_SuCOS_Protrude_Score - the protrude volume for the hit that has the best SuCOS score
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
20 Max_SuCOS_Cluster - the name of the cluster SD file that contains the best hit
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
21 Max_SuCOS_Index - the index of the best hit in the SD file
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
22
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
23 In mode 'cum' the sum of all the scores is calculated and reported as the following properties for each molecule:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
24 Cum_SuCOS_Score property: the sum of the SuCOS scores
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
25 Cum_SuCOS_FeatureMap_Score: the sum of the feature map scores
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
26 Cum_SuCOS_Protrude_Score: the sum of the protrude volume scores
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
27
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
28 If a molecule has no alignment to any of the clustered hits (all alignment scores of zero) then it is not
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
29 included in the results.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
30
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
31
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
32 SuCOS is the work of Susan Leung.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
33 GitHub: https://github.com/susanhleung/SuCOS
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
34 Publication: https://doi.org/10.26434/chemrxiv.8100203.v1
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
35 """
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
36
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
37 import sucos, utils
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
38 import argparse, gzip, os
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
39 from rdkit import Chem
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
40
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
41
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
42 def process(inputfilename, clusterfilenames, outputfilename):
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
43 all_clusters = {}
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
44 for filename in clusterfilenames:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
45 cluster = []
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
46 cluster_file = utils.open_file_for_reading(filename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
47 suppl = Chem.ForwardSDMolSupplier(cluster_file)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
48 i = 0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
49 for mol in suppl:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
50 i += 1
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
51 if not mol:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
52 utils.log("WARNING: failed to generate molecule", i, "in cluster", filename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
53 continue
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
54 try:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
55 features = sucos.getRawFeatures(mol)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
56 cluster.append((mol, features))
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
57 except:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
58 utils.log("WARNING: failed to generate features for molecule", i, "in cluster", filename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
59
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
60 cluster_file.close()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
61 all_clusters[filename] = cluster
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
62
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
63 input_file = utils.open_file_for_reading(inputfilename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
64 suppl = Chem.ForwardSDMolSupplier(input_file)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
65 output_file = utils.open_file_for_writing(outputfilename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
66 writer = Chem.SDWriter(output_file)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
67
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
68 comparisons = 0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
69 mol_num = 0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
70
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
71 for mol in suppl:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
72 mol_num += 1
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
73 if not mol:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
74 utils.log("WARNING: failed to generate molecule", mol_num, "in input")
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
75 continue
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
76 try:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
77 query_features = sucos.getRawFeatures(mol)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
78 except:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
79 utils.log("WARNING: failed to generate features for molecule", mol_num, "in input")
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
80 continue
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
81 scores_max = [0, 0, 0]
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
82 scores_cum = [0, 0, 0]
3
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
83 cluster_name = None
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
84 for clusterfilename in all_clusters:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
85 cluster = all_clusters[clusterfilename]
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
86 index = 0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
87 for entry in cluster:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
88 hit = entry[0]
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
89 ref_features = entry[1]
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
90 index += 1
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
91 comparisons += 1
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
92 sucos_score, fm_score, vol_score = sucos.get_SucosScore(hit, mol,
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
93 tani=False, ref_features=ref_features,
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
94 query_features=query_features)
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
95
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
96 if sucos_score > scores_max[0]:
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
97 scores_max[0] = sucos_score
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
98 scores_max[1] = fm_score
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
99 scores_max[2] = vol_score
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
100 cluster_name = clusterfilename
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
101 cluster_index = index
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
102
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
103 scores_cum[0] += sucos_score
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
104 scores_cum[1] += fm_score
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
105 scores_cum[2] += vol_score
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
106
2
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
107
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
108 # utils.log("Max SuCOS:", scores[0], "FM:", scores[1], "P:", scores[2],"File:", cluster_file_name_only, "Index:", cluster_index)
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
109 mol.SetDoubleProp("Max_SuCOS_Score", scores_max[0] if scores_max[0] > 0 else 0)
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
110 mol.SetDoubleProp("Max_SuCOS_FeatureMap_Score", scores_max[1] if scores_max[1] > 0 else 0)
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
111 mol.SetDoubleProp("Max_SuCOS_Protrude_Score", scores_max[2] if scores_max[2] > 0 else 0)
3
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
112
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
113 if cluster_name:
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
114 cluster_file_name_only = cluster_name.split(os.sep)[-1]
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
115 mol.SetProp("Max_SuCOS_Cluster", cluster_file_name_only)
3bf41c6bd356 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 2a74332a201fa9bb53f8e7dc3cc497f653d12929"
bgruening
parents: 2
diff changeset
116 mol.SetIntProp("Max_SuCOS_Index", cluster_index)
2
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
117
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
118 # utils.log("Cum SuCOS:", scores[0], "FM:", scores[1], "P:", scores[2])
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
119 mol.SetDoubleProp("Cum_SuCOS_Score", scores_cum[0] if scores_cum[0] > 0 else 0)
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
120 mol.SetDoubleProp("Cum_SuCOS_FeatureMap_Score", scores_cum[1] if scores_cum[1] > 0 else 0)
3120058a3058 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 8542cbcae3ebed4cb9a6c20b1fabd418a6efb7e8"
bgruening
parents: 1
diff changeset
121 mol.SetDoubleProp("Cum_SuCOS_Protrude_Score", scores_cum[2] if scores_cum[2] > 0 else 0)
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
122
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
123 writer.write(mol)
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
124
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
125 input_file.close()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
126 writer.flush()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
127 writer.close()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
128 output_file.close()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
129
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
130 utils.log("Completed", comparisons, "comparisons")
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
131
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
132
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
133 ### start main execution #########################################
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
134
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
135 def main():
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
136 parser = argparse.ArgumentParser(description='Max SuCOS scores with RDKit')
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
137 parser.add_argument('-i', '--input', help='Input file to score in SDF format. Can be gzipped (*.gz).')
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
138 parser.add_argument('-o', '--output', help='Output file in SDF format. Can be gzipped (*.gz).')
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
139 parser.add_argument('clusters', nargs='*', help="One or more SDF files with the clustered hits")
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
140
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
141 args = parser.parse_args()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
142 utils.log("Max SuCOS Args: ", args)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
143
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
144 process(args.input, args.clusters, args.output)
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
145
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
146
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
147 if __name__ == "__main__":
1
dbfcc048cbbc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 6f1ee2812cca091561a2b2e464498dae2f913b8d"
bgruening
parents: 0
diff changeset
148 main()