tiantz17/molshap

Source code for paper "MolSHAP: Interpreting Structure-Activity Relationships for Compound Optimization"

molshap's Issues

about the selected compounds in Figure 7.D. of paper

hi,

Thanks so much for providing such an interesting and helpful approach. For utilizing the molshap method, picking out three compounds is mentioned in the article. Could you please provide explanation what criteria or method was used to select these three compounds? Is the activity listed in the article the result after the actual bioassay?

Additionally, what is the ranking of compounds in the generated - opt. csv file based on? Is it uncertainy SD?

many thanks,

Sh-Y

Questions about how to read files

Thank you for developing the tool, which will be very helpful for my research. But my skills are limited, I would like to ask how to read the following files: demo_contrib.pk demo_contrib_by_smiles.pk demo_decomp.pk demo_frag2idx.pk

KeyError: 137 testing building model on demo example

Hello!

I have been testing the tool on an M2 Mac under a new conda env with Python 3.7, rdkit and shap installed.
During the step 3 of your example demo I get this error:

python molshap.py -i ./demo/demo.csv -o ./demo/ 
MolSHAP analysis for ./demo/demo.csv
Using 166 compounds for analysis.
------------------------------------------------------------
Side-chain candidates:
Core: 3
R1: 19
R2: 10
R3: 37
R4: 25
R5: 43
------------------------------------------------------------
Side-chain ranking pairs:
R5: 683
R4: 176
R3: 172
R1: 106
R2: 35
Core: 3
------------------------------------------------------------
Core background: O=C1[C@@H](N[*:5])C([*:4])c2c([*:3])nn([*:2])c2N1[*:1]
R1 background: [H][*:1]
R2 background: CCC[*:2]
R3 background: [H][*:3]
R4 background: c1nscc1[*:4]
R5 background: [H][*:5]
------------------------------------------------------------
Model training
{'Regression': {'PCC': 0.7657683761965741, 'R2': 0.5547096104081453}}
------------------------------------------------------------
Model analysing
Traceback (most recent call last):
  File "molshap.py", line 238, in <module>
    shap_diff = dict_shap_rule[frag2idx[rule[3]]] - dict_shap_rule[frag2idx[rule[4]]]
KeyError: 137

Any particular reason why?

Many thanks!

Documentation: Your publication

Hello:
Fist of all, thank you for making MolSHAP available t the community.
I am very interested in your work and would like to read the original publication.
Unfortunately, this article is behind a paywall.
Is there a way you can provide me with a preprint?
Many thanks in advance,
Markus

Error 'Explicit valence for atom'

Hi,
Thanks for your Nice work.
I'm trying to build my own model with some ligands. However, no matter what kind of software I use(including chemdraw and Chem3D) to create smiles file, the valence error keep appears, and I don't know how to solve this problem, Please help me.
example molecule: O=C(Nc1cccc(CC(O)(C(=O)O)[C@H]2CCNC2)c1)Nc1cccc(CC(O)(C(=O)O)[C@H]2CCNC2)c1
Error message
Model training [15:51:11] Explicit valence for atom # 3 C, 5, is greater than permitted Traceback (most recent call last): File "molshap.py", line 163, in <module> molshap.train_onehot(ori_idx[train_idx], y_ori[train_idx]) File "/home/wsr/MolSHAP-master/model.py", line 51, in train_onehot list_mol = [makebond(item)[0] for item in self.list_frag_mol[ori_idx]] File "/home/wsr/MolSHAP-master/model.py", line 51, in <listcomp> list_mol = [makebond(item)[0] for item in self.list_frag_mol[ori_idx]] File "/home/wsr/MolSHAP-master/utils.py", line 145, in makebond newmol.UpdatePropertyCache() rdkit.Chem.rdchem.AtomValenceException: Explicit valence for atom # 3 C, 5, is greater than permitted

segmentation fault also appears.
Thanks!