Skip to content

Draft: align MolOpt functions with GuacaMol implementation #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
AustinT wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

Draft: align MolOpt functions with GuacaMol implementation #47

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
1e8f192
Make all fingerprints larger.
AustinT May 18, 2024
515464e
Fix some wrong thresholds.
AustinT May 18, 2024
a7a8ab0
Fix scaffold in scaffold hop.
AustinT May 18, 2024
1a0baf7
Fix radii in legacy QSAR models.
AustinT May 18, 2024
aa3e01e
Only calculate isomers over atoms in target molecule, not query molec…
AustinT May 18, 2024
b8ce1bd
Get rid of MolOpt-DF (this is not present)
AustinT May 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Albuterol_similarity.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CC(C)(C)NCC(O)c1ccc(O)c(CO)c1"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": true,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Amlodipine_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CCOC(=O)C1=C(COCCN)NC(C)=C(C(=O)OC)C1c1ccccc1Cl"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Celecoxxib_rediscovery.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"Cc1ccc(-c2cc(C(F)(F)F)nn2-c2ccc(S(N)(=O)=O)cc2)cc1"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
6 changes: 3 additions & 3 deletions molscore/configs/MolOpt/Deco_hop.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@
"CCCOc1cc2ncnc(Nc3ccc4ncsc4c3)c2cc1S(=O)(=O)C(C)(C)C"
],
"fp": "PHCO",
"bits": 1024,
"bits": 16384,
"similarity_measure": "Tanimoto",
"method": "mean",
"n_jobs": 1
Expand Down Expand Up @@ -87,9 +87,9 @@
"modifier": "lin_thresh",
"parameters": {
"objective": "maximize",
"upper": 0.75,
"upper": 0.85,
"lower": 0.0,
"buffer": 0.75
"buffer": 0.85
}
}
]
Expand Down
6 changes: 3 additions & 3 deletions molscore/configs/MolOpt/Fexofenadine_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CC(C)(C1=CC=C(C=C1)C(CCCN2CCC(CC2)C(C3=CC=CC=C3)(C4=CC=CC=C4)O)O)C(=O)O"
],
"fp": "AP",
"bits": 1024,
"bits": 16384,
"similarity_measure": "Tanimoto",
"method": "mean",
"n_jobs": 1
Expand Down Expand Up @@ -53,7 +53,7 @@
"parameters": {
"objective": "maximize",
"mu": 90.0,
"sigma": 2.0
"sigma": 10.0
}
},
{
Expand All @@ -63,7 +63,7 @@
"parameters": {
"objective": "minimize",
"mu": 4.0,
"sigma": 2.0
"sigma": 1.0
}
}
]
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Median_molecules_1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CC1(C)[C@H]2CC[C@]1(C)C(=O)C2"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
4 changes: 2 additions & 2 deletions molscore/configs/MolOpt/Median_molecules_2.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CN1CC(=O)N2[C@H](Cc3c([nH]c4ccccc34)[C@H]2c2ccc3c(c2)OCO3)C1=O"
],
"radius": 3,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand All @@ -33,7 +33,7 @@
"CCCc1nn(C)c2c(=O)[nH]c(-c3cc(S(=O)(=O)N4CCN(C)CC4)ccc3OCC)nc12"
],
"radius": 3,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Mestranol_similarity.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CC12CCC3C(C1CCC2(C#C)O)CCC4=C3C=CC(=C4)OC"
],
"fp": "AP",
"bits": 1024,
"bits": 16384,
"similarity_measure": "Tanimoto",
"method": "mean",
"n_jobs": 1
Expand Down
10 changes: 5 additions & 5 deletions molscore/configs/MolOpt/Osimertinib_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"C=CC(=O)Nc1cc(Nc2nccc(-c3cn(C)c4ccccc34)n2)c(OC)cc1N(C)CCN(C)C"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": true,
"counts": true,
"method": "max",
Expand All @@ -33,7 +33,7 @@
"C=CC(=O)Nc1cc(Nc2nccc(-c3cn(C)c4ccccc34)n2)c(OC)cc1N(C)CCN(C)C"
],
"radius": 3,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down Expand Up @@ -70,7 +70,7 @@
"parameters": {
"objective": "minimize",
"mu": 0.85,
"sigma": 2.0
"sigma": 0.1
}
},
{
Expand All @@ -80,7 +80,7 @@
"parameters": {
"objective": "maximize",
"mu": 100.0,
"sigma": 2.0
"sigma": 10.0
}
},
{
Expand All @@ -90,7 +90,7 @@
"parameters": {
"objective": "minimize",
"mu": 1.0,
"sigma": 2.0
"sigma": 1.0
}
}
]
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Perindopril_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CCCC(C(=O)OCC)NC(C)C(=O)N1C2CCCCC2CC1C(=O)O"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Ranolazine_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CC1=C(C(=CC=C1)C)NC(=O)CN2CCN(CC2)CC(COC3=CC=CC=C3OC)O"
],
"fp": "AP",
"bits": 1024,
"bits": 16384,
"similarity_measure": "Tanimoto",
"method": "mean",
"n_jobs": 1
Expand Down
4 changes: 2 additions & 2 deletions molscore/configs/MolOpt/Scaffold_hop.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@
"parameters": {
"prefix": "S6",
"smarts": [
"[#6]-[#6]-[#6]-[#8]-[#6]\u223c[#6]\u223c[#6]\u223c[#6]\u223c[#6]-[#7]-c1ccc2ncsc2c1"
"[#6]-[#6]-[#6]-[#8]-[#6]~[#6]~[#6]~[#6]~[#6]-[#7]-c1ccc2ncsc2c1"
],
"n_jobs": 1,
"method": "any"
Expand All @@ -41,7 +41,7 @@
"CCCOc1cc2ncnc(Nc3ccc4ncsc4c3)c2cc1S(=O)(=O)C(C)(C)C"
],
"fp": "PHCO",
"bits": 1024,
"bits": 16384,
"similarity_measure": "Tanimoto",
"method": "mean",
"n_jobs": 1
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Sitagliptin_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"C1CN2C(=NN=C2C(F)(F)F)CN1C(=O)CC(CC3=CC(=C(C=C3F)F)F)N"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Thiothixene_rediscovery.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CN1CCN(CC/C=C2/c3ccccc3Sc3ccc(S(=O)(=O)N(C)C)cc32)CC1"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Troglitazone_rediscovery.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"Cc1c(C)c2OC(C)(CCc2c(C)c1O)COc1ccc(CC2SC(=O)NC2=O)cc1"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
2 changes: 1 addition & 1 deletion molscore/configs/MolOpt/Zaleplon_MPO.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
"CCN(C(C)=O)c1cccc(-c2ccnc3c(C#N)cnn23)c1"
],
"radius": 2,
"bits": 1024,
"bits": 16384,
"features": false,
"counts": true,
"method": "max",
Expand Down
1 change: 0 additions & 1 deletion molscore/manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -956,7 +956,6 @@ class MolScoreBenchmark:
"GuacaMol_Scaffold": resources.files("molscore.configs.GuacaMol_Scaffold"),
"MolOpt": resources.files("molscore.configs.MolOpt"),
"MolOpt-CF": resources.files("molscore.configs.MolOpt-CF"),
"MolOpt-DF": resources.files("molscore.configs.MolOpt-DF"),
"5HT2A_PhysChem": resources.files("molscore.configs.5HT2A.PhysChem"),
"5HT2A_Selectivity": resources.files(
"molscore.configs.5HT2A.PIDGIN_Selectivity"
Expand Down
1 change: 0 additions & 1 deletion molscore/scoring_functions/isomer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@ def calculate_isomer_score(self, smi):
query_formula = Descriptors.rdMolDescriptors.CalcMolFormula(mol)
query_elements = self.formula2elements(query_formula)
elements = set(self.ref_elements)
elements.update(query_elements)
scores = []
# Add per element scores
for e in elements:
Expand Down
8 changes: 4 additions & 4 deletions molscore/scoring_functions/legacy_qsar.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,31 +48,31 @@ class LegacyQSAR(BaseServerSF):
resources.files("molscore.data.models.molopt"),
"gsk3b.pkl",
"legacy_qsar_server.py",
"ECFP6",
"ECFP4",
2048,
),
"molopt_GSK3B_current": (
"ms_molopt_current",
resources.files("molscore.data.models.molopt"),
"gsk3b_current.pkl",
"legacy_qsar_server.py",
"ECFP6",
"ECFP4",
2048,
),
"molopt_JNK3": (
"ms_molopt",
resources.files("molscore.data.models.molopt"),
"jnk3.pkl",
"legacy_qsar_server.py",
"ECFP6",
"ECFP4",
2048,
),
"molopt_JNK3_current": (
"ms_molopt_current",
resources.files("molscore.data.models.molopt"),
"jnk3_current.pkl",
"legacy_qsar_server.py",
"ECFP6",
"ECFP4",
2048,
),
}
Expand Down