pharmacophore-modeling

Name: pharmacophore-modeling
Author: GPTomics

1.1kstars185forks

How to install pharmacophore-modeling?

gptomics/bioskills/pharmacophore-modeling

$npx -y skills add GPTomics/bioSkills --skill pharmacophore-modeling

Installs into the current project.

Summary

Builds and applies 3D pharmacophore models using RDKit Pharm3D, the apo2ph4 receptor-based workflow (Heider et al. 2023), Pharmer / Pharmit for search, and PharmacoForge for protein-pocket-conditioned pharmacophore generation (Flynn et al. 2025), covering ligand-based pharmacopho

Files · 1

View on GitHub

SKILL.md

1	## Version Compatibility
2
3	Reference examples tested with: RDKit 2024.09+, Pharmit web service, and PLIP 2.4+ (interaction analysis). Verify the deployed Pharmit/Pharmer interface and query format before automation.
4
5	Before using code patterns, verify installed versions match. If versions differ:
6	- Python: `pip show rdkit` then `help(rdkit.Chem.Pharm3D)` to check signatures
7
8	If code throws ImportError, AttributeError, or TypeError, introspect the installed
9	package and adapt the example to match the actual API rather than retrying.
10
11	# Pharmacophore Modeling
12
13	Build 3D pharmacophore queries that capture the essential interaction features of a ligand-target binding event. A pharmacophore is the spatial arrangement of pharmacophore features (donor, acceptor, hydrophobe, aromatic, charged) sufficient for activity, abstracted from any specific chemotype. Use pharmacophores for scaffold hopping, virtual-screening prefilters, and cross-target SAR transfer. Derive interaction features directly from a co-crystal when available, use apo2ph4 to derive models from an apo pocket (Heider et al. 2023), or align known actives for a ligand-based model. PharmacoForge generates candidate 3D pharmacophores conditioned on a protein pocket; those pharmacophores can then retrieve matching molecules from a library (Flynn et al. 2025).
14
15	For 2D scaffold-based searches, see `chemoinformatics/scaffold-analysis`. For 3D shape similarity, see `chemoinformatics/shape-similarity`. For protein-ligand interaction analysis, see `chemoinformatics/virtual-screening`.
16
17	## Pharmacophore Feature Types
18
19	\| Feature \| Common shorthand \| Definition \| Geometric tolerance \|
20	\|---------\|------------\|------------\|----------------------\|
21	\| H-bond donor \| D \| -OH, -NH \| 1.0-1.5 Å \|
22	\| H-bond acceptor \| A \| sp2 O / N (lone pair) \| 1.0-1.5 Å \|
23	\| Hydrophobe \| H \| sp3 C / aromatic ring centroid \| 1.5-2.0 Å \|
24	\| Aromatic ring \| R \| Aromatic ring centroid + normal \| 1.0-1.5 Å \|
25	\| Positive ionizable \| P \| -NH3+, -NR3+ \| 1.0-1.5 Å \|
26	\| Negative ionizable \| N \| -COO-, -SO3- \| 1.0-1.5 Å \|
27	\| Halogen \| X \| Cl, Br, I (halogen bond donor) \| 1.0-1.5 Å \|
28	\| Metal coordination \| M \| sp/sp2 N/O near metal \| 0.5-1.0 Å \|
29
30	Tolerances are pharmacophore-feature distance windows in the search. Tighter tolerances = fewer hits but more specific.
31
32	The ranges in this table are repository starting heuristics, not universal feature tolerances. Set final bounds from aligned-feature variability, coordinate uncertainty, and retrospective validation for the selected search engine.
33
34	The one-letter labels above are human-readable shorthand, not RDKit API codes. RDKit's shipped `BaseFeatures.fdef` uses family names such as `Donor`, `Acceptor`, `Hydrophobe`, `Aromatic`, `PosIonizable`, and `NegIonizable`. Its default feature definitions do not provide every halogen-bond or metal-coordination model; add and validate project-specific feature definitions when those interactions matter.
35
36	## Method Taxonomy
37
38	\| Method \| Origin \| Use case \| Fails when \|
39	\|--------\|--------\|----------\|------------\|
40	\| Ligand-based (LBP) \| Catalyst, MOE, RDKit Pharm3D \| Multiple actives, no crystal \| <3 actives; flexible actives \|
41	\| Receptor-based (RBP) \| apo2ph4, LigandScout, PLIP \| Co-crystal or a defined apo pocket \| Uncertain pocket conformation \|
42	\| Common pharmacophore \| Validated alignment/feature-consensus workflow; RDKit can represent and query the resulting model \| Consensus from active set \| Diverse actives or uncertain bioactive conformers confound alignment \|
43	\| Pocket-conditioned generation (PharmacoForge) \| Flynn et al. 2025 \| Generate candidate pharmacophores from a protein pocket \| Does not directly generate molecules; pretrained model required \|
44	\| Active learning pharmacophore \| Catalyst variant \| Iterative refinement \| Custom; not standard \|
45
46	## Decision Tree by Scenario
47
48	\| Scenario \| Method \| Tools \|
49	\|----------\|--------\|-------\|
50	\| Co-crystal structure available \| Interaction-derived receptor model \| PLIP or LigandScout + Pharmit \|
51	\| Apo structure with a defined pocket \| Apo receptor model \| apo2ph4; export LigandScout PML \|
52	\| Multiple active compounds, no crystal \| Ligand-based common pharmacophore \| Alignment plus consensus-feature derivation in validated custom or external tooling; RDKit Pharm3D can apply

People who liked this also viewed

6 picks

Type

pharmacophore-modeling

1.1kstars185forks

View on GitHub

How to install pharmacophore-modeling?

gptomics/bioskills/pharmacophore-modeling

$npx -y skills add GPTomics/bioSkills --skill pharmacophore-modeling

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Version Compatibility
2
3	Reference examples tested with: RDKit 2024.09+, Pharmit web service, and PLIP 2.4+ (interaction analysis). Verify the deployed Pharmit/Pharmer interface and query format before automation.
4
5	Before using code patterns, verify installed versions match. If versions differ:
6	- Python: `pip show rdkit` then `help(rdkit.Chem.Pharm3D)` to check signatures
7
8	If code throws ImportError, AttributeError, or TypeError, introspect the installed
9	package and adapt the example to match the actual API rather than retrying.
10
11	# Pharmacophore Modeling
12
13	Build 3D pharmacophore queries that capture the essential interaction features of a ligand-target binding event. A pharmacophore is the spatial arrangement of pharmacophore features (donor, acceptor, hydrophobe, aromatic, charged) sufficient for activity, abstracted from any specific chemotype. Use pharmacophores for scaffold hopping, virtual-screening prefilters, and cross-target SAR transfer. Derive interaction features directly from a co-crystal when available, use apo2ph4 to derive models from an apo pocket (Heider et al. 2023), or align known actives for a ligand-based model. PharmacoForge generates candidate 3D pharmacophores conditioned on a protein pocket; those pharmacophores can then retrieve matching molecules from a library (Flynn et al. 2025).
14
15	For 2D scaffold-based searches, see `chemoinformatics/scaffold-analysis`. For 3D shape similarity, see `chemoinformatics/shape-similarity`. For protein-ligand interaction analysis, see `chemoinformatics/virtual-screening`.
16
17	## Pharmacophore Feature Types
18
19	\| Feature \| Common shorthand \| Definition \| Geometric tolerance \|
20	\|---------\|------------\|------------\|----------------------\|
21	\| H-bond donor \| D \| -OH, -NH \| 1.0-1.5 Å \|
22	\| H-bond acceptor \| A \| sp2 O / N (lone pair) \| 1.0-1.5 Å \|
23	\| Hydrophobe \| H \| sp3 C / aromatic ring centroid \| 1.5-2.0 Å \|
24	\| Aromatic ring \| R \| Aromatic ring centroid + normal \| 1.0-1.5 Å \|
25	\| Positive ionizable \| P \| -NH3+, -NR3+ \| 1.0-1.5 Å \|
26	\| Negative ionizable \| N \| -COO-, -SO3- \| 1.0-1.5 Å \|
27	\| Halogen \| X \| Cl, Br, I (halogen bond donor) \| 1.0-1.5 Å \|
28	\| Metal coordination \| M \| sp/sp2 N/O near metal \| 0.5-1.0 Å \|
29
30	Tolerances are pharmacophore-feature distance windows in the search. Tighter tolerances = fewer hits but more specific.
31
32	The ranges in this table are repository starting heuristics, not universal feature tolerances. Set final bounds from aligned-feature variability, coordinate uncertainty, and retrospective validation for the selected search engine.
33
34	The one-letter labels above are human-readable shorthand, not RDKit API codes. RDKit's shipped `BaseFeatures.fdef` uses family names such as `Donor`, `Acceptor`, `Hydrophobe`, `Aromatic`, `PosIonizable`, and `NegIonizable`. Its default feature definitions do not provide every halogen-bond or metal-coordination model; add and validate project-specific feature definitions when those interactions matter.
35
36	## Method Taxonomy
37
38	\| Method \| Origin \| Use case \| Fails when \|
39	\|--------\|--------\|----------\|------------\|
40	\| Ligand-based (LBP) \| Catalyst, MOE, RDKit Pharm3D \| Multiple actives, no crystal \| <3 actives; flexible actives \|
41	\| Receptor-based (RBP) \| apo2ph4, LigandScout, PLIP \| Co-crystal or a defined apo pocket \| Uncertain pocket conformation \|
42	\| Common pharmacophore \| Validated alignment/feature-consensus workflow; RDKit can represent and query the resulting model \| Consensus from active set \| Diverse actives or uncertain bioactive conformers confound alignment \|
43	\| Pocket-conditioned generation (PharmacoForge) \| Flynn et al. 2025 \| Generate candidate pharmacophores from a protein pocket \| Does not directly generate molecules; pretrained model required \|
44	\| Active learning pharmacophore \| Catalyst variant \| Iterative refinement \| Custom; not standard \|
45
46	## Decision Tree by Scenario
47
48	\| Scenario \| Method \| Tools \|
49	\|----------\|--------\|-------\|
50	\| Co-crystal structure available \| Interaction-derived receptor model \| PLIP or LigandScout + Pharmit \|
51	\| Apo structure with a defined pocket \| Apo receptor model \| apo2ph4; export LigandScout PML \|
52	\| Multiple active compounds, no crystal \| Ligand-based common pharmacophore \| Alignment plus consensus-feature derivation in validated custom or external tooling; RDKit Pharm3D can apply

People who liked this also viewed

6 picks

Type