How to create a pharmacophore modeling report
1. Add active ligandsPaste known active molecules with SMILES and IDs.
2. Extract 3D featuresGenerate RDKit 3D conformers and pharmacophore feature centers.
3. Build consensus modelCluster supported features across ligands with tolerance and support.
4. Search & reportScreen compounds, validate active/inactive separation, export report.
This is a strong research workflow for pharmacophore hypothesis generation. For final publication-grade use,
validate with bioactive conformations, conformer ensembles, alignment, actives/inactives, docking, SAR, and experiments.
Scientific guardrails
First-pass ligand-based pharmacophore modeling should not be overclaimed. Coordinate clustering is useful for triage,
but formal alignment and conformer-ensemble screening are needed for stronger scientific claims.
HBA
HBD
HYD
ARO
POS
NEG
HAL
User outputs
3D feature table
Consensus model
Query export
Search results
JSON / HTML / Word / CSV
Share report
Active Ligands
3D Feature Map
Extract or build a model to see a 2D projection of 3D pharmacophore feature centers.
HBAHBDHYDAROPOSNEGHAL
Consensus Pharmacophore Model
Build a ligand-based consensus model from supported pharmacophore features across active ligands.
Query JSON
The model/query is automatically copied here after building or exporting.
Screening Database
Search Summary
Build a query/model and search a screening database to see ranked pharmacophore matches.
Active vs Inactive Comparison
Validation Interpretation
A useful pharmacophore should fit known actives better than inactives or decoys. A positive active-inactive score separation improves confidence, but does not replace experimental validation.
Distance Matrix
Model Geometry
Use feature-feature distances to understand the 3D pharmacophore geometry and export query constraints.
Pharmacophore Feature Types
Complete Report Center
Create a complete pharmacophore modeling report, then view it here or download/share it.
Raw JSON
{}