binding-affinity

Binding Affinity Prediction

Overview

This skill predicts protein-ligand binding affinity from docked poses — converting structural information into estimated ΔG (kcal/mol), pKd, and Kd (nM). It complements the molecular-docking skill's interaction analysis (score.py) which counts contacts but does NOT predict binding strength in energy units.

Key capabilities:

• Empirical scoring: descriptor + contact-based affinity prediction using RDKit and BioPython
• Ligand energy inspection: explicitly selected RDKit heuristic; it does not calculate receptor-dependent binding energy
• Full MM/GBSA: use a separately validated external method; the bundled script does not implement it
• Consensus scoring: combine multiple scoring methods with rank-based normalization
• Batch virtual screening: efficiently score large compound libraries

Validation Warning

All predictions from this skill are computational estimates, NOT experimentally validated measurements.

• Empirical scoring (predict.py): typical error is 1-2 log units pKd (~10-100x in Kd)
• The bundled ligand heuristic cannot establish binding affinity or receptor-dependent ranking
• Use for prioritizing compounds for experimental testing, not for making clinical claims

The scripts include uncertainty ranges and confidence flags to help calibrate expectations.

Output Integrity

Script outputs are RAW computational estimates. The agent MUST NOT:

• Apply "calibration" or scaling to raw pKd/Kd values
• Adjust values to match known experimental data
• Add fields like "calibrated_pKd" not produced by the script
• Present approximate methods (simplified MM/GBSA) as full implementations

The raw output IS the prediction. Report it exactly as produced.

Successful script outputs are logged to _script_manifest.jsonl. A failed rescoring run may retain a JSON artifact with explicit failed records and exits nonzero; it does not write a success manifest entry. Verify the exit status and record status before using a score.