drug-docking-analysis
OfficialQuantify docking screens with enrichment metrics.
Education & Research#virtual screening#drug discovery#docking analysis#enrichment metrics#ligand efficiency#ROC AUC#microstate aggregation
Authorlearningmatter-mit
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It turns virtual screening docking outputs into quantitative evidence for how well your ranked compounds discriminate actives from inactives, while also characterizing score bias and ligand efficiency.
Core Features & Use Cases
- Score distribution analysis: Produces KDE and histogram views of docking score spread to assess how “deep” and structured the screen is.
- Ligand efficiency calculations: Computes LE, BEI, and SEI from docking scores and molecular properties to compare efficiency across sizes.
- Enrichment evaluation (when labels exist): Computes ROC AUC and enrichment factors (EF at multiple early cutoffs) to measure early recognition quality.
- Microstate aggregation guardrail: Optionally collapses enumerated microstates to best-score-per-parent to avoid double-counting and inflated enrichment.
Quick Start
Use the drug-docking-analysis skill to analyze a prepared ranked docking CSV at docking/analysis by running: python .agents/skills/drug-docking-analysis/scripts/analyze_docking.py --docking_csv docking/docking_ranked.csv --output_dir docking/analysis/.
Dependency Matrix
Required Modules
rdkitnumpyscipymatplotlib
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: drug-docking-analysis Download link: https://github.com/learningmatter-mit/AtomisticSkills/archive/main.zip#drug-docking-analysis Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.