drug-pose-validation

Official

Filter ligand poses by physical plausibility

Authorlearningmatter-mit
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It eliminates wasted compute on chemically invalid or sterically impossible ligand poses by validating pose geometry and clashes before downstream refinement.

Core Features & Use Cases

  • PoseBusters-based plausibility checks: bond lengths/angles, planarity/flatness, stereochemistry, and internal ligand clashes using PoseBusters.
  • Optional receptor-aware clash screening: when a receptor PDB is provided, it also filters protein–ligand steric clashes using PoseBusters in dock mode.
  • Deterministic outputs for triage: generates a per-pose JSON validation report, a human-readable summary, and an SDF containing only valid poses.

Quick Start

Run pose validation on your docked ligand poses by converting them to SDF if needed and then executing the validate_poses.py script with the poses SDF, an optional receptor PDB, and an output directory.

Dependency Matrix

Required Modules

posebustersrdkit

Components

scripts

đź’» 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-pose-validation
Download link: https://github.com/learningmatter-mit/AtomisticSkills/archive/main.zip#drug-pose-validation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.