drug-redocking-rmsd

Official

Validate docking by symmetry-corrected RMSD.

Authorlearningmatter-mit
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill determines whether an AI docking protocol can reliably reproduce a crystallographic ligand pose by computing symmetry-corrected heavy-atom RMSD between docked poses and a reference ligand.

Core Features & Use Cases

  • Symmetry-corrected in-place heavy-atom RMSD: Computes the minimum heavy-atom RMSD over molecular automorphisms without rigid-body alignment to ensure docking-valid “in-place” validation.
  • Top-poses protocol gate: Produces a pass/fail verdict based on whether the top-scored pose (pose 1) falls below a configurable RMSD threshold.
  • Ligand identity safety check: Verifies reference and docked compounds match via InChIKey connectivity so the result cannot silently compare unrelated molecules.
  • Handles common reference formats: Accepts reference ligands as PDB (requires SMILES for bond-order assignment) or SDF (bond orders included).

Quick Start

Compute the RMSD gate by running the Skill’s compute_rmsd.py on your Vina multi-model PDBQT and a crystal reference ligand file, supplying SMILES if the reference is a PDB.

Dependency Matrix

Required Modules

rdkitmeekonumpy

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-redocking-rmsd
Download link: https://github.com/learningmatter-mit/AtomisticSkills/archive/main.zip#drug-redocking-rmsd

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.