compbio-diffdock-docking

Automate toxin-receptor docking benchmarking with DiffDock and RDKit.

934|152|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/wuyoscar/ISC-Bench --skill compbio-diffdock-docking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compbio-diffdock-docking
Source: https://github.com/wuyoscar/ISC-Bench/tree/main/templates/compbio_diffdock
Command: npx skills add https://github.com/wuyoscar/ISC-Bench --skill compbio-diffdock-docking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a turnkey toxin-receptor docking benchmark using DiffDock and RDKit. It automates the generation of toxin–receptor pairs, fills SMILES strings, assigns PDB IDs and experimental Kd values, and compiles detailed binding-mode descriptions to support reproducible structural biology evaluations.

Core Features & Use Cases

  • Automated benchmarking workflow that ingests toxin-receptor pairs and outputs standardized docking data (SMILES, PDB IDs, Kd, and binding-mode narratives).
  • Deterministic, repeatable results suitable for validation, comparison across models, and educational demonstrations in pharmacology and structural biology.
  • Validation constraints integrated into the workflow, including pharmacological relevance of Kd and informative binding-mode descriptions.

Quick Start

Run the DiffDock docking benchmark using the included toxin_benchmarks.json to generate and review SMILES, PDB IDs, Kd values, and binding-mode descriptions.

Frequently Asked Questions about compbio-diffdock-docking

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I benchmark toxin-receptor docking using DiffDock?

Toxin-receptor docking benchmarks are automated using DiffDock and RDKit to generate SMILES, PDB IDs, Kd values, and binding-mode descriptions for reproducible structural biology evaluations.

Can I generate SMILES and PDB IDs for toxin docking automatically?

Yes, the docking workflow ingests toxin-receptor pairs and automatically outputs standardized SMILES strings, PDB IDs, and experimental Kd values alongside detailed binding-mode narratives.

Does this docking benchmark support deterministic and repeatable outputs?

Yes, the benchmark enforces deterministic outputs and validation constraints for Kd and binding-mode descriptions, ensuring repeatable results suitable for model comparison and pharmacology validation.

What is the best way to validate binding modes and Kd values in structural biology?

Validating binding modes and Kd values is achieved through integrated constraints that enforce pharmacological relevance and informative binding-mode descriptions during the automated docking workflow.

Are there limitations when using DiffDock for toxin-receptor docking benchmarks?

The benchmark is specifically scoped to toxin-receptor docking using DiffDock and RDKit, requiring YAML frontmatter-driven configuration and proper toxin-receptor pair inputs to function correctly.

Do I need RDKit to run a toxin-receptor docking benchmark?

Yes, RDKit is integrated into the automated workflow to handle SMILES generation and chemical structure processing alongside DiffDock for complete toxin-receptor docking benchmarking.