torchdrug

Develop PyTorch-based graph neural networks for drug discovery and bioinformatics tasks.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yf8578/clawomics --skill torchdrug-yf8578
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: torchdrug
Source: https://github.com/yf8578/clawomics/tree/main/skills/torchdrug
Command: npx skills add https://github.com/yf8578/clawomics --skill torchdrug-yf8578

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a powerful, PyTorch-native toolkit for building and applying graph neural networks to complex molecular and biological data, accelerating research in drug discovery and bioinformatics.

Core Features & Use Cases

  • Molecular Property Prediction: Predict drug-likeness, toxicity, or binding affinity.
  • Protein Modeling: Analyze protein sequences and structures for function prediction.
  • Knowledge Graph Reasoning: Discover new drug targets or disease mechanisms.
  • Molecular Generation: Design novel molecules with desired properties.
  • Retrosynthesis: Plan synthetic routes for target molecules.
  • Use Case: Predict the binding affinity of novel drug candidates to a specific protein target using advanced GNN architectures and curated biological datasets.

Quick Start

Use the torchdrug skill to predict molecular properties using the BBBP dataset.

Frequently Asked Questions about torchdrug

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

FAQPage Schema
How do I predict molecular properties using graph neural networks?

To predict molecular properties using graph neural networks, you can utilize this Skill to build PyTorch-based GNNs on datasets like BBBP. It facilitates predicting drug-likeness, toxicity, or binding affinity directly from molecular graphs.

What is graph neural network-based retrosynthesis planning?

Graph neural network-based retrosynthesis planning uses PyTorch models to analyze molecular structures and plan synthetic routes for target molecules. This Skill applies GNN architectures to reverse-engineer drug synthesis pathways.

Does this PyTorch drug discovery toolkit require RDKit?

Yes, this PyTorch drug discovery toolkit requires integration with the RDKit cheminformatics library. RDKit provides the necessary molecular modeling and chemical structure processing capabilities for the GNN workflows.

Can I use graph neural networks for protein analysis and function prediction?

Yes, you can use graph neural networks for protein analysis to predict protein functions. This Skill supports analyzing protein sequences and structures using PyTorch-based GNN architectures for bioinformatics tasks.

What is the best way to discover new drug targets using knowledge graphs?

The best way to discover new drug targets is through knowledge graph reasoning with PyTorch-based GNNs. This Skill enables the development of models that infer disease mechanisms and identify potential targets from complex biological graphs.

How do I generate novel molecules with desired properties using PyTorch?

To generate novel molecules with desired properties using PyTorch, this Skill provides GNN architectures for molecular generation. It allows researchers to design and synthesize new drug candidates optimized for specific biological targets.