skills.rest
hxk622
hxk622COMMUNITY
Explore all skills by this author →
GitHub

torchdrug

Develop custom GNN architectures for molecular and protein data using PyTorch.

8|Updated Jan 13, 2026
Search Tags:#drug discovery#cheminformatics#graph neural networks#molecular modeling#knowledge graphs#protein analysis
One-click install
npx skills add https://github.com/hxk622/TokenDance --skill torchdrug-hxk622
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: torchdrug
Source: https://github.com/hxk622/TokenDance/tree/main/backend/app/skills/builtin/scientific/chemistry/torchdrug
Command: npx skills add https://github.com/hxk622/TokenDance --skill torchdrug-hxk622

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies the development of advanced machine learning models, specifically Graph Neural Networks (GNNs), for complex scientific domains like drug discovery and molecular biology.

Core Features & Use Cases

  • Molecular Property Prediction: Predict properties like solubility, toxicity, or binding affinity.
  • Protein Modeling: Analyze protein sequences and structures for function prediction.
  • Knowledge Graph Reasoning: Discover relationships in biomedical data for drug repurposing.
  • Molecular Generation: Design novel molecules with desired characteristics.
  • Use Case: Predict the binding affinity of a new drug candidate to a target protein using a GNN trained on existing protein-ligand data.

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 build graph neural networks for molecular property prediction?▼

Build graph neural networks for molecular property prediction by developing custom GNN architectures using PyTorch to predict properties like solubility or toxicity from datasets such as BBBP and QM9.

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

Graph neural networks support protein analysis by modeling protein sequences and structures to predict protein functions, utilizing integrated models like ESM within the PyTorch framework.

What is knowledge graph reasoning for drug repurposing?▼

Knowledge graph reasoning for drug repurposing discovers relationships in biomedical data by applying models like RotatE to knowledge graphs such as Hetionet to identify new drug candidate relationships.

How do I generate novel molecules with desired characteristics using graph neural networks?▼

Generate novel molecules with desired characteristics by developing custom graph neural network architectures with PyTorch to perform targeted molecular generation tasks on molecular datasets.

Do I need PyTorch to develop custom GNN architectures for drug discovery?▼

PyTorch is required to develop custom GNN architectures for drug discovery, as this Skill facilitates molecular modeling, protein analysis, and knowledge graph reasoning using the PyTorch framework.

Related Skills

Explore More Education & Research Skills→
HolobiomicsLabHolobiomicsLab
4

torchdrug

Build and evaluate PyTorch graph neural networks on biomedical datasets.

Official
Advanced
Imad-OuteImad-Oute

diffdock

Predict ligand binding poses and confidence scores for protein docking.

Community
Intermediate
jackspacejackspace
16

torchdrug

Apply graph neural networks to drug discovery tasks with PyTorch.

Community
Advanced
galeepgaleep

torchdrug

Predict molecular properties and model proteins with custom GNN architectures.

Community
Advanced