skills.rest
galeep
galeepCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

torchdrug

Predict molecular properties and model proteins with custom GNN architectures.

Updated May 17, 2026
Search Tags:#knowledge graph#drug discovery#protein modeling#molecular science#graph neural network
One-click install
npx skills add https://github.com/galeep/plugin-place --skill torchdrug-galeep
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: torchdrug
Source: https://github.com/galeep/plugin-place/tree/main/plugins/sci-cheminformatics-drug-discovery/skills/torchdrug
Command: npx skills add https://github.com/galeep/plugin-place --skill torchdrug-galeep

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pytorch, rdkit, torchdrug, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit for building custom graph neural network (GNN) architectures for drug discovery and molecular science, enabling users to predict molecular properties, model proteins, and reason over biological knowledge graphs.

Core Features & Use Cases

  • Custom GNN Architectures: Offers a variety of GNN architectures for different tasks, including GIN, GAT, SchNet, and more.
  • Molecular Property Prediction: Predict chemical, physical, and biological properties of molecules from their structure.
  • Protein Modeling: Work with protein sequences, structures, and properties, including function prediction, structure prediction, and stability prediction.
  • Knowledge Graph Reasoning: Predict missing links and relationships in biological knowledge graphs.
  • Use Case: Imagine you are working on drug discovery and need to predict the activity of a new molecule. Use this Skill to build a custom GNN model and predict the molecular properties of the molecule.

Quick Start

To start using torchdrug, first install the skill with claude plugin install sci-bioinformatics-drug-discovery@plugin-place. Then, you can load a dataset and build a model using the torchdrug library.

Frequently Asked Questions about torchdrug

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

FAQPage Schema
How do I build a custom graph neural network for molecular property prediction?▼

To build a custom graph neural network for molecular property prediction, use this Skill to construct architectures like GIN or SchNet and train them on molecular structures represented as graphs. It requires PyTorch and RDKit for graph representation and machine learning tasks.

Can I use PyTorch and RDKit for protein modeling and function prediction?▼

Yes, you can use PyTorch and RDKit for protein modeling and function prediction. This Skill enables you to work with protein sequences and structures, leveraging custom graph neural network architectures to predict protein functions, structures, and stability.

What is the best way to perform knowledge graph reasoning in bioinformatics?▼

The best way to perform knowledge graph reasoning in bioinformatics is using custom graph neural network architectures. This Skill applies GNN models to biological knowledge graphs to predict missing links and uncover hidden relationships between biological entities.

Do I need to install specific Python libraries to run graph neural networks for drug discovery?▼

Yes, you need to install specific Python libraries including PyTorch, RDKit, and TorchDrug. These dependencies are required to handle graph representations of molecules and execute the underlying machine learning tasks for drug discovery.

Does this approach support GAT and SchNet architectures for molecular science?▼

Yes, this approach supports GAT and SchNet architectures for molecular science. The Skill offers a variety of custom graph neural network architectures, including GIN, GAT, and SchNet, to address diverse tasks in drug discovery and molecular modeling.

Related Skills

Explore More Software Engineering Skills→
LeonChaoXLeonChaoX
783

torchdrug

Train PyTorch-native graph neural networks on TorchDrug datasets for molecular and protein tasks.

Community
Intermediate
SciMate-AISciMate-AI
1

deepchem

Predict molecular properties and materials descriptors from chemical data using DeepChem.

Official
Intermediate
Yezez9Yezez9

torchdrug

Develop custom GNN architectures for molecular and protein data analysis with PyTorch.

Community
Advanced
OwnLabAIOwnLabAI
21

deepchem

Train molecular property prediction models using DeepChem workflows.

Official
Advanced