Train graph-based models for chemistry and protein tasks with TorchDrug.
npx skills add https://github.com/fuzzy-dynamics/strings --skill torchdrug-fuzzy-dynamics
Please help me install this Agent Skill. Skill: torchdrug Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/torchdrug Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill torchdrug-fuzzy-dynamics
TorchDrug provides a unified, PyTorch-based toolkit enabling researchers to train and deploy graph-based ML models for chemistry and protein tasks, reducing the complexity of building end-to-end pipelines.
Load a dataset, choose a GNN backbone like GIN, and wrap it in a PropertyPrediction task to start training.
High-intent search queries and answers about installing and using this skill.
To perform molecular property prediction, load a dataset like BBBP, select a GNN backbone such as GIN, and wrap it in a PropertyPrediction task to start training your graph neural network.
Protein modeling and retrosynthesis workflows can be built in a single integrated PyTorch toolkit, utilizing graph-based encoders like GearNet and modular components for synthetic route planning.
Yes, knowledge graph reasoning models for datasets like Hetionet integrate directly with PyTorch Lightning, enabling scalable training for link prediction on biomedical graphs.
Yes, TorchDrug supports 3D geometry processing with multiple graph neural networks, allowing researchers to analyze protein sequences and structures using encoders like GearNet and ProteinBERT.
The toolkit provides access to over 40 datasets for drug discovery, including BBBP, HIV, QM9, EnzymeCommission, and Hetionet, covering molecular property prediction and knowledge graph reasoning tasks.
jaechang-hitsTrain GNN models for molecular property prediction using PyTorch and TorchDrug.
ovachieverConvert SMILES or RDKit molecules into ML-ready numerical representations.
LeonChaoXTrain PyTorch-native graph neural networks on TorchDrug datasets for molecular and protein tasks.
hxk622Train machine learning models for molecular property prediction and drug discovery.
