Agens torchdrug

skill_id: torchdrug name: torchdrug description: PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc. version: 1.0.0 author: K-Dense Inc. license: Apache-2.0 license tags:

• scientific-agent-skills
• torchdrug tools: [] permissions: network: false filesystem: false shell: false agents:
• bio_code_agent enabled: true source: scientific-agent-skills entrypoint: entry.py readme: README.md input_schema: {} output_schema: type: object metadata: upstream_repo: K-Dense-AI/scientific-agent-skills upstream_skill: torchdrug upstream_path: scientific-skills/torchdrug/SKILL.md upstream_frontmatter: name: torchdrug description: PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc. license: Apache-2.0 license metadata: skill-author: K-Dense Inc.