PyTDC (Therapeutics Data Commons)
技能 已验证 活跃Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
To empower AI agents with readily accessible and standardized drug discovery datasets, facilitating research in therapeutic ML and pharmacological prediction.
功能
- Access to curated drug discovery datasets (ADME, Tox, DTI, etc.)
- Standardized data splitting methods (scaffold, cold-drug, cold-target)
- Integrated model evaluation metrics
- Data processing utilities (molecule conversion, filtering)
使用场景
- Working with AI-ready drug discovery datasets
- Benchmarking machine learning models on pharmaceutical tasks
- Predicting molecular properties and interactions
- Generating novel molecules with desired characteristics
非目标
- Performing wet-lab experiments
- Deploying trained models
- Providing extensive molecular visualization beyond basic dataframes
工作流
- Load a specific dataset using its name
- Split the dataset into train/validation/test sets using a chosen method
- Process or convert data as needed (e.g., to graphs)
- Train a machine learning model on the prepared data
- Evaluate the model using provided metrics
先决条件
- uv
- Python 3.11+
Scope
- info:Tool surface sizeThe skill primarily exposes functions for data loading and splitting, with a focused tool surface rather than a large number of distinct commands.
安装
npx skills add K-Dense-AI/claude-scientific-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Molfeat
99Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
Deepchem
99Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
PyTDC (Therapeutics Data Commons)
99Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction. Part of the AlterLab Academic Skills suite.
RDKit Cheminformatics Toolkit
99Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.
Medchem
99Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
Datamol Cheminformatics Skill
99Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly. Part of the AlterLab Academic Skills suite.