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. Part of the AlterLab Academic Skills suite.
To empower researchers in drug discovery and therapeutic ML by providing easy access to standardized datasets, benchmarks, and evaluation tools.
功能
- Access AI-ready drug discovery datasets (ADME, toxicity, DTI)
- Utilize standardized benchmarks and data splits
- Perform molecular property prediction and generation
- Integrates with the PyTDC Python library for programmatic access
使用场景
- Working with drug discovery or therapeutic ML datasets
- Benchmarking machine learning models on pharmaceutical tasks
- Predicting molecular properties (ADME, toxicity, bioactivity)
- Accessing curated datasets with proper train/test splits
非目标
- Performing actual wet-lab experiments
- Replacing dedicated cheminformatics software for advanced molecular modeling
- Providing real-time clinical decision support
工作流
- Install PyTDC via pip
- Import relevant modules from tdc
- Load a specific dataset (e.g., ADME, DTI)
- Get data split (scaffold, random, cold splits)
- Process data (convert formats, filter molecules)
- Train a model (user-implemented)
- Evaluate model using TDC evaluators
实践
- Data Curation
- Machine Learning Benchmarking
- Reproducible Research
先决条件
- Python environment
- pip or uv for package installation
- PyTDC library installed
安装
npx skills add AlterLab-IEU/AlterLab-Academic-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
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.
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.
Open Targets Platform Query Skill
100Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification. 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.