pytdc
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
Security Assessment
Detected risks:
About pytdc
PyTDC, or Therapeutics Data Commons, is an open-science platform designed to facilitate drug discovery and development through the provision of AI-ready datasets and benchmarks. It addresses the challenge of accessing reliable and standardized data in the pharmaceutical field, enabling researchers to leverage curated datasets that span the entire therapeutics pipeline. This platform aggregates information related to drug properties, interactions, and molecular characteristics, thus providing essential resources for therapeutic machine learning (ML) and pharmacological prediction tasks.
FAQ
How do I install PyTDC?
You can install PyTDC using pip with the command 'pip install PyTDC'. To upgrade to the latest version, use 'pip install PyTDC --upgrade'.
What types of datasets are available in PyTDC?
PyTDC offers datasets categorized into single-instance predictions (like ADME and toxicity), multi-instance predictions (such as drug-target interactions), and generation tasks (like molecule generation).
Can I use PyTDC for benchmarking machine learning models?
Yes, PyTDC is designed for benchmarking machine learning models on standardized pharmaceutical tasks, providing proper train/test splits and evaluation metrics.
What are the core dependencies for using PyTDC?
The core dependencies include numpy, pandas, tqdm, seaborn, scikit_learn, and fuzzywuzzy, which are automatically installed.
What programming language is PyTDC built with?
PyTDC is built with Python and is intended for use within Python-based projects.
Install pytdc
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
K-Dense-AI/claude-scientific-skills