Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
Detected risks:
PyTDC is an open-science platform designed to facilitate drug discovery and development by providing a wide array of AI-ready datasets and benchmarks. It addresses the critical need for accessible, high-quality data in the field of therapeutics, enabling researchers to effectively predict molecular properties, assess drug interactions, and generate novel compounds. By offering standardized evaluation metrics and meaningful data splits, PyTDC helps streamline the process of model benchmarking and performance evaluation in pharmaceutical tasks.
You can install PyTDC using pip with the command 'pip install PyTDC'. To upgrade to the latest version, use 'pip install PyTDC --upgrade'.
PyTDC offers datasets in three main categories: single-instance prediction (e.g., ADME, toxicity), multi-instance prediction (e.g., drug-target interactions), and generation tasks (e.g., molecule generation).
Yes, PyTDC is built on core dependencies like numpy, pandas, and scikit_learn, making it compatible with many other Python libraries used in data science and machine learning.
Common use cases include predicting pharmacokinetic properties of drug molecules, assessing drug toxicity, benchmarking machine learning models, and generating new molecules with desired characteristics.
The primary requirement is having Python and pip installed. Additionally, some features may automatically install additional packages as needed.
Quick Setup:
.claude/skills/Repository
davila7/claude-code-templates