lib-pytdc

What problem does it solve?

This Skill provides access to a comprehensive suite of AI-ready datasets and benchmarks specifically designed for drug discovery and development, streamlining machine learning workflows in pharmacology.

Core Features & Use Cases

• Diverse Datasets: Access curated datasets for molecular property prediction (ADME, toxicity), drug-target interactions (DTI), molecular generation, and more.
• Standardized Benchmarks: Utilize pre-defined benchmark groups for systematic model evaluation.
• Data Utilities: Leverage tools for data splitting, molecule conversion, and performance evaluation.
• Use Case: Train a machine learning model to predict drug toxicity using standardized datasets and evaluation metrics provided by PyTDC.

Quick Start

Use the lib-pytdc skill to load the Caco2_Wang ADME dataset and get a scaffold split.