pytdc

What problem does it solve?

PyTDC provides AI-ready therapeutics datasets and benchmarks (ADME, toxicity, DTI) with standardized splits, benchmarks, and data processing utilities to accelerate drug-discovery research and evaluation.

Core Features & Use Cases

• Curated datasets for ADME, Toxicity, DTI, and generation tasks
• Scaffold/random/cold partitioning and standardized evaluation metrics
• Data processing utilities and molecular generation oracles for model benchmarking

Quick Start

• Install with: pip install PyTDC
• Example: from tdc.single_pred import ADME; data = ADME(name='Caco2_Wang'); split = data.get_split(method='scaffold'); df = data.get_data(format='df')