
by MIT
Therapeutics Data Commons is a collection of AI-ready datasets, tasks and benchmarks for drug discovery. Everything is accessed through an open Python library.
DatasetFree
Step 1: Browse the site for the task or dataset you need.
Step 2: Install the TDC Python library.
Step 3: Load a dataset with a few lines of code.
Step 4: Use the provided splits and evaluators to train and score your model.
Step 5: Compare your results on the benchmarks and leaderboards.
It covers target discovery, activity screening, efficacy, safety and manufacturing across small molecules, antibodies and vaccines.
Through the open Python library. The site says any dataset can be retrieved with just three lines of code.
Yes. The library includes data evaluators, data splits, data processors and molecule generation oracles.
Yes. The site says it welcomes contributions from the research community, and there is a Slack group to join.
ChempropChemprop is a PyTorch-based framework for training and evaluating message-passing neural networks that predict molecular properties. The site hosts its documentation for version 2.3.1.
ASKCOSASKCOS is a hosted set of computer-aided design tools for organic synthesis. You enter or draw a molecule or reaction SMILES and see the tasks available for it, such as synthetic planning modules.
TDC-2Therapeutics Data Commons (TDC) is a resource of AI-ready datasets, learning tasks and benchmarks for therapeutic science, accessed through an open Python library.