---
title: README
emoji: 🚀
colorFrom: green
colorTo: gray
sdk: static
pinned: false
license: mit
---

<p align="center"><img src="https://raw.githubusercontent.com/mims-harvard/TDC/master/fig/logo.png" alt="logo"/></p>


[**Nature Chemical Biology Paper**](https://www.nature.com/articles/s41589-022-01131-2) | [**NeurIPS Paper**](https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/4c56ff4ce4aaf9573aa5dff913df997a-Abstract-round1.html) | [**GitHub**](https://github.com/mims-harvard/TDC) | [**Leaderboards**](https://tdcommons.ai/benchmark/overview/) | [**Datasets**](https://tdcommons.ai/overview/)

[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ProjectTDC)](https://twitter.com/ProjectTDC)

Artificial intelligence is poised to enable breakthroughs and discoveries in therapeutic science. Therapeutics Data Commons is a global initiative to access and evaluate artificial intelligence capability across therapeutic modalities and stages of discovery. The Commons is a resource with AI-solvable tasks, AI-ready datasets, and curated benchmarks, providing an ecosystem of tools, libraries, leaderboards, and community resources, including data functions, strategies for systematic model evaluation, meaningful data splits, data processors, and molecule generation oracles.

<div class="grid lg:grid-cols-3 gap-x-4 gap-y-7">
  <a href="https://tdcommons.ai/" class="block overflow-hidden group">
      <div
          class="w-full h-40 object-cover mb-2 rounded-lg flex items-center justify-center bg-green-50"
      >
          <img alt="" src="https://tdcommons.ai/logonav.png" class="w-40" />
      </div>
      <div class="underline">Therapeutics Commons website</div>
  </a>
  <a
      href="https://github.com/mims-harvard/TDC"
      class="block overflow-hidden"
  >
      <div class="flex items-center h-40 bg-green-50 rounded-lg px-4 mb-2">
          <pre
              class="break-words leading-1 whitespace-pre-line text-xs text-gray-800">
  from tdc.single_pred import ADME
  data = ADME(name = 'HIA_Hou')
  # split into train/val/test with scaffold split methods
  split = data.get_split(method = 'scaffold')
  # get the entire data in the various formats
  data.get_data(format = 'df')
      </pre>
      </div>
      <div class="underline">Retrieve AI tasks, data functions, model evaluators and benchmarks</div>
  </a>
  <a
      href="https://huggingface.co/models?filter=tdc"
      class="block overflow-hidden group"
  >
      <div
          class="w-full h-40 mb-2 bg-gray-900 group-hover:bg-gray-850 rounded-lg flex items-start justify-start overflow-hidden"
      >
          <img
              alt=""
              src="/front/assets/promo/spacy_widget.jpeg"
              class="w-full h-40 object-cover overflow-hidden"
          />
      </div>
      <div class="underline">Find all Therapeutics Commons models in the Hub</div>
  </a>
</div>
      <p>
          More information: <a href="https://join.slack.com/t/pytdc/shared_invite/zt-x0ujg5v6-zwtQZt83fhRdgrYjXRFz5g" class="underline">Therapeutics Commons Slack Workspace</a>, <a href="https://tdcommons.ai/news/" class="underline">Release News</a>
      </p>