DeepPurpose
Huang et al. (Harvard / MIT)
Deep learning toolkit for drug-target interaction (DTI) prediction, compound property prediction, protein-protein interaction prediction, and drug-drug interaction prediction. Supports 15+ encoding methods and 5+ model architectures.
Best For
Rapid DTI prediction prototyping; drug repurposing virtual screening
License
Open Source (BSD 3-Clause)
Strengths
- +15+ encoding methods
- +DTI + DDI + PPI in one toolkit
- +Easy-to-use API
- +Drug repurposing modules
Limitations
- −Not optimized for production throughput
- −Pre-2021 training data
- −Limited to pairwise interaction prediction
R&D Pipeline Coverage
Related Tools
ADMET-AI
Greenstone Biosciences / Stanford
Predicts 41 ADMET endpoints using a Chemprop-RDKit GNN. Held the highest average rank on the TDC ADMET Leaderboard at time of publication.
Therapeutics Data Commons
Zitnik Lab, Harvard Medical School
Coordinated initiative providing AI-ready datasets, curated benchmarks, and leaderboards across therapeutic modalities and discovery stages. Covers 22 tasks across single-instance, multi-instance, and generation problems.
More in ADMET Prediction
ADMET-AI
Greenstone Biosciences / Stanford
Predicts 41 ADMET endpoints using a Chemprop-RDKit GNN. Held the highest average rank on the TDC ADMET Leaderboard at time of publication.
ADMETlab 3.0
SCBDD Group, Central South University
Comprehensive ADMET prediction platform covering 119 endpoints with uncertainty estimates. Trained on >400,000 curated entries.
SwissADME
Swiss Institute of Bioinformatics (SIB)
Predicts pharmacokinetics, drug-likeness, and medicinal chemistry friendliness. Known for the BOILED-Egg visualization and Bioavailability Radar.
Stay updated on DeepPurpose
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.