Uni-Mol / Uni-Mol2
DP Technology / DeepModeling
Universal 3D molecular pretraining framework for property prediction, conformation generation, and docking. Uni-Mol2 (2024) scales to 1.1B parameters trained on 800M conformations.
Best For
3D-aware molecular property prediction; foundation model for downstream drug discovery tasks
License
Open Source (MIT)
Strengths
- +3D structure-aware representations
- +1.1B parameter model (Uni-Mol2)
- +MIT license
- +Covers property prediction + docking + conformations
Limitations
- −Requires 3D conformer input for best results
- −Large model needs GPU
- −DP Technology ecosystem
R&D Pipeline Coverage
Related Tools
Chemprop v2
MIT (Barzilay, Coley et al.)
Open-source D-MPNN library for molecular property prediction. The architecture underlying ADMET-AI and ADMETlab 3.0. Used in Halicin antibiotic discovery.
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.
Uni-Dock
DP Technology
GPU-accelerated molecular docking achieving >2000x speedup over CPU Vina. Enables ultra-large virtual screening of billions of compounds.
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 Uni-Mol / Uni-Mol2
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.