Uni-Mol2
Scaled molecular pretraining model using atomic, graph, and 3D geometry features, with models up to 1.1B parameters pretrained on 800M conformations.
- from
- Computational Biology
- added
- 2026-10-10
- likes
- 0
similar
-
Uni-Mol github.com
3D molecular pretraining framework for universal representation learning on molecules and protein pockets.
-
MolFormer github.com
Linear attention transformer pretrained on millions of SMILES strings for efficient molecular embeddings.
-
-
ChemFM github.com
1B/3B-parameter chemical language model pretrained on 178M molecules for molecular representation, property prediction, generation, and synthesis tasks.
-
-
Matcha github.com
Multi-stage Riemannian flow matching model for physically valid molecular docking with scoring, pose filtering, and benchmarks.
Computational Biology › Machine Learning Tasks and Models > Foundation Models > Compound Foundation Models: “Scaled molecular pretraining model using atomic, graph, and 3D geometry features, with models up to 1.1B parameters pretrained on 800M conformations.”