Umol
Bryant et al. (FU Berlin / Noé Lab)
Unified molecular model predicting protein-ligand complex structures directly from sequence information. Combines MSA-based protein features with ligand graph representations.
Best For
Protein-ligand structure prediction from sequence without requiring a pre-docked pose
License
Open Source (check repo)
Strengths
- +Sequence-only input
- +No docking step required
- +Colab notebook available
Limitations
- −Lower accuracy than AF3-class models on diverse benchmarks
- −Single ligand per prediction
- −Pre-AF3 era model
R&D Pipeline Coverage
Related Tools
AlphaFold3
Google DeepMind / Isomorphic Labs
Joint structure prediction of proteins, DNA, RNA, small molecules, ions, and covalent modifications in a single diffusion-based model.
Boltz-1
MIT Jameel Clinic
First fully open-source model achieving AlphaFold3-level accuracy for joint structure prediction of proteins, nucleic acids, and small molecules.
NeuralPLexer
Qiao et al. (Caltech / NVIDIA)
Multi-scale deep generative model for state-specific protein-ligand complex structure prediction. Predicts both protein conformational change and ligand binding pose simultaneously from sequence.
More in Structure Prediction
AlphaFold2
Google DeepMind
Predicts single-chain and multimer protein 3D structures from amino acid sequence using MSA-based deep learning. Set the modern benchmark on CASP14.
ColabFold
Steinegger Lab (Seoul National University)
Wraps AlphaFold2 with MMseqs2-based MSA generation, making AF2 runs 40-60x faster. Accessible via Google Colab or local install.
Boltz-1
MIT Jameel Clinic
First fully open-source model achieving AlphaFold3-level accuracy for joint structure prediction of proteins, nucleic acids, and small molecules.
Stay updated on Umol
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.