HITS Inc.

MSA-free all-atom protein structure prediction, folding monomers from the representations of a 3B-parameter metagenomic protein language model.

Biomolecular complex structure prediction without multiple sequence alignment, for protein-protein, protein-ligand and protein-nucleic acid binding.

Enzyme-substrate specificity prediction by end-to-end co-folding, with no predefined binding pocket. AUROC 0.766 on unseen enzymes and substrates.

Predicts protein-ligand complex structures and binding affinity from sequence and ligand SMILES, without a PDB structure or a predefined pocket.

Structure-based drug design that generates molecules as synthetic pathways over 1.2M purchasable building blocks, so each design carries its route.