Loading…
Part of University of Washington
A computational protein design lab at the University of Washington, creating software and new proteins for challenges in medicine and sustainability.
Deep network that predicts structures of full biological assemblies: proteins, nucleic acids, small molecules, metals, and covalent modifications.
Structure accuracy estimation over atom graphs, scoring macrocyclic peptide and protein-DNA models that residue-level predictors cannot represent.
Full-atom protein model accuracy estimation, regressing per-atom lDDT with an SE(3)-transformer over a heavy-atom graph of the modeled structure.
Baker Lab / Institute for Protein Design / University of Washington / Harvard University / UT Southwestern Medical Center / University of Cambridge / Stanford University / Lawrence Berkeley National Laboratory / North-West University / University of the Free State / University of Graz / Medical University of Graz / University of Victoria / University of British Columbia / UC Berkeley / Howard Hughes Medical Institute
Released July 15, 2021
Protein structure and complex prediction from sequence, in a three-track network that reasons over alignments, distances, and 3D coordinates at once.