Peer-Reviewed Publication
Nat Biotechnol2022;40(6):932-937.June 1, 2022Journal Article
Using deep learning to annotate the protein universe.
Maxwell L Bileschi1, David Belanger2, Drew H Bryant2, Theo Sanderson2,3, Brandon Carter4, D Sculley2, Alex Bateman5, Mark A DePristo2,6, Lucy J Colwell7,8
1Google Research, Cambridge, MA, USA. mlbileschi@google.com.
2Google Research, Cambridge, MA, USA.
3The Francis Crick Institute, London, UK.
4MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA.
5European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Hinxton, UK.
6BigHat Biosciences, San Mateo, CA, USA.
7Google Research, Cambridge, MA, USA. lcolwell@google.com.
8Department of Chemistry, University of Cambridge, Cambridge, UK. lcolwell@google.com.
Abstract
Understanding the relationship between amino acid sequence and protein function is a long-standing challenge with far-reaching scientific and translational implications. State-of-the-art alignment-based techniques cannot predict function for one-third of microbial protein sequences, hampering our ability to exploit data from diverse organisms. Here, we train deep learning models to accurately pred…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans