Predicting protein interactions with artificial intelligence
November 2021
University of Texas Southwestern Medical Center, Dallas, USA(1)
University of Washington, Seattle, USA(2)
University of Washington, Seattle, USA(2)
Protein-protein interactions play critical roles in biology, but the structures of many eukaryotic protein complexes are unknown and there are likely many interactions not yet identified. This study takes advantage of the advances in proteome-wide amino acid coevolution analysis and deep-learning-based structure modelling to systematically identify and build accurate models of core eukaryotic protein complexes within the Saccharomyces cerevisiae proteome. A combination of RoseTTAFold and AlphaFold was used to screen through paired multiple sequence alignments for 8.3 million pairs of yeast proteins, identifying 1505 possibly interacting proteins and building structural models for 106 previously unidentified compounds and for 806 compounds that have not been structurally characterized. These complexes, which have as many as five subunits, play roles in almost all key processes in eukaryotic cells and provide broad insights into biological function.
Computed structures of core eukaryotic protein complexes
Qian Cong(1), David Baker(2)
Added on: 01-28-2022
[1] https://www.science.org/doi/10.1126/science.abm4805[2] https://www.technologynetworks.com/drug-discovery/news/predicting-protein-interactions-with-artificial-intelligence-355904