Learning the shape of protein microenvironments with a holographic convolutional neural network

• 成果类型: Article
• 署名作者: Pun, Michael N.; Ivanov, Andrew; Bellamy, Quinn; Montague, Zachary; Lamont, Colin; Bradley, Philip; Otwinowski, Jakub; Nourmohammad, Armita
• 署名单位: University of Washington; University of Washington Seattle; Max Planck Society; Fred Hutchinson Cancer Center; University of Washington; University of Washington Seattle; University of Washington; University of Washington Seattle; University of Washington; University of Washington Seattle; University of Washington; University of Washington Seattle
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-12632
• DOI: 10.1073/pnas.2300838121
• 发表日期: 2024-02-01
• 关键词: temperature-sensitive mutant; t4 lysozyme; structural-analysis; hydrophobic core; bacteriophage-t4 lysozyme; prediction; mutations; language; domain; thermostability

摘要

Proteins play a central role in biology from immune recognition to brain activity. While major advances in machine learning have improved our ability to predict protein structure from sequence, determining protein function from its sequence or structure remains a major challenge. Here, we introduce holographic convolutional neural network (H-CNN) for proteins, which is a physically motivated machine learning approach to model amino acid preferences in protein structures. H-CNN reflects physical interactions in a protein structure and recapitulates the functional information stored in evolutionary data. H-CNN accurately predicts the impact of mutations on protein stability and binding of protein complexes. Our interpretable computational model for protein structure-function maps could guide design of novel proteins with desired function.