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

2024/02/01 by Michael N. Pun, A. Ivanov, Quinn Bellamy +5 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · #Protein Structure and Dynamics #RNA and protein synthesis mechanisms #Machine Learning in Bioinformatics

paper · pdf · doi:10.1073/pnas.2300838121

openalex publication_date 2024/02/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/12

Abstract

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.

Citations

• Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
• Highly accurate protein structure prediction with AlphaFold
• Accurate prediction of protein structures and interactions using a three-track neural network
• Learning inverse folding from millions of predicted structures
• E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
• Robust deep learning–based protein sequence design using ProteinMPNN
• Large language models generate functional protein sequences across diverse families
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• Rapid protein stability prediction using deep learning representations

Cited by

• Recent advances on protein engineering for improved stability

Discussions

• some relevant recent publications from the group: Protein structure modeling with symmetry-aware neural nets: www.pnas.org/doi/10.1073/... designing T-cell antigens w/ our protein models: www.pnas.org [bsky, 3 points, 0 comments]

Related

• Learning the shape of protein micro-environments with a holographic convolutional neural network
• Advances of Deep Learning in Protein Science: A Comprehensive Survey
• MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
• Leveraging Sequence Embedding and Convolutional Neural Network for Protein Function Prediction
• Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences