Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)

We describe AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13. Submissions were made by three free‐modeling (FM) methods which combine the predictions of three neural networks. All three systems were guided by predictions of distances between pairs of res...

Full description

Saved in:
Bibliographic Details
Published in:Proteins, structure, function, and bioinformatics Vol. 87; no. 12; pp. 1141 - 1148
Main Authors: Senior, Andrew W., Evans, Richard, Jumper, John, Kirkpatrick, James, Sifre, Laurent, Green, Tim, Qin, Chongli, Žídek, Augustin, Nelson, Alexander W. R., Bridgland, Alex, Penedones, Hugo, Petersen, Stig, Simonyan, Karen, Crossan, Steve, Kohli, Pushmeet, Jones, David T., Silver, David, Kavukcuoglu, Koray, Hassabis, Demis
Format: Journal Article
Language:English
Published: Hoboken, USA John Wiley & Sons, Inc 01.12.2019
Wiley Subscription Services, Inc
Subjects:
Algorithms
Artificial neural networks
CASP
Computational Biology - methods
Databases, Protein
deep learning
Domains
machine learning
Models, Molecular
Neural networks
Neural Networks, Computer
Protein Conformation
Protein Folding
Protein structure
protein structure prediction
Proteins
Proteins - chemistry
Segmentation
deep learning
CASP
machine learning
protein structure prediction
ISSN:0887-3585, 1097-0134, 1097-0134
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13. Submissions were made by three free‐modeling (FM) methods which combine the predictions of three neural networks. All three systems were guided by predictions of distances between pairs of residues produced by a neural network. Two systems assembled fragments produced by a generative neural network, one using scores from a network trained to regress GDT_TS. The third system shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation. In the CASP13 FM assessors' ranking by summed z‐scores, this system scored highest with 68.3 vs 48.2 for the next closest group (an average GDT_TS of 61.4). The system produced high‐accuracy structures (with GDT_TS scores of 70 or higher) for 11 out of 43 FM domains. Despite not explicitly using template information, the results in the template category were comparable to the best performing template‐based methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Andrew W. Senior, Richard Evans, John Jumper, James Kirkpatrick, and Laurent Sifre should be considered joint first authors
ISSN:0887-3585
1097-0134
1097-0134
DOI:10.1002/prot.25834