Journal article
NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning
Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark1
Cognitive Systems, Department of Applied Mathematics and Computer Science, Technical University of Denmark2
Department of Applied Mathematics and Computer Science, Technical University of Denmark3
AI for Immunological Molecules, Bioinformatics, Department of Health Technology, Technical University of Denmark4
Bacterial Synthetic Biology, Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark5
Immunoinformatics and Machine Learning, Bioinformatics, Department of Health Technology, Technical University of Denmark6
Bioinformatics, Department of Health Technology, Technical University of Denmark7
Department of Health Technology, Technical University of Denmark8
Process engineering, National Centre for Nano Fabrication and Characterization, Technical University of Denmark9
National Centre for Nano Fabrication and Characterization, Technical University of Denmark10
University of Copenhagen11
Copenhagen Center for Health Technology, Centers, Technical University of Denmark12
...and 2 moreThe ability to predict local structural features of a protein from the primary sequence is of paramount importance for unravelling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed.
Here, we present NetSurfP-2.0, a novel tool that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures.
Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences. We assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features.
We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1,000 proteins in less than 2 hours, and complete proteomes in less than 1 day.
This article is protected by copyright. All rights reserved.
Language: | English |
---|---|
Publisher: | John Wiley & Sons, Inc. |
Year: | 2019 |
Pages: | 520-527 |
ISSN: | 10970134 and 08873585 |
Types: | Journal article |
DOI: | 10.1002/prot.25674 |
ORCIDs: | Petersen, Bent , Marcatili, Paolo , Winther, Ole , Klausen, Michael Schantz , Jensen, Kamilla Kjærgaard , Sommer, Morten Otto Alexander and Nielsen, Morten |