NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning.
Klausen, M. S., Jespersen, M. C., Nielsen, H., Jensen, K. K., Jurtz, V. I., Sonderby, C. K., Sommer, M. O. A., Winther, O., Nielsen, M., Petersen, B. and Marcatili, P.
Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Kongens Lyngby, Denmark.
Department of Bio and Health Informatics, Technical University of Denmark, Kongens Lyngby, Denmark.
The Bioinformatics Centre, Department of Biology, University of Copenhagen, Copenhagen, Denmark.
Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby, Denmark.
Instituto de Investigaciones Biotecnologicas, Universidad Nacional de San Martin, Buenos Aires, Argentina.
Faculty of Applied Sciences, Centre of Excellence for Omics-Driven Computational Biodiscovery (COMBio), AIMST University, Kedah, Malaysia.
The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unraveling 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 1000 proteins in less than 2 hours, and complete proteomes in less than 1 day.
Proteins 87(6): 520-527 (2019)