DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier

Handle URI:
http://hdl.handle.net/10754/625903
Title:
DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier
Authors:
Kulmanov, Maxat ( 0000-0003-1710-1820 ) ; Khan, Mohammed Asif; Hoehndorf, Robert ( 0000-0001-8149-5890 )
Abstract:
Motivation A large number of protein sequences are becoming available through the application of novel high-throughput sequencing technologies. Experimental functional characterization of these proteins is time-consuming and expensive, and is often only done rigorously for few selected model organisms. Computational function prediction approaches have been suggested to fill this gap. The functions of proteins are classified using the Gene Ontology (GO), which contains over 40 000 classes. Additionally, proteins have multiple functions, making function prediction a large-scale, multi-class, multi-label problem. Results We have developed a novel method to predict protein function from sequence. We use deep learning to learn features from protein sequences as well as a cross-species protein–protein interaction network. Our approach specifically outputs information in the structure of the GO and utilizes the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and demonstrate a significant improvement over baseline methods such as BLAST, in particular for predicting cellular locations.
KAUST Department:
Computational Bioscience Research Center (CBRC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Kulmanov M, Khan MA, Hoehndorf R (2017) DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics. Available: http://dx.doi.org/10.1093/bioinformatics/btx624.
Publisher:
Oxford University Press (OUP)
Journal:
Bioinformatics
KAUST Grant Number:
FCC/1/1976-08-01
Issue Date:
27-Sep-2017
DOI:
10.1093/bioinformatics/btx624
Type:
Article
ISSN:
1367-4803; 1460-2059
Sponsors:
This work was supported by funding from King Abdullah University of Science and Technology (KAUST) [FCC/1/1976-08-01]
Additional Links:
https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btx624/4265461/DeepGO-predicting-protein-functions-from-sequence
Appears in Collections:
Articles; Computational Bioscience Research Center (CBRC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKulmanov, Maxaten
dc.contributor.authorKhan, Mohammed Asifen
dc.contributor.authorHoehndorf, Roberten
dc.date.accessioned2017-10-19T07:10:41Z-
dc.date.available2017-10-19T07:10:41Z-
dc.date.issued2017-09-27en
dc.identifier.citationKulmanov M, Khan MA, Hoehndorf R (2017) DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics. Available: http://dx.doi.org/10.1093/bioinformatics/btx624.en
dc.identifier.issn1367-4803en
dc.identifier.issn1460-2059en
dc.identifier.doi10.1093/bioinformatics/btx624en
dc.identifier.urihttp://hdl.handle.net/10754/625903-
dc.description.abstractMotivation A large number of protein sequences are becoming available through the application of novel high-throughput sequencing technologies. Experimental functional characterization of these proteins is time-consuming and expensive, and is often only done rigorously for few selected model organisms. Computational function prediction approaches have been suggested to fill this gap. The functions of proteins are classified using the Gene Ontology (GO), which contains over 40 000 classes. Additionally, proteins have multiple functions, making function prediction a large-scale, multi-class, multi-label problem. Results We have developed a novel method to predict protein function from sequence. We use deep learning to learn features from protein sequences as well as a cross-species protein–protein interaction network. Our approach specifically outputs information in the structure of the GO and utilizes the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and demonstrate a significant improvement over baseline methods such as BLAST, in particular for predicting cellular locations.en
dc.description.sponsorshipThis work was supported by funding from King Abdullah University of Science and Technology (KAUST) [FCC/1/1976-08-01]en
dc.publisherOxford University Press (OUP)en
dc.relation.urlhttps://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btx624/4265461/DeepGO-predicting-protein-functions-from-sequenceen
dc.rightsThis is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleDeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifieren
dc.typeArticleen
dc.contributor.departmentComputational Bioscience Research Center (CBRC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalBioinformaticsen
dc.eprint.versionPublisher's Version/PDFen
kaust.authorKulmanov, Maxaten
kaust.authorKhan, Mohammed Asifen
kaust.authorHoehndorf, Roberten
kaust.grant.numberFCC/1/1976-08-01en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.