No retraction, correction or concern found when last checked on Oct 17, 2026.

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

Maxat Kulmanov, Mohammed Asif Khan, Robert Hoehndorf

Bioinformatics · 2017 · CC BY

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.

Availability and implementation. Web server: http://deepgo.bio2vec.net, Source code: https://github.com/bio-ontology-research-group/deepgo

Supplementary information. Supplementary data are available at Bioinformatics online.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 40

1.
Abadi M. et al (2016 ) Tensorflow: A system for large-scale machine learning. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, OSDI’16, pp. 265–283. Berkeley, CA, USA. USENIX Association.
Not in our library
2.
Alberts B. et al (2002 ) Molecular Biology of the Cell, 4th edn. Garland Science, New York, NY, USA.
Not in our library
3.
Alipanahi B. et al (2015 ) Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol., 33, 831–838.
Not in our library10.1038/nbt.3300
4.
Alshahrani M. et al (2017 ) Neuro-symbolic representation learning on biological knowledge graphs. Bioinformatics, 33, 2723–2730.
Not in our library10.1093/bioinformatics/btx275
5.
Altschul S.F. et al (1997 ) Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res., 25, 3389–3402.
Not in our library10.1093/nar/25.17.3389
6.
Ashburner M. et al (2000 ) Gene ontology: tool for the unification of biology. Nat. Genet., 25, 25–29.
Not in our library10.1038/75556
7.
Baryshnikova A. (2016 ) Systematic functional annotation and visualization of biological networks. Cell Syst., 2, 412–421.
Not in our library10.1016/j.cels.2016.04.014
8.
Bengio Y. et al (2003 ) A neural probabilistic language model. J. Mach. Learn. Res., 3, 1137–1155.
Not in our library
9.
Boutet E. et al (2016 ) UniProtKB/Swiss-Prot, the Manually Annotated Section of the UniProt KnowledgeBase: How to Use the Entry View. Springer, New York, NY, pp. 23–54.
Not in our library10.1007/978-1-4939-3167-5_2
10.
Clark W.T., Radivojac P. (2013 ) Information-theoretic evaluation of predicted ontological annotations. Bioinformatics, 29, i53.
Not in our library10.1093/bioinformatics/btt228
11.
Collobert R. et al (2011 ) Natural language processing (almost) from scratch. J. Mach. Learn. Res., 12, 2493–2537.
Not in our library
12.
Costanzo M. et al (2016 ) A global genetic interaction network maps a wiring diagram of cellular function. Science, 353, aaf1420.
Not in our library10.1126/science.aaf1420
13.
Cozzetto D. et al (2016 ) Ffpred 3: feature-based function prediction for all gene ontology domains. Sci. Rep., 6, 31865.
Not in our library10.1038/srep31865
14.
Functional classification of CATH superfamilies: a domain-based approach for protein function annotation · 2015
No notice
15.
Engelhardt B.E. et al (2011 ) Genome-scale phylogenetic function annotation of large and diverse protein families. Genome Res., 21, 1969–1980.
Not in our library10.1101/gr.104687.109
16.
InterPro in 2017—beyond protein family and domain annotations · 2016
No notice
17.
Gaudet P. et al (2011 ) Phylogenetic-based propagation of functional annotations within the gene ontology consortium. Brief. Bioinf., 12, 449.
Not in our library10.1093/bib/bbr042
18.
Gkoutos G.V. et al (2017 ) The anatomy of phenotype ontologies: principles, properties and applications. Brief. Bioinf., doi: 10.1093/bib/bbx035.
Not in our library10.1093/bib/bbx035
19.
Glorot X., Bengio Y. (2010 ) Understanding the difficulty of training deep feedforward neural networks. In: Aistats, vol. 9, pp. 249–256.
Not in our library
20.
Gong Q. et al (2016 ) Gofdr: a sequence alignment based method for predicting protein functions. Methods, 93, 3–14. Computational protein function predictions.
Not in our library10.1016/j.ymeth.2015.08.009
21.
Hinton G.E. (1986 ) Learning distributed representations of concepts. In: Proceedings of the eighth annual conference of the cognitive science society, vol. 1. Amherst, MA, p. 12.
Not in our library
22.
Hou J. (2017 ) Chapter 7 - protein function prediction from functional connectivity In: Hou J. (ed.) New Approaches of Protein Function Prediction from Protein Interaction Networks. Academic Press, Salt Lake City, UT, USA, pp. 97–105.
Not in our library
23.
eggNOG 4.5: a hierarchical orthology framework with improved functional annotations for eukaryotic, prokaryotic and viral sequences · 2015
No notice
24.
Jiang J.Q., McQuay L.J. (2012 ) Predicting protein function by multi-label correlated semi-supervised learning. IEEE/ACM Trans. Comput. Biol. Bioinf., 9, 1059–1069.
Not in our library10.1109/tcbb.2011.156
25.
Kirac M., Ozsoyoglu G. (2008 ) Protein Function Prediction Based on Patterns in Biological Networks. Springer, Berlin, Heidelberg, pp. 197–213.
Not in our library
26.
Konc J. et al (2013 ) Structure-based function prediction of uncharacterized protein using binding sites comparison. PLOS Comput. Biol., 9, e1003341.
Not in our library10.1371/journal.pcbi.1003341
27.
LeCun,Y. and Bengio,Y. (1998). Convolutional networks for images, speech, and time series. In: Arbib,A. (ed.) The handbook of brain theory and neural networks. MIT Press, Cambridge, MA, USA, pp. 255–258.
Not in our library
28.
Moult J. et al (2014 ) Critical assessment of methods of protein structure prediction (casp) round x. Proteins Struct. Funct. Bioinf., 82, 1–6.
Not in our library10.1002/prot.24452
29.
Nguyen C.D. et al (2011 ) Protein annotation from protein interaction networks and gene ontology. J. Biomed. Inf., 44, 824–829.
Not in our library10.1016/j.jbi.2011.04.010
30.
Annotating the human genome with Disease Ontology · 2009
No notice
31.
Radivojac P. et al (2013 ) A large-scale evaluation of computational protein function prediction. Nat. Methods, 10, 221–227.
Not in our library10.1038/nmeth.2340
32.
Resnik P. (1999 ) Semantic similarity in a taxonomy: an Information-Based measure and its application to problems of ambiguity in natural language. J. Artif. Intell. Res., 11, 95–130.
Not in our library
33.
Sharan R. et al (2007 ) Network-based prediction of protein function. Mol. Syst. Biol., 3, 1.
Not in our library10.1038/msb4100129
34.
Sokolov A., Ben-Hur A. (2010 ) Hierarchical classification of gene ontology terms using the gostruct method. J. Bioinf. Comput. Biol., 8, 357–376.
Not in our library10.1142/s0219720010004744
35.
STRING v10: protein–protein interaction networks, integrated over the tree of life · 2014
No notice
36.
Tieleman T., Hinton G. (2012 ) Lecture 6.5—RmsProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4, 26–31.
Not in our library
37.
Verspoor K.M. (2014 ) Roles for Text Mining in Protein Function Prediction. Springer, New York, NY, pp. 95–108.
Not in our library10.1007/978-1-4939-0709-0_6
38.
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model · 2017
No notice
39.
Wass M.N. et al (2012 ) Combfunc: predicting protein function using heterogeneous data sources. Nucleic Acids Res., 40, W466–W470.
Not in our library10.1093/nar/gks489
40.
Zhou J., Troyanskaya O.G. (2015 ) Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods, 12, 931–934.
Not in our library10.1038/nmeth.3547

Cited by papers we hold 9

Hierarchical graph learning for protein–protein interaction · 2023
No notice
ProteInfer, deep neural networks for protein functional inference · 2023
No notice
The STRING database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interest · 2022
No notice
Current progress and open challenges for applying deep learning across the biosciences · 2022
No notice
Structure-based protein function prediction using graph convolutional networks · 2021
No notice
The sterlet sturgeon genome sequence and the mechanisms of segmental rediploidization · 2020
No notice
UDSMProt: universal deep sequence models for protein classification · 2020
No notice
DeepGOPlus: improved protein function prediction from sequence · 2019
No notice
ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network · 2017
No notice

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.