Hierarchical Deep Learning for Predicting GO Annotations by Integrating Protein Knowledge

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2022 Aug 5

PMID 35929781

Authors

Gabriela A Merino

Rabie Saidi

Diego H Milone

Georgina Stegmayer

Maria J Martin

Affiliations

Soon will be listed here.

Abstract

Motivation: Experimental testing and manual curation are the most precise ways for assigning Gene Ontology (GO) terms describing protein functions. However, they are expensive, time-consuming and cannot cope with the exponential growth of data generated by high-throughput sequencing methods. Hence, researchers need reliable computational systems to help fill the gap with automatic function prediction. The results of the last Critical Assessment of Function Annotation challenge revealed that GO-terms prediction remains a very challenging task. Recent developments on deep learning are significantly breaking out the frontiers leading to new knowledge in protein research thanks to the integration of data from multiple sources. However, deep models hitherto developed for functional prediction are mainly focused on sequence data and have not achieved breakthrough performances yet.

Results: We propose DeeProtGO, a novel deep-learning model for predicting GO annotations by integrating protein knowledge. DeeProtGO was trained for solving 18 different prediction problems, defined by the three GO sub-ontologies, the type of proteins, and the taxonomic kingdom. Our experiments reported higher prediction quality when more protein knowledge is integrated. We also benchmarked DeeProtGO against state-of-the-art methods on public datasets, and showed it can effectively improve the prediction of GO annotations.

Availability And Implementation: DeeProtGO and a case of use are available at https://github.com/gamerino/DeeProtGO.

Supplementary Information: Supplementary data are available at Bioinformatics online.

Citing Articles

The CABANA model 2017-2022: research and training synergy to facilitate bioinformatics applications in Latin America.

Campos-Sanchez R, Willis I, Gopalasingam P, Lopez-Juarez D, Cristancho M, Brooksbank C Front Educ (Lausanne). 2024; 9.

PMID: 39686965 PMC: 7617245. DOI: 10.3389/feduc.2024.1358620.

Optimizing Scorpion Toxin Processing through Artificial Intelligence.

Psenicnik A, Ojanguren-Affilastro A, Graham M, Hassan M, Abdel-Rahman M, Sharma P Toxins (Basel). 2024; 16(10).

PMID: 39453213 PMC: 11511117. DOI: 10.3390/toxins16100437.

Osmoprotectants play a major role in the resistance to high levels of salinity stress-insights from a metabolomics and proteomics integrated approach.

Rodrigues Neto J, Salgado F, Braga I, Carvalho da Silva T, Belo Silva V, Leao A Front Plant Sci. 2023; 14:1187803.

PMID: 37384354 PMC: 10296175. DOI: 10.3389/fpls.2023.1187803.

PFresGO: an attention mechanism-based deep-learning approach for protein annotation by integrating gene ontology inter-relationships.

Pan T, Li C, Bi Y, Wang Z, Gasser R, Purcell A Bioinformatics. 2023; 39(3).

PMID: 36794913 PMC: 9978587. DOI: 10.1093/bioinformatics/btad094.

Elucidating the functional roles of prokaryotic proteins using big data and artificial intelligence.

Ardern Z, Chakraborty S, Lenk F, Kaster A FEMS Microbiol Rev. 2023; 47(1).

PMID: 36725215 PMC: 9960493. DOI: 10.1093/femsre/fuad003.

References

Littmann M, Heinzinger M, Dallago C, Olenyi T, Rost B . Embeddings from deep learning transfer GO annotations beyond homology. Sci Rep. 2021; 11(1):1160. PMC: 7806674. DOI: 10.1038/s41598-020-80786-0. View

Rost B, Liu J, Nair R, Wrzeszczynski K, Ofran Y . Automatic prediction of protein function. Cell Mol Life Sci. 2003; 60(12):2637-50. PMC: 11138487. DOI: 10.1007/s00018-003-3114-8. View

Raad J, Stegmayer G, Milone D . Complexity measures of the mature miRNA for improving pre-miRNAs prediction. Bioinformatics. 2019; 36(8):2319-2327. DOI: 10.1093/bioinformatics/btz940. View

Bonetta R, Valentino G . Machine learning techniques for protein function prediction. Proteins. 2019; 88(3):397-413. DOI: 10.1002/prot.25832. View

Zhou N, Jiang Y, Bergquist T, Lee A, Kacsoh B, Crocker A . The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens. Genome Biol. 2019; 20(1):244. PMC: 6864930. DOI: 10.1186/s13059-019-1835-8. View

Kulmanov M, Hoehndorf R . DeepGOPlus: improved protein function prediction from sequence. Bioinformatics. 2019; 36(2):422-429. PMC: 9883727. DOI: 10.1093/bioinformatics/btz595. View

Cruz L, Trefflich S, Weiss V, Castro M . Protein Function Prediction. Methods Mol Biol. 2017; 1654:55-75. DOI: 10.1007/978-1-4939-7231-9_5. View

. UniProt: a worldwide hub of protein knowledge. Nucleic Acids Res. 2018; 47(D1):D506-D515. PMC: 6323992. DOI: 10.1093/nar/gky1049. View

Klopfenstein D, Zhang L, Pedersen B, Ramirez F, Warwick Vesztrocy A, Naldi A . GOATOOLS: A Python library for Gene Ontology analyses. Sci Rep. 2018; 8(1):10872. PMC: 6052049. DOI: 10.1038/s41598-018-28948-z. View

10.

You R, Zhang Z, Xiong Y, Sun F, Mamitsuka H, Zhu S . GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank. Bioinformatics. 2018; 34(14):2465-2473. DOI: 10.1093/bioinformatics/bty130. View

11.

Makrodimitris S, van Ham R, Reinders M . Automatic Gene Function Prediction in the 2020's. Genes (Basel). 2020; 11(11). PMC: 7692357. DOI: 10.3390/genes11111264. View

12.

Shi Q, Chen W, Huang S, Wang Y, Xue Z . Deep learning for mining protein data. Brief Bioinform. 2019; 22(1):194-218. DOI: 10.1093/bib/bbz156. View

13.

You R, Yao S, Xiong Y, Huang X, Sun F, Mamitsuka H . NetGO: improving large-scale protein function prediction with massive network information. Nucleic Acids Res. 2019; 47(W1):W379-W387. PMC: 6602452. DOI: 10.1093/nar/gkz388. View

14.

Rifaioglu A, Dogan T, Martin M, Cetin-Atalay R, Atalay V . DEEPred: Automated Protein Function Prediction with Multi-task Feed-forward Deep Neural Networks. Sci Rep. 2019; 9(1):7344. PMC: 6517386. DOI: 10.1038/s41598-019-43708-3. View

15.

Heinzinger M, Elnaggar A, Wang Y, Dallago C, Nechaev D, Matthes F . Modeling aspects of the language of life through transfer-learning protein sequences. BMC Bioinformatics. 2019; 20(1):723. PMC: 6918593. DOI: 10.1186/s12859-019-3220-8. View

16.

Liu J, Wu T, Guo Z, Hou J, Cheng J . Improving protein tertiary structure prediction by deep learning and distance prediction in CASP14. Proteins. 2021; 90(1):58-72. PMC: 8671168. DOI: 10.1002/prot.26186. View

17.

Cao Y, Shen Y . TALE: Transformer-based protein function Annotation with joint sequence-Label Embedding. Bioinformatics. 2021; 37(18):2825-2833. PMC: 8479653. DOI: 10.1093/bioinformatics/btab198. View

18.

You R, Huang X, Zhu S . DeepText2GO: Improving large-scale protein function prediction with deep semantic text representation. Methods. 2018; 145:82-90. DOI: 10.1016/j.ymeth.2018.05.026. View

19.

Elnaggar A, Heinzinger M, Dallago C, Rehawi G, Wang Y, Jones L . ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning. IEEE Trans Pattern Anal Mach Intell. 2021; 44(10):7112-7127. DOI: 10.1109/TPAMI.2021.3095381. View

20.

Jiang Y, Ronnen Oron T, Clark W, Bankapur A, DAndrea D, Lepore R . An expanded evaluation of protein function prediction methods shows an improvement in accuracy. Genome Biol. 2016; 17(1):184. PMC: 5015320. DOI: 10.1186/s13059-016-1037-6. View