{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T21:05:22Z","timestamp":1773954322574,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"S16","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T00:00:00Z","timestamp":1608076800000},"content-version":"vor","delay-in-days":15,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Maize (<jats:italic>Zea mays<\/jats:italic>ssp. mays L.) is the most widely grown and yield crop in the world, as well as an important model organism for fundamental research of the function of genes. The functions of Maize proteins are annotated using the Gene Ontology (GO), which has more than 40000 terms and organizes GO terms in a direct acyclic graph (DAG). It is a huge challenge to accurately annotate relevant GO terms to a Maize protein from such a large number of candidate GO terms. Some deep learning models have been proposed to predict the protein function, but the effectiveness of these approaches is unsatisfactory. One major reason is that they inadequately utilize the GO hierarchy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To use the knowledge encoded in the GO hierarchy, we propose a deep Graph Convolutional Network (GCN) based model (DeepGOA) to predict GO annotations of proteins. DeepGOA firstly quantifies the correlations (or edges) between GO terms and updates the edge weights of the DAG by leveraging GO annotations and hierarchy, then learns the semantic representation and latent inter-relations of GO terms in the way by applying GCN on the updated DAG. Meanwhile, Convolutional Neural Network (CNN) is used to learn the feature representation of amino acid sequences with respect to the semantic representations. After that, DeepGOA computes the dot product of the two representations, which enable to train the whole network end-to-end coherently. Extensive experiments show that DeepGOA can effectively integrate GO structural information and amino acid information, and then annotates proteins accurately.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Experiments on Maize PH207 inbred line and Human protein sequence dataset show that DeepGOA outperforms the state-of-the-art deep learning based methods. The ablation study proves that GCN can employ the knowledge of GO and boost the performance. Codes and datasets are available at<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/mlda.swu.edu.cn\/codes.php?name=DeepGOA\">http:\/\/mlda.swu.edu.cn\/codes.php?name=DeepGOA<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-020-03745-6","type":"journal-article","created":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T02:02:40Z","timestamp":1608084160000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Predicting functions of maize proteins using graph convolutional network"],"prefix":"10.1186","volume":"21","author":[{"given":"Guangjie","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Maozu","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-6705","authenticated-orcid":false,"given":"Guoxian","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,12,16]]},"reference":[{"issue":"5956","key":"3745_CR1","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1126\/science.1178534","volume":"326","author":"PS Schnable","year":"2009","unstructured":"Schnable PS, Ware D, Fulton RS, Stein JC, Wei F, Pasternak S, Liang C, Zhang J, Fulton L, Graves TA, et al. The b73 maize genome: complexity, diversity, and dynamics. Science. 2009; 326(5956):1112\u20135.","journal-title":"Science"},{"issue":"5726","key":"3745_CR2","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1126\/science.1107891","volume":"308","author":"SI Wright","year":"2005","unstructured":"Wright SI, Bi IV, Schroeder SG, Yamasaki M, Doebley JF, McMullen MD, Gaut BS. The effects of artificial selection on the maize genome. Science. 2005; 308(5726):1310\u20134.","journal-title":"Science"},{"issue":"5428","key":"3745_CR3","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1126\/science.285.5428.751","volume":"285","author":"EM Marcotte","year":"1999","unstructured":"Marcotte EM, Pellegrini M, Ng H-L, Rice DW, Yeates TO, Eisenberg D. Detecting protein function and protein-protein interactions from genome sequences. Science. 1999; 285(5428):751\u20133.","journal-title":"Science"},{"issue":"3","key":"3745_CR4","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1038\/nmeth.2340","volume":"10","author":"P Radivojac","year":"2013","unstructured":"Radivojac P, Clark WT, Oron TR, Schnoes AM, Wittkop T, Sokolov A, Graim K, Funk C, Verspoor K, Ben-Hur A. A large-scale evaluation of computational protein function prediction. Nat Methods. 2013; 10(3):221.","journal-title":"Nat Methods"},{"key":"3745_CR5","volume-title":"Big data analytics in genomics","author":"A Shehu","year":"2016","unstructured":"Shehu A, Barbar\u00e1 D, Molloy K. A survey of computational methods for protein function prediction In: Wong KC, editor. Big data analytics in genomics. Cham: Springer: 2016. p. 225\u201398."},{"issue":"7659","key":"3745_CR6","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1038\/nature22971","volume":"546","author":"Y Jiao","year":"2017","unstructured":"Jiao Y, Peluso P, Shi J, Liang T, Stitzer MC, Wang B, Campbell MS, Stein JC, Wei X, Chin C-S, et al. Improved maize reference genome with single-molecule technologies. Nature. 2017; 546(7659):524\u20137.","journal-title":"Nature"},{"issue":"5","key":"3745_CR7","doi-asserted-by":"crossref","first-page":"1003063","DOI":"10.1371\/journal.pcbi.1003063","volume":"9","author":"AM Schnoes","year":"2013","unstructured":"Schnoes AM, Ream DC, Thorman AW, Babbitt PC, Friedberg I. Biases in the experimental annotations of protein function and their effect on our understanding of protein function space. PLoS Comput Biol. 2013; 9(5):1003063.","journal-title":"PLoS Comput Biol"},{"issue":"7","key":"3745_CR8","doi-asserted-by":"crossref","first-page":"1000431","DOI":"10.1371\/journal.pcbi.1000431","volume":"5","author":"PC Biol","year":"2009","unstructured":"Biol PC. The gene ontology\u2019s reference genome project: a unified framework for functional annotation across species. PLoS Comput Biol. 2009; 5(7):1000431.","journal-title":"PLoS Comput Biol"},{"issue":"2","key":"3745_CR9","doi-asserted-by":"crossref","first-page":"1002386","DOI":"10.1371\/journal.pcbi.1002386","volume":"8","author":"PD Thomas","year":"2012","unstructured":"Thomas PD, Wood V, Mungall CJ, Lewis SE, Blake JA. On the use of gene ontology annotations to assess functional similarity among orthologs and paralogs: A short report. PLoS Comput Biol. 2012; 8(2):1002386.","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"3745_CR10","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1186\/s13059-016-1037-6","volume":"17","author":"Y Jiang","year":"2016","unstructured":"Jiang Y, Oron TR, Clark WT, Bankapur AR, D\u2019Andrea D, Lepore R, Funk CS, Kahanda I, Verspoor KM, Ben-Hur A, et al. An expanded evaluation of protein function prediction methods shows an improvement in accuracy. Genome Biol. 2016; 17(1):184.","journal-title":"Genome Biol"},{"issue":"S1","key":"3745_CR11","first-page":"331","volume":"38","author":"GO Consortium","year":"2009","unstructured":"Consortium GO. The gene ontology in 2010: extensions and refinements. Nucleic Acids Res. 2009; 38(S1):331\u20135.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"3745_CR12","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/2047-217X-3-4","volume":"3","author":"RP Huntley","year":"2014","unstructured":"Huntley RP, Sawford T, Martin MJ, O\u2019Donovan C. Understanding how and why the gene ontology and its annotations evolve: the go within uniprot. GigaScience. 2014; 3(1):4.","journal-title":"GigaScience"},{"key":"3745_CR13","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4939-3743-1","volume-title":"The gene ontology handbook","author":"C Dessimoz","year":"2017","unstructured":"Dessimoz C, \u0160kunca N. The gene ontology handbook. New York: Springer; 2017."},{"issue":"3","key":"3745_CR14","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/TCBB.2010.38","volume":"8","author":"G Valentini","year":"2011","unstructured":"Valentini G. True path rule hierarchical ensembles for genome-wide gene function prediction. IEEE\/ACM Trans Comput Biol Bioinforma. 2011; 8(3):832\u201347.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinforma"},{"issue":"3","key":"3745_CR15","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1109\/TCBB.2013.142","volume":"11","author":"G Yu","year":"2014","unstructured":"Yu G, Rangwala H, Domeniconi C, Zhang G, Yu Z. Protein function prediction with incomplete annotations. IEEE\/ACM Trans Comput Biol Bioinforma. 2014; 11(3):579\u201391.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinforma"},{"issue":"3","key":"3745_CR16","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/TCBB.2011.148","volume":"9","author":"X-F Zhang","year":"2012","unstructured":"Zhang X-F, Dai D-Q. A framework for incorporating functional interrelationships into protein function prediction algorithms. IEEE\/ACM Trans Comput Biol Bioinforma. 2012; 9(3):740\u201353.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinforma"},{"issue":"4","key":"3745_CR17","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/TCBB.2013.111","volume":"10","author":"G Yu","year":"2013","unstructured":"Yu G, Rangwala H, Domeniconi C, Zhang G, Yu Z. Protein function prediction using multi-label ensemble classification. IEEE\/ACM Trans Comput Biol Bioinforma. 2013; 10(4):1045\u201357.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinforma"},{"issue":"1","key":"3745_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-014-0430-y","volume":"16","author":"G Yu","year":"2015","unstructured":"Yu G, Zhu H, Domeniconi C. Predicting protein functions using incomplete hierarchical labels. BMC Bioinformatics. 2015; 16(1):1.","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"3745_CR19","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1186\/1471-2105-10-142","volume":"10","author":"G Pandey","year":"2009","unstructured":"Pandey G, Myers CL, Kumar V. Incorporating functional inter-relationships into protein function prediction algorithms. BMC Bioinformatics. 2009; 10(1):142.","journal-title":"BMC Bioinformatics"},{"issue":"19","key":"3745_CR20","doi-asserted-by":"crossref","first-page":"2996","DOI":"10.1093\/bioinformatics\/btw366","volume":"32","author":"G Fu","year":"2016","unstructured":"Fu G, Wang J, Yang B, Yu G. Neggoa: Negative go annotations selection using ontology structure. Bioinformatics. 2016; 32(19):2996\u20133004.","journal-title":"Bioinformatics"},{"issue":"4","key":"3745_CR21","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1109\/TCBB.2017.2715842","volume":"15","author":"G Yu","year":"2018","unstructured":"Yu G, Fu G, Wang J, Zhao Y. Newgoa: Predicting new go annotations of proteins by bi-random walks on a hybrid graph. IEEE\/ACM Trans Comput Biol Bioinforma. 2018; 15(4):1390\u2013402.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinforma"},{"issue":"3","key":"3745_CR22","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.ygeno.2018.02.008","volume":"111","author":"Y Zhao","year":"2019","unstructured":"Zhao Y, Fu G, Wang J, Guo M, Yu G. Gene function prediction based on gene ontology hierarchy preserving hashing. Genomics. 2019; 111(3):334\u201342.","journal-title":"Genomics"},{"key":"3745_CR23","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.compbiolchem.2017.09.010","volume":"71","author":"G Yu","year":"2017","unstructured":"Yu G, Zhao Y, Lu C, Wang J. Hashgo: hashing gene ontology for protein function prediction. Comput Biol Chem. 2017; 71:264.","journal-title":"Comput Biol Chem"},{"issue":"3","key":"3745_CR24","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng L, Yu D. Deep learning: Methods and applications. Found Trends Sig Process. 2014; 7(3):197\u2013387.","journal-title":"Found Trends Sig Process"},{"key":"3745_CR25","volume-title":"Proceedings of the ACM Symposium on Applied Computing","author":"J Wehrmann","year":"2017","unstructured":"Wehrmann J, Barros RC, D\u00f4res SNd, Cerri R. Hierarchical multi-label classification with chained neural networks. In: Proceedings of the ACM Symposium on Applied Computing. New York: ACM Press: 2017. p. 790\u20135."},{"key":"3745_CR26","unstructured":"Rifaioglu AS, Do\u011fan T, Martin MJ, Cetin-Atalay R, Atalay MV. Multi-task deep neural networks in automated protein function prediction. arXiv preprint arXiv:1705.04802. 2017."},{"issue":"1","key":"3745_CR27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"AS Rifaioglu","year":"2019","unstructured":"Rifaioglu AS, Do\u011fan T, Martin MJ, Cetin-Atalay R, Atalay V. Deepred: automated protein function prediction with multi-task feed-forward deep neural networks. Sci Rep. 2019; 9(1):1\u201316.","journal-title":"Sci Rep"},{"issue":"11","key":"3745_CR28","doi-asserted-by":"crossref","first-page":"4337","DOI":"10.1073\/pnas.0607879104","volume":"104","author":"J Shen","year":"2007","unstructured":"Shen J, Zhang J, Luo X, Zhu W, Yu K, Chen K, Li Y, Jiang H. Predicting protein\u2013protein interactions based only on sequences information. Proc Natl Acad Sci. 2007; 104(11):4337\u201341.","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"3745_CR29","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1002\/prot.1035","volume":"43","author":"K-C Chou","year":"2001","unstructured":"Chou K-C. Prediction of protein cellular attributes using pseudo-amino acid composition. Proteins Struct Funct Bioinforma. 2001; 43(3):246\u201355.","journal-title":"Proteins Struct Funct Bioinforma"},{"issue":"2","key":"3745_CR30","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.compbiolchem.2007.11.004","volume":"32","author":"OS Sarac","year":"2008","unstructured":"Sarac OS, G\u00fcrsoy-Y\u00fcz\u00fcg\u00fcll\u00fc \u00d6, Cetin-Atalay R, Atalay V. Subsequence-based feature map for protein function classification. Comput Biol Chem. 2008; 32(2):122\u201330.","journal-title":"Comput Biol Chem"},{"issue":"4","key":"3745_CR31","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1093\/bioinformatics\/btx624","volume":"34","author":"M Kulmanov","year":"2017","unstructured":"Kulmanov M, Khan MA, Hoehndorf R. Deepgo: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics. 2017; 34(4):660\u20138.","journal-title":"Bioinformatics"},{"issue":"2","key":"3745_CR32","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1093\/bioinformatics\/btz595","volume":"36","author":"M Kulmanov","year":"2020","unstructured":"Kulmanov M, Hoehndorf R. Deepgoplus: improved protein function prediction from sequence. Bioinformatics. 2020; 36(2):422\u20139.","journal-title":"Bioinformatics"},{"key":"3745_CR33","volume-title":"Proceedings of the 31stAnnual International ACM SIGIR conference on research and development in information retrieval","author":"C Wang","year":"2008","unstructured":"Wang C, Zhang L, Zhang H-J. Learning to reduce the semantic gap in web image retrieval and annotation. In: Proceedings of the 31stAnnual International ACM SIGIR conference on research and development in information retrieval. New York: ACM Press: 2008. p. 355\u201362."},{"key":"3745_CR34","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. 2016."},{"issue":"17","key":"3745_CR35","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul SF, Madden TL, Sch\u00e4ffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ. Gapped blast and psi-blast: a new generation of protein database search programs. Nucleic Acids Res. 1997; 25(17):3389\u2013402.","journal-title":"Nucleic Acids Res"},{"key":"3745_CR36","volume-title":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"G Zhou","year":"2019","unstructured":"Zhou G, Wang J, Zhang X, Yu G. Deepgoa: Predicting gene ontology annotations of proteins via graph convolutional network. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). San Diego: IEEE: 2019. p. 1836\u201341."},{"issue":"13","key":"3745_CR37","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1093\/bioinformatics\/btt228","volume":"29","author":"WT Clark","year":"2013","unstructured":"Clark WT, Radivojac P. Information-theoretic evaluation of predicted ontological annotations. Bioinformatics. 2013; 29(13):53\u201361.","journal-title":"Bioinformatics"},{"issue":"11","key":"3745_CR38","doi-asserted-by":"crossref","first-page":"2700","DOI":"10.1105\/tpc.16.00353","volume":"28","author":"CN Hirsch","year":"2016","unstructured":"Hirsch CN, Hirsch CD, Brohammer AB, Bowman MJ, Soifer I, Barad O, Shem-Tov D, Baruch K, Lu F, Hernandez AG, et al. Draft assembly of elite inbred line ph207 provides insights into genomic and transcriptome diversity in maize. Plant Cell. 2016; 28(11):2700\u201314.","journal-title":"Plant Cell"},{"issue":"13","key":"3745_CR39","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1093\/bioinformatics\/btm195","volume":"23","author":"Y Tao","year":"2007","unstructured":"Tao Y, Sam L, Li J, Friedman C, Lussier YA. Information theory applied to the sparse gene ontology annotation network to predict novel gene function. Bioinformatics. 2007; 23(13):529\u201338.","journal-title":"Bioinformatics"},{"issue":"11","key":"3745_CR40","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1093\/bioinformatics\/btt160","volume":"29","author":"Z Teng","year":"2013","unstructured":"Teng Z, Guo M, Liu X, Dai Q, Wang C, Xuan P. Measuring gene functional similarity based on group-wise comparison of go terms. Bioinformatics. 2013; 29(11):1424\u201332.","journal-title":"Bioinformatics"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03745-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-020-03745-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-020-03745-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,15]],"date-time":"2023-10-15T10:32:40Z","timestamp":1697365960000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-020-03745-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":40,"journal-issue":{"issue":"S16","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["3745"],"URL":"https:\/\/doi.org\/10.1186\/s12859-020-03745-6","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"16 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"420"}}