{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:23:48Z","timestamp":1774052628312,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T00:00:00Z","timestamp":1653868800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T00:00:00Z","timestamp":1653868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100019081","name":"Science and Technology Program of Hunan Province","doi-asserted-by":"publisher","award":["2020JJ4648"],"award-info":[{"award-number":["2020JJ4648"]}],"id":[{"id":"10.13039\/501100019081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772089"],"award-info":[{"award-number":["61772089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The accurate characterization of protein functions is critical to understanding life at the molecular level and has a huge impact on biomedicine and pharmaceuticals. Computationally predicting protein function has been studied in the past decades. Plagued by noise and errors in protein\u2013protein interaction (PPI) networks, researchers have undertaken to focus on the fusion of multi-omics data in recent years. A data model that appropriately integrates network topologies with biological data and preserves their intrinsic characteristics is still a bottleneck and an aspirational goal for protein function prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this paper, we propose the RWRT (Random Walks with Restart on Tensor) method to accomplish protein function prediction by applying bi-random walks on the tensor. RWRT firstly constructs a functional similarity tensor by combining protein interaction networks with multi-omics data derived from domain annotation and protein complex information. After this, RWRT extends the bi-random walks algorithm from a two-dimensional matrix to the tensor for scoring functional similarity between proteins. Finally, RWRT filters out possible pretenders based on the concept of cohesiveness coefficient and annotates target proteins with functions of the remaining functional partners. Experimental results indicate that RWRT performs significantly better than the state-of-the-art methods and improves the area under the receiver-operating curve (AUROC) by no less than 18%.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The functional similarity tensor offers us an alternative, in that it is a collection of networks sharing the same nodes; however, the edges belong to different categories or represent interactions of different nature. We demonstrate that the tensor-based random walk model can not only discover more partners with similar functions but also free from the constraints of errors in protein interaction networks effectively. We believe that the performance of function prediction depends greatly on whether we can extract and exploit proper functional similarity information on protein correlations.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-022-04747-2","type":"journal-article","created":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T11:03:54Z","timestamp":1653908634000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A tensor-based bi-random walks model for protein function prediction"],"prefix":"10.1186","volume":"23","author":[{"given":"Sai","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijun","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiping","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bihai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,30]]},"reference":[{"issue":"12","key":"4747_CR1","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1038\/82360","volume":"18","author":"B Schwikowski","year":"2000","unstructured":"Schwikowski B, Uetz P, Fields S. A network of protein\u2013protein interactions in yeast. Nat Biotechnol. 2000;18(12):1257\u201361.","journal-title":"Nat Biotechnol"},{"issue":"13","key":"4747_CR2","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1093\/bioinformatics\/btl145","volume":"22","author":"HN Chua","year":"2006","unstructured":"Chua HN, Sung WK, Wong L. Exploiting indirect neighbours and topological weight to predict protein function from protein\u2013protein interactions. Bioinformatics. 2006;22(13):1623\u201330.","journal-title":"Bioinformatics"},{"issue":"1","key":"4747_CR3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.compbiolchem.2012.12.003","volume":"43C","author":"S Moosavi","year":"2013","unstructured":"Moosavi S, Rahgozar M, Rahimi A. Protein function prediction using neighbor relativity in protein\u2013protein interaction network. Comput Biol Chem. 2013;43C(1):11\u20136.","journal-title":"Comput Biol Chem"},{"issue":"6","key":"4747_CR4","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1038\/nbt825","volume":"21","author":"A Vazquez","year":"2003","unstructured":"Vazquez A, Flammini A, Maritan A, et al. Global protein function prediction from protein\u2013protein interaction networks. Nat Biotechnol. 2003;21(6):697\u2013700.","journal-title":"Nat Biotechnol"},{"issue":"suppl 1","key":"4747_CR5","doi-asserted-by":"publisher","first-page":"i302","DOI":"10.1093\/bioinformatics\/bti1054","volume":"21","author":"E Nabieva","year":"2005","unstructured":"Nabieva E, Jim K, Agarwal A, et al. Whole-proteome prediction of protein function via graph-theoretic analysis of interaction maps. Bioinformatics. 2005;21(suppl 1):i302\u201310.","journal-title":"Bioinformatics"},{"key":"4747_CR6","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.ymeth.2015.09.011","volume":"93","author":"R Cao","year":"2016","unstructured":"Cao R, Cheng J. Integrated protein function prediction by mining function associations, sequences, and protein\u2013protein and gene\u2013gene interaction networks. Methods. 2016;93:84\u201391.","journal-title":"Methods"},{"issue":"3","key":"4747_CR7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0090962","volume":"9","author":"B Liao","year":"2014","unstructured":"Liao B, Li Y, Jiang Y, et al. Using multi-instance hierarchical clustering learning system to predict yeast gene function. PLoS ONE. 2014;9(3): e90962.","journal-title":"PLoS ONE"},{"issue":"1","key":"4747_CR8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/1752-0509-7-61","volume":"7","author":"S Liang","year":"2013","unstructured":"Liang S, Zheng D, Standley DM, et al. A novel function prediction approach using protein overlap networks. BMC Syst Biol. 2013;7(1):61.","journal-title":"BMC Syst Biol"},{"key":"4747_CR9","doi-asserted-by":"crossref","unstructured":"Sarker B, Rtichie D W, Aridhi S. Exploiting complex protein domain networks for protein function annotation. In: International conference on complex networks and their applications. Springer, Cham, p. 598\u2013610; 2018.","DOI":"10.1007\/978-3-030-05414-4_48"},{"issue":"2","key":"4747_CR10","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1109\/TCBB.2015.2394314","volume":"14","author":"P Wei","year":"2017","unstructured":"Wei P, Min L, Lu C, et al. Predicting protein functions by using unbalanced random walk algorithm on three biological networks. IEEE\/ACM Trans Comput Biol Bioinf. 2017;14(2):360.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"},{"issue":"2","key":"4747_CR11","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TNB.2016.2536161","volume":"15","author":"B Zhao","year":"2016","unstructured":"Zhao B, Wang J, Li M, et al. A new method for predicting protein functions from dynamic weighted interactome networks. IEEE Trans Nanobiosci. 2016;15(2):131\u20139.","journal-title":"IEEE Trans Nanobiosci"},{"issue":"1","key":"4747_CR12","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1186\/1471-2105-10-395","volume":"10","author":"S Zhang","year":"2009","unstructured":"Zhang S, Chen H, Liu K, et al. Inferring protein function by domain context similarities in protein\u2013protein interaction networks. BMC Bioinform. 2009;10(1):395.","journal-title":"BMC Bioinform"},{"issue":"1","key":"4747_CR13","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/1752-0509-8-35","volume":"8","author":"W Peng","year":"2014","unstructured":"Peng W, Wang J, Cai J, et al. Improving protein function prediction using domain and protein complexes in PPI networks. BMC Syst Biol. 2014;8(1):35.","journal-title":"BMC Syst Biol"},{"key":"4747_CR14","doi-asserted-by":"crossref","unstructured":"Rehman H U, Benso A, Di Carlo S, et al. Combining homolog and motif similarity data with Gene Ontology relationships for protein function prediction. In: 2012 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, p. 1\u20134; 2012.","DOI":"10.1109\/BIBM.2012.6392719"},{"issue":"W1","key":"4747_CR15","doi-asserted-by":"publisher","first-page":"W134","DOI":"10.1093\/nar\/gkv523","volume":"43","author":"D Piovesan","year":"2015","unstructured":"Piovesan D, Giollo M, Leonardi E, et al. INGA: protein function prediction combining interaction networks, domain assignments and sequence similarity. Nucleic Acids Res. 2015;43(W1):W134\u201340.","journal-title":"Nucleic Acids Res"},{"issue":"W1","key":"4747_CR16","doi-asserted-by":"publisher","first-page":"W373","DOI":"10.1093\/nar\/gkz375","volume":"47","author":"D Piovesan","year":"2019","unstructured":"Piovesan D, Tosatto SCE. INGA 2.0: improving protein function prediction for the dark proteome. Nucleic Acids Res. 2019;47(W1):W373\u20138.","journal-title":"Nucleic Acids Res"},{"issue":"7","key":"4747_CR17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0160098","volume":"11","author":"MJ O\u2019Meara","year":"2016","unstructured":"O\u2019Meara MJ, Ballouz S, Shoichet BK, et al. Ligand similarity complements sequence, physical interaction, and co-expression for gene function prediction. PLoS ONE. 2016;11(7): e0160098.","journal-title":"PLoS ONE"},{"issue":"4","key":"4747_CR18","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1093\/bioinformatics\/btz731","volume":"36","author":"S Makrodimitris","year":"2020","unstructured":"Makrodimitris S, Reinders MJT, Van Ham RCHJ. Metric learning on expression data for gene function prediction. Bioinformatics. 2020;36(4):1182\u201390.","journal-title":"Bioinformatics"},{"issue":"1","key":"4747_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-23303-9","volume":"12","author":"V Gligorijevi\u0107","year":"2021","unstructured":"Gligorijevi\u0107 V, Renfrew PD, Kosciolek T, et al. Structure-based protein function prediction using graph convolutional networks. Nat Commun. 2021;12(1):1\u201314.","journal-title":"Nat Commun"},{"key":"4747_CR20","doi-asserted-by":"crossref","unstructured":"Martiniano HFMC, Asif M, Vicente AM, et al. Network propagation-based semi-supervised identification of genes associated with autism spectrum disorder. In: International meeting on computational intelligence methods for bioinformatics and biostatistics. Springer, Cham, p. 239\u2013248; 2018.","DOI":"10.1007\/978-3-030-34585-3_21"},{"issue":"1","key":"4747_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-019-2930-2","volume":"20","author":"BH Zhao","year":"2019","unstructured":"Zhao BH, Zhao YL, Zhang XX, et al. An iteration method for identifying yeast essential proteins from heterogeneous network. BMC Bioinform. 2019;20(1):1\u201313.","journal-title":"BMC Bioinform"},{"issue":"13","key":"4747_CR22","doi-asserted-by":"publisher","first-page":"i484","DOI":"10.1093\/bioinformatics\/bty247","volume":"34","author":"W Zhang","year":"2018","unstructured":"Zhang W, Ma J, Ideker T. Classifying tumors by supervised network propagation. Bioinformatics. 2018;34(13):i484\u201393.","journal-title":"Bioinformatics"},{"issue":"8","key":"4747_CR23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009263","volume":"17","author":"EM Novoa-del-Toro","year":"2021","unstructured":"Novoa-del-Toro EM, Mezura-Montes E, Vignes M, et al. A multi-objective genetic algorithm to find active modules in multiplex biological networks. PLoS Comput Biol. 2021;17(8): e1009263.","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"4747_CR24","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/MNET.2018.1800192","volume":"33","author":"X Wang","year":"2019","unstructured":"Wang X, Yang LT, Kuang L, et al. A tensor-based big-data-driven routing recommendation approach for heterogeneous networks. IEEE Netw. 2019;33(1):64\u20139.","journal-title":"IEEE Netw"},{"issue":"15","key":"4747_CR25","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1093\/bioinformatics\/btn312","volume":"24","author":"K Forslund","year":"2008","unstructured":"Forslund K, Sonnhammer ELL. Predicting protein function from domain content. Bioinformatics. 2008;24(15):1681\u20137.","journal-title":"Bioinformatics"},{"key":"4747_CR26","first-page":"903","volume":"7","author":"J Li","year":"2016","unstructured":"Li J, Zhao PX. Mining functional modules in heterogeneous biological networks using multiplex PageRank approach. Front Plant Sci. 2016;7:903.","journal-title":"Front Plant Sci"},{"issue":"18","key":"4747_CR27","first-page":"2023","volume":"24","author":"H Taehyun","year":"2014","unstructured":"Taehyun H, Hugues S, Tian Z, et al. Robust and efficient identification of biomarkers by classifying features on graphs. Bioinformatics. 2014;24(18):2023\u20139.","journal-title":"Bioinformatics"},{"issue":"1","key":"4747_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000641","volume":"6","author":"O Vanunu","year":"2010","unstructured":"Vanunu O, Magger O, Ruppin E, et al. Associating genes and protein complexes with disease via network propagation. PLoS Comput Biol. 2010;6(1): e1000641.","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"4747_CR29","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1186\/s12859-020-03663-7","volume":"21","author":"B Zhao","year":"2020","unstructured":"Zhao B, Zhang Z, Jiang M, et al. NPF:network propagation for protein function prediction. BMC Bioinform. 2020;21(1):355.","journal-title":"BMC Bioinform"},{"issue":"6761","key":"4747_CR30","doi-asserted-by":"publisher","first-page":"C47","DOI":"10.1038\/35011540","volume":"402","author":"L Hartwell","year":"1999","unstructured":"Hartwell L, Hopfield J, Leibler S, Murray AW. From molecular to modular cell biology. Nature. 1999;402(6761):C47\u201352.","journal-title":"Nature"},{"issue":"5","key":"4747_CR31","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nmeth.1938","volume":"9","author":"T Nepusz","year":"2012","unstructured":"Nepusz T, Yu H, Paccanaro A. Detecting overlapping protein complexes in protein\u2013protein interaction networks. Nat Methods. 2012;9(5):471\u20132.","journal-title":"Nat Methods"},{"issue":"1","key":"4747_CR32","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1093\/nar\/30.1.303","volume":"30","author":"I Xenarios","year":"2002","unstructured":"Xenarios I, Salwinski L, Duan XJ, et al. DIP, the Database of Interacting Proteins: a research tool for studying cellular networks of protein interactions. Nucleic Acids Res. 2002;30(1):303\u20135.","journal-title":"Nucleic Acids Res"},{"issue":"D1","key":"4747_CR33","doi-asserted-by":"publisher","first-page":"D529","DOI":"10.1093\/nar\/gky1079","volume":"47","author":"R Oughtred","year":"2019","unstructured":"Oughtred R, Stark C, Breitkreutz BJ, et al. The BioGRID interaction database: 2019 update. Nucleic Acids Res. 2019;47(D1):D529\u201341.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"4747_CR34","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","volume":"25","author":"M Ashburner","year":"2000","unstructured":"Ashburner M, Ball CA, Blake JA, et al. Gene Ontology: tool for the unification of biology. Nat Genet. 2000;25(1):25\u20139.","journal-title":"Nat Genet"},{"issue":"suppl 1","key":"4747_CR35","doi-asserted-by":"publisher","first-page":"D138","DOI":"10.1093\/nar\/gkh121","volume":"32","author":"A Bateman","year":"2004","unstructured":"Bateman A, Coin L, Durbin R, et al. The Pfam protein families database. Nucleic Acids Res. 2004;32(suppl 1):D138\u201341.","journal-title":"Nucleic Acids Res"},{"key":"4747_CR36","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1093\/nar\/gkn1005","volume":"37","author":"S Pu","year":"2009","unstructured":"Pu S, Wong J, Turner B, et al. Up-to-date catalogues of yeast protein complexes. Nucleic Acids Res. 2009;37:825\u201331.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"4747_CR37","doi-asserted-by":"publisher","first-page":"bbab432","DOI":"10.1093\/bib\/bbab432","volume":"23","author":"W Peng","year":"2022","unstructured":"Peng W, Tang Q, Dai W, et al. Improving cancer driver gene identification using multi-task learning on graph convolutional network. Brief Bioinform. 2022;23(1):bbab432.","journal-title":"Brief Bioinform"},{"key":"4747_CR38","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ymeth.2020.07.013","volume":"192","author":"W Peng","year":"2021","unstructured":"Peng W, Yi S, Dai W, et al. Identifying and ranking potential cancer drivers using representation learning on attributed network. Methods. 2021;192:13\u201324.","journal-title":"Methods"},{"issue":"3","key":"4747_CR39","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1109\/TCBB.2019.2897931","volume":"17","author":"J Song","year":"2019","unstructured":"Song J, Peng W, Wang F. An Entropy-based method for identifying mutual exclusive driver genes in cancer. IEEE\/ACM Trans Comput Biol Bioinf. 2019;17(3):758\u201368.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04747-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-022-04747-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-022-04747-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T18:38:49Z","timestamp":1675708729000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-022-04747-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,30]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["4747"],"URL":"https:\/\/doi.org\/10.1186\/s12859-022-04747-2","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,30]]},"assertion":[{"value":"25 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"199"}}