{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:38:15Z","timestamp":1765438695220,"version":"3.41.2"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T00:00:00Z","timestamp":1616716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Genet."],"abstract":"<jats:p>Understanding the substrate specificity of HIV-1 protease plays an essential role in the prevention of HIV infection. A variety of computational models have thus been developed to predict substrate sites that are cleaved by HIV-1 protease, but most of them normally follow a supervised learning scheme to build classifiers by considering experimentally verified cleavable sites as positive samples and unknown sites as negative samples. However, certain noisy can be contained in the negative set, as false negative samples are possibly existed. Hence, the performance of the classifiers is not as accurate as they could be due to the biased prediction results. In this work, unknown substrate sites are regarded as unlabeled samples instead of negative ones. We propose a novel positive-unlabeled learning algorithm, namely PU-HIV, for an effective prediction of HIV-1 protease cleavage sites. Features used by PU-HIV are encoded from different perspectives of substrate sequences, including amino acid identities, coevolutionary patterns and chemical properties. By adjusting the weights of errors generated by positive and unlabeled samples, a biased support vector machine classifier can be built to complete the prediction task. In comparison with state-of-the-art prediction models, benchmarking experiments using cross-validation and independent tests demonstrated the superior performance of PU-HIV in terms of AUC, PR-AUC, and F-measure. Thus, with PU-HIV, it is possible to identify previously unknown, but physiologically existed substrate sites that are able to be cleaved by HIV-1 protease, thus providing valuable insights into designing novel HIV-1 protease inhibitors for HIV treatment.<\/jats:p>","DOI":"10.3389\/fgene.2021.658078","type":"journal-article","created":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T07:04:10Z","timestamp":1616742250000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Predicting HIV-1 Protease Cleavage Sites With Positive-Unlabeled Learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Zhenfeng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehai","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2021,3,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e1002634","DOI":"10.1371\/journal.ppat.1002634","article-title":"Cell-cell transmission enables HIV-1 to evade inhibition by potent CD4bs directed antibodies","volume":"8","author":"Abela","year":"2012","journal-title":"PLoS Pathog"},{"key":"B2","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1002\/jcc.10017","article-title":"Support vector machines for predicting HIV protease cleavage sites in protein","volume":"23","author":"Cai","year":"2002","journal-title":"J. Comput. Chem"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/abio.1996.0001","article-title":"Prediction of human immunodeficiency virus protease cleavage sites in proteins","volume":"233","author":"Chou","year":"1996","journal-title":"Anal. Biochem"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2857","DOI":"10.1093\/bioinformatics\/btn546","article-title":"Prediction of kinase-specific phosphorylation sites using conditional random fields","volume":"24","author":"Dang","year":"2008","journal-title":"Bioinformatics"},{"key":"B5","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between precision-recall and ROC curves","volume-title":"ICML '06: Proceedings of the International Conference on Machine Learning","author":"Davis","year":"2006"},{"key":"B6","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.virol.2004.10.023","article-title":"HIV-1 incorporates and proteolytically processes human NDR1 and NDR2 serine-threonine kinases","volume":"331","author":"Devroe","year":"2005","journal-title":"Virology"},{"volume-title":"UCI Machine Learning Repository","year":"2019","author":"Dua","key":"B7"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TPAMI.2010.95","article-title":"Maximum likelihood model selection for 1-norm soft margin SVMs with multiple parameters","volume":"32","author":"Glasmachers","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1007\/s00521-012-0967-5","article-title":"A new feature encoding scheme for HIV-1 protease cleavage site prediction","volume":"22","author":"G\u00f6k","year":"2013","journal-title":"Neural Comput. Appl"},{"key":"B10","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/TNB.2015.2429672","article-title":"Discovering variable-length patterns in protein sequences for protein-protein interaction prediction","volume":"14","author":"Hu","year":"2015","journal-title":"IEEE Trans. Nanobiosci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/TCBB.2016.2520923","article-title":"Extracting coevolutionary features from protein sequences for predicting protein-protein interactions","volume":"14","author":"Hu","year":"2017","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1109\/TCBB.2019.2914208","article-title":"Incorporating the coevolving information of substrates in predicting HIV-1 protease cleavage sites","volume":"17","author":"Hu","year":"","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa775","article-title":"HiSCF: leveraging higher-order structures for clustering analysis in biological networks","author":"Hu","year":"","journal-title":"Bioinformatics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1002\/prot.21415","article-title":"Computational proteomics analysis of HIV-1 protease interactome","volume":"68","author":"Kontijevskis","year":"2007","journal-title":"Proteins"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1093\/bioinformatics\/btz721","article-title":"Deepcleave: a deep learning predictor for caspase and matrix metalloprotease substrates and cleavage sites","volume":"36","author":"Li","year":"2020","journal-title":"Bioinformatics"},{"key":"B16","first-page":"387","article-title":"Partially supervised classification of text documents","volume-title":"ICML","author":"Liu","year":"2002"},{"key":"B17","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.1093\/bioinformatics\/18.suppl_1.S5","article-title":"Mining viral protease data to extract cleavage knowledge","volume":"18","author":"Narayanan","year":"2002","journal-title":"Bioinformatics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"B19","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/S0969-2126(02)00720-7","article-title":"Substrate shape determines specificity of recognition for HIV-1 protease: analysis of crystal structures of six substrate complexes","volume":"10","author":"Prabu-Jeyabalan","year":"2002","journal-title":"Structure"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1093\/bioinformatics\/bth144","article-title":"Why neural networks should not be used for HIV-1 protease cleavage site prediction","volume":"20","author":"R\u00f6gnvaldsson","year":"2004","journal-title":"Bioinformatics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1093\/bioinformatics\/btu810","article-title":"State of the art prediction of HIV-1 protease cleavage sites","volume":"31","author":"R\u00f6gnvaldsson","year":"2015","journal-title":"Bioinformatics"},{"key":"B22","doi-asserted-by":"publisher","first-page":"20449","DOI":"10.1073\/pnas.1210983109","article-title":"Kinetic characterization of the critical step in HIV-1 protease maturation","volume":"109","author":"Sadiq","year":"2012","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"B23","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.ab.2008.01.012","article-title":"HIVCleave: a web-server for predicting human immunodeficiency virus protease cleavage sites in proteins","volume":"375","author":"Shen","year":"2008","journal-title":"Anal. Biochem"},{"key":"B24","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1093\/bioinformatics\/btx670","article-title":"Prosperous: high-throughput prediction of substrate cleavage sites for 90 proteases with improved accuracy","volume":"34","author":"Song","year":"2018","journal-title":"Bioinformatics"},{"key":"B25","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1093\/bib\/bby028","article-title":"iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites","volume":"20","author":"Song","year":"2019","journal-title":"Brief. Bioinformatics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1006\/jtbi.1995.0254","article-title":"Neural network prediction of the HIV-1 protease cleavage sites","volume":"177","author":"Thompson","year":"1995","journal-title":"J. Theor. Biol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2787","DOI":"10.1093\/molbev\/msm213","article-title":"A study of the coevolutionary patterns operating within the env gene of the HIV-1 group m subtypes","volume":"24","author":"Travers","year":"2007","journal-title":"Mol. Biol. Evol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12977-015-0200-6","article-title":"HIV-1 protease cleaves the serine-threonine kinases RIPK1 and RIPK2","volume":"12","author":"Wagner","year":"2015","journal-title":"Retrovirology"},{"key":"B29","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1126\/science.2537531","article-title":"Molecular modeling of the HIV-1 protease and its substrate binding site","volume":"243","author":"Weber","year":"1989","journal-title":"Science"},{"key":"B30","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1093\/bioinformatics\/btv550","article-title":"Positive-unlabeled ensemble learning for kinase substrate prediction from dynamic phosphoproteomics data","volume":"32","author":"Yang","year":"2016","journal-title":"Bioinformatics"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2640","DOI":"10.1093\/bioinformatics\/bts504","article-title":"Positive-unlabeled learning for disease gene identification","volume":"28","author":"Yang","year":"2012","journal-title":"Bioinformatics"},{"key":"B32","doi-asserted-by":"publisher","first-page":"12477","DOI":"10.1128\/JVI.79.19.12477-12486.2005","article-title":"Comprehensive bioinformatic analysis of the specificity of human immunodeficiency virus type 1 protease","volume":"79","author":"You","year":"2005","journal-title":"J. Virol"}],"container-title":["Frontiers in Genetics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2021.658078\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T07:04:14Z","timestamp":1616742254000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fgene.2021.658078\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,26]]},"references-count":32,"alternative-id":["10.3389\/fgene.2021.658078"],"URL":"https:\/\/doi.org\/10.3389\/fgene.2021.658078","relation":{},"ISSN":["1664-8021"],"issn-type":[{"type":"electronic","value":"1664-8021"}],"subject":[],"published":{"date-parts":[[2021,3,26]]},"article-number":"658078"}}