{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:03:33Z","timestamp":1761059013209},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"S1","content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2010,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>In <jats:italic>supervised learning<\/jats:italic>, traditional approaches to building a classifier use two sets of examples with pre-defined classes along with a learning algorithm. The main limitation of this approach is that examples from both classes are required which might be infeasible in certain cases, especially those dealing with biological data. Such is the case for membrane-binding peripheral domains that play important roles in many biological processes, including cell signaling and membrane trafficking by reversibly binding to membranes. For these domains, a well-defined <jats:italic>positive<\/jats:italic> set is available with domains known to bind membrane along with a large <jats:italic>unlabeled<\/jats:italic> set of domains whose membrane binding affinities have not been measured. The aforementioned limitation can be addressed by a special class of <jats:italic>semi-supervised<\/jats:italic> machine learning called <jats:italic>positive-unlabeled (PU)<\/jats:italic> learning that uses a positive set with a large unlabeled set.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>In this study, we implement the first application of <jats:italic>PU-learning<\/jats:italic> to a protein function prediction problem: identification of peripheral domains. <jats:italic>PU-learning<\/jats:italic> starts by identifying reliable negative (<jats:italic>RN<\/jats:italic>) examples iteratively from the unlabeled set until convergence and builds a classifier using the positive and the final <jats:italic>RN<\/jats:italic> set. A data set of 232 positive cases and ~3750 unlabeled ones were used to construct and validate the protocol.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Holdout evaluation of the protocol on a left-out positive set showed that the accuracy of prediction reached up to 95% during two independent implementations.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>These results suggest that our protocol can be used for predicting membrane-binding properties of a wide variety of modular domains. Protocols like the one presented here become particularly useful in the case of availability of information from one class only.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/1471-2105-11-s1-s6","type":"journal-article","created":{"date-parts":[[2010,1,19]],"date-time":"2010-01-19T07:18:12Z","timestamp":1263885492000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Genome-wide sequence-based prediction of peripheral proteins using a novel semi-supervised learning technique"],"prefix":"10.1186","volume":"11","author":[{"given":"Nitin","family":"Bhardwaj","sequence":"first","affiliation":[]},{"given":"Mark","family":"Gerstein","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,1,18]]},"reference":[{"key":"3956_CR1","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop CM: Pattern Recognition and Machine Learning. Springer; 2006."},{"key":"3956_CR2","volume-title":"Proceedings of Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03): 2003; Acapulco, Mexico","author":"X Li","year":"2003","unstructured":"Li X, Liu B: Learning to classify text using positive and unlabeled data. Proceedings of Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-03): 2003; Acapulco, Mexico 2003."},{"key":"3956_CR3","volume-title":"The Third IEEE International Conference on Data Mining (ICDM-03): 2003; Melbourne, Florida","author":"B Liu","year":"2003","unstructured":"Liu B, Dai Y, Li X, Lee WS, Yu P: Building Text Classifiers Using Positive and Unlabeled Examples. The Third IEEE International Conference on Data Mining (ICDM-03): 2003; Melbourne, Florida 2003."},{"key":"3956_CR4","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1016\/j.bbalip.2006.02.020","volume":"1761","author":"JH Hurley","year":"2006","unstructured":"Hurley JH: Membrane binding domains. Biochimica et biophysica acta 2006, 1761: 805\u2013811.","journal-title":"Biochimica et biophysica acta"},{"key":"3956_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/3527606769.ch16","volume-title":"Structure and interactions of C2 domains at membrane surfaces","author":"DS Cafiso","year":"2005","unstructured":"Cafiso DS: Structure and interactions of C2 domains at membrane surfaces. John Wiley & Sons; 2005."},{"key":"3956_CR6","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S0092-8674(00)81780-8","volume":"95","author":"V Stambolic","year":"1998","unstructured":"Stambolic V, Suzuki A, de la Pompa JL, Brothers GM, Mirtsos C, Sasaki T, Ruland J, Penninger JM, Siderovski DP, Mak TW: Negative regulation of PKB\/Akt-dependent cell survival by the tumor suppressor PTEN. Cell 1998, 95: 29\u201339. 10.1016\/S0092-8674(00)81780-8","journal-title":"Cell"},{"issue":"7","key":"3956_CR7","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1038\/nrc839","volume":"2","author":"I Vivanco","year":"2002","unstructured":"Vivanco I, Sawyers CL: The phosphatidylinositol 3-Kinase AKT pathway in human cancer. Nat Rev Cancer 2002, 2(7):489\u2013501. 10.1038\/nrc839","journal-title":"Nat Rev Cancer"},{"issue":"30","key":"3956_CR8","doi-asserted-by":"publisher","first-page":"11364","DOI":"10.1073\/pnas.0602818103","volume":"103","author":"JS Saad","year":"2006","unstructured":"Saad JS, Miller J, Tai J, Kim A, Ghanam RH, Summers MF: Structural basis for targeting HIV-1 Gag proteins to the plasma membrane for virus assembly. Proc Natl Acad Sci USA 2006, 103(30):11364\u201311369. 10.1073\/pnas.0602818103","journal-title":"Proc Natl Acad Sci USA"},{"issue":"2","key":"3956_CR9","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1016\/j.jmb.2006.03.039","volume":"359","author":"N Bhardwaj","year":"2006","unstructured":"Bhardwaj N, Stahelin RV, Langlois RE, Cho W, Lu H: Structural bioinformatics prediction of membrane-binding proteins. Journal of molecular biology 2006, 359(2):486\u2013495. 10.1016\/j.jmb.2006.03.039","journal-title":"Journal of molecular biology"},{"issue":"6","key":"3956_CR10","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s10439-007-9312-z","volume":"35","author":"R Langlois","year":"2007","unstructured":"Langlois R, Carson M, Bhardwaj N, Lu H: Learning to Translate Sequence and Structure to Function: Identifying DNA Binding and Membrane Binding Proteins. Annals of Biomedical Engineering 2007, 35(6):1043\u20131052. 10.1007\/s10439-007-9312-z","journal-title":"Annals of Biomedical Engineering"},{"issue":"1","key":"3956_CR11","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1093\/nar\/gkg095","volume":"31","author":"B Boeckmann","year":"2003","unstructured":"Boeckmann B, Bairoch A, Apweiler R, Blatter MC, Estreicher A, Gasteiger E, Martin MJ, Michoud K, O'Donovan C, Phan I, et al.: The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003. Nucleic acids research 2003, 31(1):365\u2013370. 10.1093\/nar\/gkg095","journal-title":"Nucleic acids research"},{"issue":"13","key":"3956_CR12","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","volume":"22","author":"W Li","year":"2006","unstructured":"Li W, Godzik A: Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics (Oxford, England) 2006, 22(13):1658\u20131659. 10.1093\/bioinformatics\/btl158","journal-title":"Bioinformatics (Oxford, England)"},{"key":"3956_CR13","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1146\/annurev.biophys.33.110502.133337","volume":"34","author":"W Cho","year":"2005","unstructured":"Cho W, Stahelin RV: Membrane-protein interactions in cell signaling and membrane trafficking. Annual review of biophysics and biomolecular structure 2005, 34: 119\u2013151. 10.1146\/annurev.biophys.33.110502.133337","journal-title":"Annual review of biophysics and biomolecular structure"},{"issue":"21","key":"3956_CR14","doi-asserted-by":"publisher","first-page":"21833","DOI":"10.1074\/jbc.M313469200","volume":"279","author":"NM Okeley","year":"2004","unstructured":"Okeley NM, Gelb MH: A designed probe for acidic phospholipids reveals the unique enriched anionic character of the cytosolic face of the mammalian plasma membrane. J Biol Chem 2004, 279(21):21833\u201321840. 10.1074\/jbc.M313469200","journal-title":"J Biol Chem"},{"key":"3956_CR15","first-page":"81","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan JR: Induction of Decision Trees. Mach Learn 1986, 1: 81\u2013106.","journal-title":"Mach Learn"},{"key":"3956_CR16","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1613\/jair.279","volume":"4","author":"JR Quinlan","year":"1996","unstructured":"Quinlan JR: Improved use of continuous attributes in c4.5. J Artif Intell Res 1996, 4: 77\u201390.","journal-title":"J Artif Intell Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-11-S1-S6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T04:38:00Z","timestamp":1630471080000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-11-S1-S6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1]]},"references-count":16,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2010,1]]}},"alternative-id":["3956"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-11-s1-s6","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,1]]},"assertion":[{"value":"18 January 2010","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"S6"}}