{"corpus_id":2341929,"paper_sha":"0dab053c9ff1b41aead7d3b14cd219e322f8ee5b","doi":"10.1186/1745-7580-2-2","arxiv_id":null,"pmid":16635264,"pmcid":"1479323","mag_id":2160397907,"dblp_id":null,"acl_id":null,"title":"Improved method for predicting linear B-cell epitopes","year":2006,"publication_date":"2006-04-24","venue":"Immunome Research","journal":{"name":"Immunome Research","pages":"2 - 2","volume":"2"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article"],"s2_fields_of_study":["Biology","Medicine","Computer Science"],"reference_count":31,"citation_count":1264,"influential_citation_count":121,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"BackgroundB-cell epitopes are the sites of molecules that are recognized by antibodies of the immune system. Knowledge of B-cell epitopes may be used in the design of vaccines and diagnostics tests. It is therefore of interest to develop improved methods for predicting B-cell epitopes. In this paper, we describe an improved method for predicting linear B-cell epitopes.ResultsIn order to do this, three data sets of linear B-cell epitope annotated proteins were constructed. A data set was collected from the literature, another data set was extracted from the AntiJen database and a data sets of epitopes in the proteins of HIV was collected from the Los Alamos HIV database. An unbiased validation of the methods was made by testing on data sets on which they were neither trained nor optimized on. We have measured the performance in a non-parametric way by constructing ROC-curves.ConclusionThe best single method for predicting linear B-cell epitopes is the hidden Markov model. Combining the hidden Markov model with one of the best propensity scale methods, we obtained the BepiPred method. When tested on the validation data set this method performs significantly better than any of the other methods tested. The server and data sets are publicly available at http://www.cbs.dtu.dk/services/BepiPred.","claims":[{"public_id":"cl_09ddd6503d0891418a317efa1a21c6d2","status":"active","text":"The BepiPred method, combining a hidden Markov model with a propensity scale method, performs significantly better than any other method on the validation data set.","confidence":0.9,"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_09ddd6503d0891418a317efa1a21c6d2"},{"public_id":"cl_146ce150f1ac516dcc3a1f041f628e3b","status":"active","text":"The hidden Markov model is the best single method for predicting linear B-cell epitopes.","confidence":0.9,"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_146ce150f1ac516dcc3a1f041f628e3b"},{"public_id":"cl_d73c466b5c472e7196550cfab2713695","status":"active","text":"Three data sets of linear B-cell epitope annotated proteins were constructed: a literature data set, a data set from the AntiJen database, and an HIV epitope data set from the Los Alamos HIV database.","confidence":0.95,"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/claims/cl_d73c466b5c472e7196550cfab2713695"}],"concepts":[{"public_id":"co_0ed35bc450fc9b49e782c1ba9f38ffbd","status":"active","name":"propensity scale method","description":"A scale-based method used in combination with the hidden Markov model to form BepiPred.","types":["method"],"aliases":[],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_0ed35bc450fc9b49e782c1ba9f38ffbd"},{"public_id":"co_158e8d80be4d4905f65f33aa8fb19aa1","status":"active","name":"AntiJen database","description":"A database from which one of the three data sets of linear B-cell epitope annotated proteins was extracted.","types":["resource"],"aliases":["AntiJen"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_158e8d80be4d4905f65f33aa8fb19aa1"},{"public_id":"co_236200002fd9cfdfb45b05c894432bb6","status":"active","name":"validation data set","description":"The set of data used for unbiased testing of prediction methods, on which they were neither trained nor optimized.","types":["data set"],"aliases":["validation dataset"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_236200002fd9cfdfb45b05c894432bb6"},{"public_id":"co_345cfc08ead596b9bb85de957718daf9","status":"active","name":"linear B-cell epitope annotated proteins","description":"Proteins annotated with linear B-cell epitopes used to construct data sets.","types":["data set"],"aliases":[],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_345cfc08ead596b9bb85de957718daf9"},{"public_id":"co_44dc48f2c52dc1a8b213a11b28ab35b6","status":"active","name":"Los Alamos HIV database","description":"The database from which the HIV epitope data set was collected.","types":["resource"],"aliases":[],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_44dc48f2c52dc1a8b213a11b28ab35b6"},{"public_id":"co_4e431798bb90fd5713a58ca370b1fe5d","status":"active","name":"BepiPred method","description":"The combined method of a hidden Markov model and a propensity scale method for improved linear B-cell epitope prediction.","types":["method"],"aliases":["BepiPred"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_4e431798bb90fd5713a58ca370b1fe5d"},{"public_id":"co_755d9a83b8f1298538fb054a6c82e67d","status":"active","name":"linear B-cell epitopes","description":"The specific sites on molecules recognized by antibodies, targeted for prediction.","types":["biological entity"],"aliases":["linear B-cell epitope"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_755d9a83b8f1298538fb054a6c82e67d"},{"public_id":"co_89436b643f05d0b7aeb074ee2fd36aa9","status":"active","name":"literature data set","description":"A data set of linear B-cell epitope annotated proteins collected from published literature.","types":["data set"],"aliases":[],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_89436b643f05d0b7aeb074ee2fd36aa9"},{"public_id":"co_b6cae51c464e89bfbacc0c165c9c148f","status":"active","name":"HIV epitope data set","description":"A data set of epitopes in HIV proteins collected from the Los Alamos HIV database.","types":["data set"],"aliases":[],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_b6cae51c464e89bfbacc0c165c9c148f"},{"public_id":"co_f9b30b176cfac2a8f4b9c8d4ba781a37","status":"active","name":"hidden Markov model","description":"A statistical model used here as the best single method for linear B-cell epitope prediction.","types":["method"],"aliases":["HMM"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_f9b30b176cfac2a8f4b9c8d4ba781a37"},{"public_id":"co_fb0ebb71ebb4dac94c4a68f405000bae","status":"active","name":"ROC-curves","description":"Non-parametric performance measurement curves used to evaluate prediction methods.","types":["statistical method","evaluation technique"],"aliases":["ROC curve"],"contributors":[{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["extraction"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"}],"url":"https://sah.borca.ai/concepts/co_fb0ebb71ebb4dac94c4a68f405000bae"}],"external_ids":{"DOI":"10.1186/1745-7580-2-2","ArXiv":null,"PubMed":16635264,"PubMedCentral":"1479323","MAG":2160397907,"DBLP":null,"ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/2341929","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":631069,"paper_uid":"f4e374c6-f556-46c5-9006-8d8577b874d9","canonical_identity":{"paper_id":631069,"paper_uid":"f4e374c6-f556-46c5-9006-8d8577b874d9","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/2341929"}