{"id":"https://openalex.org/W4255995321","doi":"https://doi.org/10.1109/csb.2004.1332488","title":"Positive sample only learning (PSOL) for predicting RNA genes in E. coli","display_name":"Positive sample only learning (PSOL) for predicting RNA genes in E. coli","publication_year":2004,"publication_date":"2004-11-08","ids":{"openalex":"https://openalex.org/W4255995321","doi":"https://doi.org/10.1109/csb.2004.1332488"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2004.1332488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2004.1332488","pdf_url":null,"source":{"id":"https://openalex.org/S4363608884","display_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059500389","display_name":"R.F. Meraz","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.F. Meraz","raw_affiliation_strings":["Physical Biosciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Physical Biosciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104093437","display_name":"Xiaofeng He","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng He","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034684873","display_name":"Chuntao Ding","orcid":"https://orcid.org/0009-0001-4897-8716"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.H.Q. Ding","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078623036","display_name":"S.R. Holbrook","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.R. Holbrook","raw_affiliation_strings":["Physical Biosciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Physical Biosciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"513","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9409000277519226,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9380000233650208,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.7171250581741333},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.6714139580726624},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5885263681411743},{"id":"https://openalex.org/keywords/intergenic-region","display_name":"Intergenic region","score":0.5750385522842407},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5378105044364929},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.49555933475494385},{"id":"https://openalex.org/keywords/non-coding-rna","display_name":"Non-coding RNA","score":0.4612070918083191},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.45358920097351074},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4133053421974182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.26280486583709717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2086905837059021}],"concepts":[{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.7171250581741333},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.6714139580726624},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5885263681411743},{"id":"https://openalex.org/C195139083","wikidata":"https://www.wikidata.org/wiki/Q3463539","display_name":"Intergenic region","level":4,"score":0.5750385522842407},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5378105044364929},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.49555933475494385},{"id":"https://openalex.org/C194993378","wikidata":"https://www.wikidata.org/wiki/Q427087","display_name":"Non-coding RNA","level":4,"score":0.4612070918083191},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.45358920097351074},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4133053421974182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26280486583709717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2086905837059021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2004.1332488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2004.1332488","pdf_url":null,"source":{"id":"https://openalex.org/S4363608884","display_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1822105579","https://openalex.org/W1950410402","https://openalex.org/W2008455848","https://openalex.org/W2051115739","https://openalex.org/W2063742961","https://openalex.org/W2117431427","https://openalex.org/W2121678363","https://openalex.org/W2146831994","https://openalex.org/W2148603752","https://openalex.org/W2149941588","https://openalex.org/W2155258523","https://openalex.org/W2158381555"],"related_works":["https://openalex.org/W2571285940","https://openalex.org/W2108267719","https://openalex.org/W2952365809","https://openalex.org/W2163001863","https://openalex.org/W1989930315","https://openalex.org/W4205782745","https://openalex.org/W4307343984","https://openalex.org/W2058984380","https://openalex.org/W1988125422","https://openalex.org/W2900182103"],"abstract_inverted_index":{"RNA":[0,22,88,96],"genes":[1,24,89],"lack":[2],"most":[3,72],"of":[4,15,35,107],"the":[5,60,71,100,108],"signals":[6],"used":[7],"for":[8],"protein":[9],"gene":[10,97],"identification.":[11],"A":[12],"major":[13],"shortcoming":[14],"previous":[16,104],"discriminative":[17],"methods":[18],"to":[19,84],"distinguish":[20,85],"functional":[21,87],"(fRNA)":[23],"from":[25,76,90],"other":[26,91],"non-coding":[27,92],"genomic":[28],"sequences":[29,47],"is":[30,81],"that":[31,48],"only":[32,45,63],"positive":[33,51],"examples":[34,75],"fRNAs":[36],"are":[37,40],"known;":[38],"there":[39],"no":[41],"confirmed":[42],"negatives":[43],"-":[44],"intergenic":[46],"may":[49],"be":[50],"or":[52],"negative.":[53],"To":[54],"address":[55],"this":[56],"problem":[57],"we":[58],"developed":[59],"\"positive":[61],"sample":[62],"learning\"":[64],"(PSOL)":[65],"method.":[66],"This":[67],"method":[68,102],"can":[69],"identify":[70],"likely":[73],"negative":[74],"an":[77],"unlabeled":[78],"set":[79],"and":[80],"therefore":[82],"able":[83],"putative":[86],"sequence.":[93],"We":[94],"compare":[95],"predictions":[98],"using":[99],"PSOL":[101],"with":[103],"large-scale":[105],"analyses":[106],"E.":[109],"coli":[110],"K12":[111],"genome.":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
