{"id":"https://openalex.org/W2141262207","doi":"https://doi.org/10.1186/1471-2105-3-11","title":"Homology Induction: the use of machine learning to improve sequence similarity searches","display_name":"Homology Induction: the use of machine learning to improve sequence similarity searches","publication_year":2002,"publication_date":"2002-04-23","ids":{"openalex":"https://openalex.org/W2141262207","doi":"https://doi.org/10.1186/1471-2105-3-11","mag":"2141262207","pmid":"https://pubmed.ncbi.nlm.nih.gov/11972320"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-3-11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-3-11","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/1471-2105-3-11","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026210150","display_name":"Andreas Karwath","orcid":"https://orcid.org/0000-0002-6942-3760"},"institutions":[{"id":"https://openalex.org/I16038530","display_name":"Aberystwyth University","ror":"https://ror.org/015m2p889","country_code":"GB","type":"education","lineage":["https://openalex.org/I16038530"]},{"id":"https://openalex.org/I97429440","display_name":"University of Wales","ror":"https://ror.org/01se4f844","country_code":"GB","type":"education","lineage":["https://openalex.org/I97429440"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreas Karwath","raw_affiliation_strings":["Department of Computer Sciences, University of Wales, Aberystwyth, SY23 3DB, UK. adk@aber.ac.uk","Department of Computer Sciences University of Wales Aberystwyth UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Wales, Aberystwyth, SY23 3DB, UK. adk@aber.ac.uk","institution_ids":["https://openalex.org/I16038530","https://openalex.org/I97429440"]},{"raw_affiliation_string":"Department of Computer Sciences University of Wales Aberystwyth UK","institution_ids":["https://openalex.org/I16038530","https://openalex.org/I97429440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020822487","display_name":"Ross D. King","orcid":"https://orcid.org/0000-0001-7208-4387"},"institutions":[{"id":"https://openalex.org/I16038530","display_name":"Aberystwyth University","ror":"https://ror.org/015m2p889","country_code":"GB","type":"education","lineage":["https://openalex.org/I16038530"]},{"id":"https://openalex.org/I97429440","display_name":"University of Wales","ror":"https://ror.org/01se4f844","country_code":"GB","type":"education","lineage":["https://openalex.org/I97429440"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ross D King","raw_affiliation_strings":["Department of Computer Sciences, University of Wales, Aberystwyth, SY23 3DB, UK","Department of Computer Sciences University of Wales Aberystwyth UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Wales, Aberystwyth, SY23 3DB, UK","institution_ids":["https://openalex.org/I16038530"]},{"raw_affiliation_string":"Department of Computer Sciences University of Wales Aberystwyth UK","institution_ids":["https://openalex.org/I16038530","https://openalex.org/I97429440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020822487"],"corresponding_institution_ids":["https://openalex.org/I16038530","https://openalex.org/I97429440"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9161,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.73574606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"1","first_page":"11","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6304000020027161,"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":0.6304000020027161,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.08969999849796295,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.05260000005364418,"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/inference","display_name":"Inference","score":0.5649514198303223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5636296272277832},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.5603489875793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157166123390198},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5104893445968628},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5065892934799194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41531795263290405},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4028756618499756},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3506678342819214},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.32496342062950134},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.25641393661499023},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.2158297300338745},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11681464314460754}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5649514198303223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5636296272277832},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5603489875793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157166123390198},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5104893445968628},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5065892934799194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41531795263290405},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4028756618499756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3506678342819214},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.32496342062950134},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25641393661499023},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.2158297300338745},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11681464314460754},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005656","descriptor_name":"Fungal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005656","descriptor_name":"Fungal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005656","descriptor_name":"Fungal Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010940","descriptor_name":"Plant Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010940","descriptor_name":"Plant Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010940","descriptor_name":"Plant Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012191","descriptor_name":"Retroviridae Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012191","descriptor_name":"Retroviridae Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012191","descriptor_name":"Retroviridae Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012275","descriptor_name":"Oryza","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012275","descriptor_name":"Oryza","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012275","descriptor_name":"Oryza","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":9,"locations":[{"id":"doi:10.1186/1471-2105-3-11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-3-11","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:11972320","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11972320","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:107726","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/1471-2105-3-11","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-3-11","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:publications/1b580ff3-5292-4d3f-a250-44be186a739e","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/1b580ff3-5292-4d3f-a250-44be186a739e","pdf_url":"https://link.springer.com/content/pdf/10.1186/1471-2105-3-11.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Karwath, A & King, R D 2002, 'Homology induction: The use of machine learning to improve sequence similarity searches', BMC Bioinformatics, vol. 3, 11. https://doi.org/10.1186/1471-2105-3-11","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:aber.ac.uk:Publications/c2c1c7b4-7aac-4144-99ab-bc79b0910e76","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401660","display_name":"Aberystwyth Research portal (Aberystwyth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16038530","host_organization_name":"Aberystwyth University","host_organization_lineage":["https://openalex.org/I16038530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:aber.ac.uk:openaire_cris_publications/c2c1c7b4-7aac-4144-99ab-bc79b0910e76","is_oa":false,"landing_page_url":"http://hdl.handle.net/2160/258","pdf_url":null,"source":{"id":"https://openalex.org/S4306401660","display_name":"Aberystwyth Research portal (Aberystwyth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16038530","host_organization_name":"Aberystwyth University","host_organization_lineage":["https://openalex.org/I16038530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:doaj.org/article:fe3b7784cd14405ba973351c80d8dec6","is_oa":false,"landing_page_url":"https://doaj.org/article/fe3b7784cd14405ba973351c80d8dec6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 3, Iss 1, p 11 (2002)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:1782389","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/107726","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/9fa7603b-a998-4529-ba42-7588f0c3a842","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/9fa7603b-a998-4529-ba42-7588f0c3a842","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Karwath, A & King, R D 2002, 'Homology Induction: the use of machine learning to improve sequence similarity searches', BMC Bioinformatics, vol. 3, no. 1. https://doi.org/10.1186/1471-2105-3-11","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-3-11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-3-11","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6200000047683716,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W648774283","https://openalex.org/W1483118642","https://openalex.org/W1496929357","https://openalex.org/W1500551892","https://openalex.org/W1509562192","https://openalex.org/W1528627603","https://openalex.org/W1536719366","https://openalex.org/W1568011753","https://openalex.org/W1606045260","https://openalex.org/W1969051510","https://openalex.org/W1970818396","https://openalex.org/W1988237769","https://openalex.org/W1988790447","https://openalex.org/W1988916638","https://openalex.org/W1990748933","https://openalex.org/W2000218938","https://openalex.org/W2000488027","https://openalex.org/W2000758249","https://openalex.org/W2003144438","https://openalex.org/W2003361463","https://openalex.org/W2013570924","https://openalex.org/W2015292449","https://openalex.org/W2055043387","https://openalex.org/W2056619794","https://openalex.org/W2058336694","https://openalex.org/W2074231493","https://openalex.org/W2080336769","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2097555181","https://openalex.org/W2099254366","https://openalex.org/W2102122585","https://openalex.org/W2103210188","https://openalex.org/W2106397972","https://openalex.org/W2117019496","https://openalex.org/W2117030594","https://openalex.org/W2119831128","https://openalex.org/W2122369731","https://openalex.org/W2124158580","https://openalex.org/W2132984323","https://openalex.org/W2134517171","https://openalex.org/W2145454254","https://openalex.org/W2155042162","https://openalex.org/W2155653793","https://openalex.org/W2156630822","https://openalex.org/W2157046483","https://openalex.org/W2157975034","https://openalex.org/W2158292827","https://openalex.org/W2158714788","https://openalex.org/W2162061564","https://openalex.org/W2162621793","https://openalex.org/W2170913656","https://openalex.org/W2171091522","https://openalex.org/W2178996695","https://openalex.org/W2394515930","https://openalex.org/W2503212997","https://openalex.org/W2522853541","https://openalex.org/W2912934387","https://openalex.org/W2916193864","https://openalex.org/W3150945973","https://openalex.org/W4212848460","https://openalex.org/W4213149192","https://openalex.org/W4256395558"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2012019886","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2166090428"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,14,175],"inference":[2],"of":[3,22,71,120,135,193,206],"homology":[4,137,177],"between":[5],"proteins":[6],"is":[7,60,199,216,226],"a":[8,25,38,57,106,111,200],"key":[9],"problem":[10],"in":[11,93,105],"molecular":[12],"biology":[13],"current":[15],"best":[16],"approaches":[17],"only":[18],"identify":[19],"approximately":[20],"50%":[21],"homologies":[23],"(with":[24],"false":[26],"positive":[27],"rate":[28],"set":[29],"at":[30],"1/1000).":[31],"RESULTS:":[32],"We":[33,142],"present":[34],"Homology":[35],"Induction":[36],"(HI),":[37],"new":[39,201],"approach":[40],"to":[41,48,74,90,187,218],"inferring":[42],"homology.":[43],"HI":[44,63,101,126,145,152,181,198,213,235],"uses":[45],"machine":[46,117],"learning":[47,118],"bootstrap":[49],"from":[50],"standard":[51,58],"sequence":[52,140,238],"similarity":[53,73,239],"search":[54],"methods.":[55],"First":[56],"method":[59,119],"run,":[61],"then":[62,88],"learns":[64],"rules":[65,86,100,178],"which":[66,132],"are":[67,87],"true":[68,81],"for":[69,82,170,203,221],"sequences":[70,92,104,134],"high":[72],"the":[75,94,99,103,116,129,144,204],"target":[76],"(assumed":[77],"homologues)":[78],"and":[79,115,150],"not":[80],"general":[83],"sequences,":[84],"these":[85,166],"used":[89,128],"discriminate":[91],"twilight":[95],"zone.":[96],"To":[97,124],"learn":[98],"describes":[102],"novel":[107],"way":[108],"based":[109],"on":[110],"bioinformatic":[112,211],"knowledge":[113],"base,":[114],"inductive":[121],"logic":[122],"programming.":[123],"evaluate":[125],"we":[127],"PDB40D":[130],"benchmark":[131],"lists":[133],"known":[136],"but":[138],"low":[139],"similarity.":[141],"compared":[143],"methodology":[146],"with":[147,214,236],"PSI-BLAST":[148,215,220],"alone":[149],"found":[151],"performed":[153],"significantly":[154],"better.":[155],"In":[156],"addition,":[157],"Receiver":[158],"Operating":[159],"Characteristic":[160],"(ROC)":[161],"curve":[162],"analysis":[163],"showed":[164],"that":[165,228],"improvements":[167,230],"were":[168],"robust":[169],"all":[171,222],"reasonable":[172],"error":[173,223],"costs.":[174,224],"predictive":[176],"learnt":[179],"by":[180,182],"can":[183],"be":[184,232],"interpreted":[185],"biologically":[186],"provide":[188],"insight":[189],"into":[190],"conserved":[191],"features":[192],"homologous":[194],"protein":[195,208],"families.":[196],"CONCLUSIONS:":[197],"technique":[202],"detection":[205],"remote":[207],"homology--a":[209],"central":[210],"problem.":[212],"shown":[217],"outperform":[219],"It":[225],"expect":[227],"similar":[229],"would":[231],"obtained":[233],"using":[234],"any":[237],"method.":[240]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
