{"id":"https://openalex.org/W2140244239","doi":"https://doi.org/10.1093/bioinformatics/14.10.846","title":"Hidden Markov models for detecting remote protein homologies.","display_name":"Hidden Markov models for detecting remote protein homologies.","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2140244239","doi":"https://doi.org/10.1093/bioinformatics/14.10.846","mag":"2140244239","pmid":"https://pubmed.ncbi.nlm.nih.gov/9927713"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/14.10.846","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/14.10.846","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/14/10/846/48834782/bioinformatics_14_10_846.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/14/10/846/48834782/bioinformatics_14_10_846.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059033237","display_name":"Kevin Karplus","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K Karplus","raw_affiliation_strings":["Department of Computer Engineering, Jack Baskin School of Engineering, University of California, Santa Cruz, CA 95064, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Jack Baskin School of Engineering, University of California, Santa Cruz, CA 95064, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050252906","display_name":"Curtis L. Barrett","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C Barrett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047915561","display_name":"Richard Hughey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Hughey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059033237"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":13.0229,"has_fulltext":false,"cited_by_count":1111,"citation_normalized_percentile":{"value":0.9926092,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"14","issue":"10","first_page":"846","last_page":"856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.5713000297546387,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.5713000297546387,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.28619998693466187,"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":0.01940000057220459,"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/computer-science","display_name":"Computer science","score":0.6161670088768005},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.600548505783081},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5241991281509399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37106743454933167},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3703639507293701},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2427385151386261},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21708667278289795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161670088768005},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.600548505783081},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5241991281509399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37106743454933167},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3703639507293701},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2427385151386261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21708667278289795}],"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":"D005069","descriptor_name":"Evaluation Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005069","descriptor_name":"Evaluation Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005069","descriptor_name":"Evaluation Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/14.10.846","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/14.10.846","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/14/10/846/48834782/bioinformatics_14_10_846.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:9927713","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9927713","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.5575","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.5575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.ucsc.edu/~karplus/papers/sam-t98-bioinformatics.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.1859","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.1859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.kuicr.kyoto-u.ac.jp/~vert/bibli/karp98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.2762","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.2762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ucsc.edu/research/compbio/papers/w9824.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.5023","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.5023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ucsc.edu/research/compbio/papers/remotehomology.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/14.10.846","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/14.10.846","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/14/10/846/48834782/bioinformatics_14_10_846.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2140244239.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3145575561"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1,222],"new":[2,200],"hidden":[3,31],"Markov":[4,32],"model":[5,33,53,213],"method":[6,20,66,94,104,169,197],"(SAM-T98)":[7],"for":[8,44,124],"finding":[9],"remote":[10],"homologs":[11,39],"of":[12,71,112,137,194],"protein":[13],"sequences":[14,57],"is":[15,48,95,170,198],"described":[16],"and":[17,27,38,99,145,158,175,236],"evaluated.":[18],"The":[19,87,93,168],"begins":[21],"with":[22,67,154,164,210],"a":[23,30,90,102,199,211,217],"single":[24],"target":[25],"sequence":[26,37],"iteratively":[28],"builds":[29],"(HMM)":[34],"from":[35,56],"the":[36,42,64,72,79,117,125,129,133,192,195,205,208,233],"found":[40,243],"using":[41,109],"HMM":[43,196],"database":[45],"search.":[46],"SAM-T98":[47,65,115,140],"also":[49],"used":[50,182],"to":[51,106,172,180,183,191,207,216],"construct":[52],"libraries":[54],"automatically":[55],"in":[58,120],"structural":[59,85],"databases.":[60],"METHODS:":[61],"We":[62],"evaluate":[63],"four":[68],"datasets.":[69],"Three":[70],"test":[73],"sets":[74],"are":[75,82],"fold-recognition":[76,126],"tests,":[77],"where":[78],"correct":[80],"answers":[81],"determined":[83],"by":[84],"similarity.":[86],"fourth":[88],"uses":[89],"curated":[91],"database.":[92],"compared":[96],"against":[97,100],"WU-BLASTP":[98,159],"DOUBLE-BLAST,":[101],"two-step":[103],"similar":[105],"ISS,":[107],"but":[108],"BLAST":[110],"instead":[111],"FASTA.":[113],"RESULTS:":[114],"had":[116],"fewest":[118],"errors":[119],"all":[121],"tests-dramatically":[122],"so":[123],"tests.":[127],"At":[128],"minimum-error":[130],"point":[131],"on":[132,231],"SCOP":[134],"(Structural":[135],"Classification":[136],"Proteins)-domains":[138],"test,":[139],"got":[141,150,160],"880":[142],"true":[143,152,162],"positives":[144,153,163],"68":[146],"false":[147,156,166],"positives,":[148,157],"DOUBLE-BLAST":[149],"533":[151],"71":[155],"353":[161],"24":[165],"positives.":[167],"optimized":[171],"recognize":[173],"superfamilies,":[174],"would":[176],"require":[177],"parameter":[178],"adjustment":[179],"be":[181,242],"find":[184],"family":[185],"or":[186],"fold":[187],"relationships.":[188],"One":[189],"key":[190],"performance":[193],"score-normalization":[201],"technique":[202],"that":[203],"compares":[204],"score":[206,209],"reversed":[212],"rather":[214],"than":[215],"uniform":[218],"null":[219],"model.":[220],"AVAILABILITY:":[221],"World":[223],"Wide":[224],"Web":[225],"server,":[226],"as":[227,229],"well":[228],"information":[230],"obtaining":[232],"Sequence":[234],"Alignment":[235],"Modeling":[237],"(SAM)":[238],"software":[239],"suite,":[240],"can":[241],"at":[244],"http://www.cse.ucsc.edu/research/compbi":[245],"o/":[246],"CONTACT:":[247],"karplus@cse.ucsc.edu;":[248],"http://www.cse.ucsc.edu/karplus":[249]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":32},{"year":2012,"cited_by_count":32}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
