{"id":"https://openalex.org/W2029167127","doi":"https://doi.org/10.1145/1458082.1458186","title":"Identification of gene function using prediction by partial matching (PPM) language models","display_name":"Identification of gene function using prediction by partial matching (PPM) language models","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2029167127","doi":"https://doi.org/10.1145/1458082.1458186","mag":"2029167127"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","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/A5062980935","display_name":"Malika Mahoui","orcid":"https://orcid.org/0000-0002-2025-0205"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Malika Mahoui","raw_affiliation_strings":["IUPUI, Indianapolis, IN, USA"],"affiliations":[{"raw_affiliation_string":"IUPUI, Indianapolis, IN, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025875274","display_name":"William J. Teahan","orcid":"https://orcid.org/0000-0003-3640-6750"},"institutions":[{"id":"https://openalex.org/I161548249","display_name":"Bangor University","ror":"https://ror.org/006jb1a24","country_code":"GB","type":"education","lineage":["https://openalex.org/I161548249"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William John Teahan","raw_affiliation_strings":["University of Wales, Bangor, Wales, United Kngdm","University of Wales, Bangor, Wales, United Kngdm#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Wales, Bangor, Wales, United Kngdm","institution_ids":["https://openalex.org/I161548249"]},{"raw_affiliation_string":"University of Wales, Bangor, Wales, United Kngdm#TAB#","institution_ids":["https://openalex.org/I161548249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004145054","display_name":"Arvind Kumar Thirumalaiswamy Sekhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arvind Kumar Thirumalaiswamy Sekhar","raw_affiliation_strings":["Dow AgroSciences, Indianapolis, IN, USA","Dow AgroSciences, Indianapolis, IN, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Dow AgroSciences, Indianapolis, IN, USA","institution_ids":[]},{"raw_affiliation_string":"Dow AgroSciences, Indianapolis, IN, USA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016883216","display_name":"Satyasaibabu Chilukuri","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satyasaibabu Chilukuri","raw_affiliation_strings":["IUPUI, Indianapolis, IN, USA"],"affiliations":[{"raw_affiliation_string":"IUPUI, Indianapolis, IN, USA","institution_ids":["https://openalex.org/I55769427"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062980935"],"corresponding_institution_ids":["https://openalex.org/I55769427"],"apc_list":null,"apc_paid":null,"fwci":0.1347,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.53308299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"786"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619308829307556},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6880802512168884},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6734914183616638},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.617611289024353},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.598148763179779},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5440475344657898},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47733360528945923},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46132010221481323},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.458871990442276},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44903939962387085},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.4321005940437317},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4275493621826172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38295960426330566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33865636587142944},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.297267884016037},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.16762453317642212},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12008213996887207},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11688897013664246},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10816740989685059},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08198067545890808},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08151444792747498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619308829307556},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6880802512168884},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6734914183616638},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.617611289024353},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.598148763179779},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5440475344657898},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47733360528945923},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46132010221481323},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.458871990442276},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44903939962387085},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.4321005940437317},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4275493621826172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38295960426330566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33865636587142944},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.297267884016037},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.16762453317642212},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12008213996887207},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11688897013664246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10816740989685059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08198067545890808},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08151444792747498},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W87844232","https://openalex.org/W1483118642","https://openalex.org/W1490796714","https://openalex.org/W1505057072","https://openalex.org/W1508514598","https://openalex.org/W1571468614","https://openalex.org/W1944963667","https://openalex.org/W1987947967","https://openalex.org/W1991133427","https://openalex.org/W1993657037","https://openalex.org/W1995875735","https://openalex.org/W2009341227","https://openalex.org/W2028455782","https://openalex.org/W2070127972","https://openalex.org/W2099737682","https://openalex.org/W2103907281","https://openalex.org/W2106093878","https://openalex.org/W2109070394","https://openalex.org/W2117243442","https://openalex.org/W2122305935","https://openalex.org/W2135771747","https://openalex.org/W2161628678","https://openalex.org/W2167289895","https://openalex.org/W2441154163","https://openalex.org/W2611071497","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W623261610","https://openalex.org/W2129888767","https://openalex.org/W4365815255","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W2387801216"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,96],"describe":[4,91],"the":[5,38,55,62,71,81,84,92,99,107,114],"utilization":[6],"of":[7,23,37,46,57,83,101,113],"text":[8],"encoding":[9],"and":[10,80,136,138],"prediction":[11],"by":[12],"partial":[13],"matching":[14],"language":[15],"modeling":[16],"to":[17,53,65,69,75,105,123],"identify":[18,124],"gene":[19,78,87,110,125],"functions":[20,79,104,126],"within":[21],"abstracts":[22,47,129],"biomedical":[24],"papers.":[25],"The":[26,116],"National":[27],"Center":[28],"for":[29,43,143],"Biotechnology":[30],"Information":[31],"has":[32],"\"GeneRIF\"":[33],"-":[34],"a":[35,44],"collection":[36],"best":[39],"possible":[40],"functional":[41],"representations":[42],"subset":[45],"from":[48],"PubMed.":[49],"We":[50,60,89],"use":[51,144],"GeneRIF":[52],"test":[54],"efficiency":[56],"our":[58,120],"technique.":[59],"discuss":[61],"methodology":[63],"adopted":[64],"construct":[66],"models":[67],"necessary":[68],"enable":[70],"Text":[72],"Mining":[73],"Toolkit":[74],"distinguish":[76],"between":[77],"rest":[82],"abstract":[85],"(non":[86],"functions).":[88],"also":[90],"similarity":[93],"based":[94],"approach":[95,122],"deploy":[97],"on":[98,133],"list":[100],"automatically":[102],"annotated":[103],"generate":[106],"most":[108],"likely":[109],"function":[111],"representative":[112],"paper.":[115],"results":[117],"indicate":[118],"that":[119],"combined":[121],"in":[127,145,150],"scientific":[128,151],"performs":[130],"very":[131],"well":[132],"both":[134],"precision":[135],"recall,":[137],"therefore":[139],"presents":[140],"exciting":[141],"opportunities":[142],"extracting":[146],"other":[147],"entities":[148],"embedded":[149],"text.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}