{"id":"https://openalex.org/W2145262276","doi":"https://doi.org/10.1145/1851476.1851548","title":"Modeling sequence and function similarity between proteins for protein functional annotation","display_name":"Modeling sequence and function similarity between proteins for protein functional annotation","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W2145262276","doi":"https://doi.org/10.1145/1851476.1851548","mag":"2145262276"},"language":"en","primary_location":{"id":"doi:10.1145/1851476.1851548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4120521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108222756","display_name":"Roger Higdon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roger Higdon","raw_affiliation_strings":["Seattle Children's Research Institute, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Seattle Children's Research Institute, Seattle, WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006349820","display_name":"Brenton Louie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brenton Louie","raw_affiliation_strings":["Seattle Children's Research Institute, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Seattle Children's Research Institute, Seattle, WA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087861388","display_name":"Eugene Kolker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Kolker","raw_affiliation_strings":["Seattle Children's Research Institute, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Seattle Children's Research Institute, Seattle, WA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108222756"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2703,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.60171374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2010","issue":null,"first_page":"499","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9976999759674072,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9976999759674072,"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":0.9975000023841858,"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":0.9970999956130981,"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/similarity","display_name":"Similarity (geometry)","score":0.6695325970649719},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.6460753679275513},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5982734560966492},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5818521976470947},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.5166926383972168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4556898772716522},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.43909522891044617},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.43737921118736267},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4204229712486267},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3348264694213867},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3300522565841675},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.31762754917144775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3158227205276489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31044936180114746},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28888165950775146},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.25850510597229004},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21458178758621216},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08050939440727234}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6695325970649719},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.6460753679275513},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5982734560966492},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5818521976470947},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.5166926383972168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4556898772716522},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.43909522891044617},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.43737921118736267},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4204229712486267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3348264694213867},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3300522565841675},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.31762754917144775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3158227205276489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31044936180114746},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28888165950775146},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.25850510597229004},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21458178758621216},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08050939440727234},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1851476.1851548","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-article"},{"id":"mag:25101328","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International Symposium on High Performance Distributed Computing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4120521","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4120521","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int Symp High Perform Distrib Comput","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4120521","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4120521","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int Symp High Perform Distrib Comput","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1109423982","display_name":null,"funder_award_id":"5R01 GM076680-02UO1 DK072473","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G609504397","display_name":null,"funder_award_id":"DBI-0544757NSF-07140","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8267318235","display_name":null,"funder_award_id":"DBI-0544757NSF-07140","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W290667870","https://openalex.org/W1647729745","https://openalex.org/W1783219955","https://openalex.org/W1980948656","https://openalex.org/W1993267991","https://openalex.org/W2002458103","https://openalex.org/W2003647795","https://openalex.org/W2011025549","https://openalex.org/W2050160299","https://openalex.org/W2076735582","https://openalex.org/W2099946731","https://openalex.org/W2101220662","https://openalex.org/W2103017472","https://openalex.org/W2107580398","https://openalex.org/W2121481633","https://openalex.org/W2123858481","https://openalex.org/W2124410686","https://openalex.org/W2127563440","https://openalex.org/W2131399825","https://openalex.org/W2141411672","https://openalex.org/W2151831732","https://openalex.org/W2158714788","https://openalex.org/W2167244132","https://openalex.org/W4239967865"],"related_works":["https://openalex.org/W2159663778","https://openalex.org/W2065993463","https://openalex.org/W2181899571","https://openalex.org/W2135470984","https://openalex.org/W2082535576","https://openalex.org/W1568877569","https://openalex.org/W2015809665","https://openalex.org/W2935275081","https://openalex.org/W2111105050","https://openalex.org/W2348674368"],"abstract_inverted_index":{"A":[0,33],"common":[1,214],"task":[2,245],"in":[3,67,164,199,215],"biological":[4],"research":[5],"is":[6,23,38,59,81,213],"to":[7,116,124,174],"predict":[8],"function":[9,53,79,120,143,177,233],"for":[10,88,100,112,134,161,222,237,242],"proteins":[11,16,69,123,133],"by":[12],"comparing":[13],"sequences":[14,191,206],"between":[15,45,55,76,122,132],"of":[17,41,65,155,225,230],"known":[18],"and":[19,51,78,119,234,250],"unknown":[20],"function.":[21,136],"This":[22,57,157],"often":[24],"done":[25],"using":[26],"pair-wise":[27,162],"sequence":[28,48,77,118,148,168,210,239],"alignment":[29],"algorithms":[30,202,241],"(e.g.":[31],"BLAST).":[32],"problem":[34,198],"with":[35,147,151,207],"this":[36,113,244],"approach":[37],"the":[39,52,62,128,228,235],"assumption":[40,58],"a":[42,46,152,186,197],"simple":[43],"equivalence":[44],"minimum":[47],"similarity":[49,54,121,130,144,149,169],"threshold":[50],"proteins.":[56],"based":[60,103],"on":[61,104],"binary":[63],"concept":[64],"homology":[66],"that":[68,142,165,200],"are":[70,185,196,220],"or":[71,96,219],"not":[72],"homologous.":[73],"The":[74],"relationship":[75,131],"however":[80],"more":[82],"complex":[83],"as":[84,86],"well":[85],"pertinent":[87],"predicting":[89,135,231],"protein":[90,232],"function,":[91],"e.g.":[92],"evaluating":[93],"BLAST":[94],"alignments":[95,192],"developing":[97],"training":[98],"sets":[99],"profile":[101],"models":[102,180],"functional":[105],"rather":[106],"than":[107],"homologous":[108],"groupings.":[109],"Our":[110],"motivation":[111],"study":[114],"was":[115],"model":[117,139],"gain":[125],"insights":[126],"into":[127],"\"sequence-function":[129],"Using":[137],"our":[138,216],"we":[140],"found":[141],"generally":[145],"increases":[146],"but":[150],"high":[153,173,176,223],"degree":[154],"variability.":[156],"result":[158],"has":[159],"implications":[160],"approaches":[163],"it":[166],"appears":[167],"must":[170],"be":[171,247],"very":[172,208],"ensure":[175],"similarity.":[178],"Profile":[179],"which":[181,212],"enable":[182],"higher":[183],"sensitivity":[184],"potential":[187],"solution.":[188],"However,":[189],"multiple":[190,238],"(a":[193],"necessary":[194],"prerequisite)":[195],"current":[201],"have":[203],"difficulty":[204],"aligning":[205],"low":[209],"similarity,":[211],"data":[217],"set,":[218],"intractable":[221],"numbers":[224],"sequences.":[226],"Given":[227],"importance":[229],"need":[236],"alignments,":[240],"accomplishing":[243],"should":[246],"further":[248],"refined":[249],"developed.":[251]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}