{"id":"https://openalex.org/W2096556032","doi":"https://doi.org/10.1145/299432.299445","title":"Modeling protein families using probabilistic suffix trees","display_name":"Modeling protein families using probabilistic suffix trees","publication_year":1999,"publication_date":"1999-04-01","ids":{"openalex":"https://openalex.org/W2096556032","doi":"https://doi.org/10.1145/299432.299445","mag":"2096556032"},"language":"en","primary_location":{"id":"doi:10.1145/299432.299445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/299432.299445","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/299432.299445","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third annual international conference on Computational molecular biology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/299432.299445","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085525898","display_name":"Gill Bejerano","orcid":"https://orcid.org/0000-0001-5179-3635"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gill Bejerano","raw_affiliation_strings":["Institute of Computer Science, Hebrew University, Jerusalem 91904, Israel","Institute of Computer Science,#N# Hebrew University,#N# Jerusalem 91904, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Hebrew University, Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Institute of Computer Science,#N# Hebrew University,#N# Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001926130","display_name":"Golan Yona","orcid":null},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Golan Yona","raw_affiliation_strings":["Institute of Computer Science, Hebrew University, Jerusalem 91904, Israel","Institute of Computer Science,#N# Hebrew University,#N# Jerusalem 91904, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Hebrew University, Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"Institute of Computer Science,#N# Hebrew University,#N# Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197251160"],"apc_list":null,"apc_paid":null,"fwci":3.3416,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.92866797,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9973999857902527,"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":0.9927999973297119,"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/hebrew","display_name":"Hebrew","score":0.9536641240119934},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.745577871799469},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.7392348051071167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5871344208717346},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4969485104084015},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.35532867908477783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21990367770195007},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.21145689487457275},{"id":"https://openalex.org/keywords/classics","display_name":"Classics","score":0.15779006481170654},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12694358825683594}],"concepts":[{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.9536641240119934},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.745577871799469},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.7392348051071167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5871344208717346},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4969485104084015},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.35532867908477783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21990367770195007},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.21145689487457275},{"id":"https://openalex.org/C74916050","wikidata":"https://www.wikidata.org/wiki/Q841090","display_name":"Classics","level":1,"score":0.15779006481170654},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12694358825683594},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/299432.299445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/299432.299445","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/299432.299445","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third annual international conference on Computational molecular biology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.2389","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.2389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.huji.ac.il/~jill/Papers/recomb99.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.731","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cbio.ensmp.fr/~jvert/svn/bibli/local/Bejerano1999Modeling.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.45.9235","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.45.9235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.protomap.cs.huji.ac.il/~golany/Papers/recomb99.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.6777","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.6777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.huji.ac.il/labs/learning/Papers/recomb99.ps.gz","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/299432.299445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/299432.299445","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/299432.299445","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third annual international conference on Computational molecular biology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2096556032.pdf","grobid_xml":"https://content.openalex.org/works/W2096556032.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1502621331","https://openalex.org/W1969051510","https://openalex.org/W1982496832","https://openalex.org/W1994920552","https://openalex.org/W2001331793","https://openalex.org/W2014544984","https://openalex.org/W2032991899","https://openalex.org/W2036667662","https://openalex.org/W2040703580","https://openalex.org/W2083680786","https://openalex.org/W2102122585","https://openalex.org/W2117019496","https://openalex.org/W2120561148","https://openalex.org/W2122674287","https://openalex.org/W2124871329","https://openalex.org/W2143210482","https://openalex.org/W2154367568","https://openalex.org/W2156628505","https://openalex.org/W4236181223"],"related_works":["https://openalex.org/W2371678724","https://openalex.org/W4311055779","https://openalex.org/W2761558751","https://openalex.org/W1558215493","https://openalex.org/W3128574596","https://openalex.org/W1976009970","https://openalex.org/W2084800428","https://openalex.org/W2391300236","https://openalex.org/W2981728181","https://openalex.org/W2978475281"],"abstract_inverted_index":{"proteins":[0],"which":[1,159],"await":[2],"analysis.We":[3],"present":[4],"a":[5,26,88],"method":[6,18,47,108],"for":[7,91,96,184],"modeling":[8],"protein":[9,30,92,106,121],"families":[10],"by":[11],"means":[12],"of":[13,28,43,113,116,120,127],"probabilistic":[14],"suffix":[15],"trees":[16],"(PSTs).The":[17],"is":[19,41,48],"based":[20,140,161],"on":[21,111,141,162],"identifying":[22],"significant":[23],"patterns":[24,99,175,206],"in":[25,81,176,237,244],"set":[27],"related":[29],"sequences.The":[31,107],"input":[32],"sequences":[33],"do":[34],"not":[35],"need":[36],"to":[37,190],"be":[38,52,136],"aligned,":[39],"nor":[40],"delineation":[42],"domain":[44],"boundaries":[45],"required.The":[46],"automatic,":[49],"and":[50,72,95,157,194,197,228],"can":[51,77,85,135],"applied,":[53],"without":[54],"assuming":[55],"any":[56],"preliminary":[57],"biological":[58,64],"information,":[59],"with":[60,129],"surprising":[61],"success.Incorporating":[62],"basic":[63],"considerations":[65],"such":[66,186],"as":[67,87,180,241,243],"amino":[68,73],"acid":[69],"background":[70],"probabilities,":[71],"acids":[74],"substitution":[75],"probabilities":[76],"improve":[78],"the":[79,114,117,124,132,199,204,215,229],"performance":[80],"some":[82],"cases.The":[83],"PST":[84],"serve":[86],"predictive":[89],"tool":[90],"sequence":[93],"classification,":[94],"detecting":[97],"conserved":[98,143],"(possibly":[100],"functionally":[101],"or":[102],"structurally":[103],"important)":[104],"within":[105],"was":[109],"tested":[110],"one":[112],"state":[115],"art":[118],"databases":[119],"families,":[122],"namely,":[123],"Pfam":[125],"database":[126],"HMMs,":[128],"satisfactory":[130],"performance.Generally,":[131],"existing":[133],"approaches":[134],"divided":[137],"into":[138],"those":[139,158],"short":[142],"motifs":[144,193],"(e.g.[Bairoch":[145],"et":[146,150,170,208,212,221,232],"al.":[147,151,171,209,213,222,233],"1997,":[148,210],"Attwood":[149,211],"1998,":[152],"Henikoff":[153,155,224,226],"&":[154,166,225],"19911)":[156],"are":[160,203],"whole":[163],"domains":[164,195],"(e.g.[Sonnhammer":[165],"Kahn":[167],"1994,":[168],"Sonnhammer":[169],"19981).The":[172],"manually":[173],"defined":[174],"PROSITE":[177],"have":[178],"served":[179],"an":[181],"excellent":[182],"seed":[183],"several":[185],"works.The":[187],"methods":[188],"used":[189],"represent":[191],"these":[192],"vary,":[196],"among":[198],"most":[200],"popular":[201],"forms":[202,235],"consensus":[205],"[Bairoch":[207],"19981,":[214],"position-specific":[216],"scoring":[217],"matrices":[218],"(profiles)":[219],"[Gribskov":[220],"1987,":[223],"19911":[227],"HMMs":[230],"[Krogh":[231],"19961.These":[234],"differ":[236],"their":[238,245],"mathematical":[239],"complexity,":[240],"well":[242],"sensitivity/selectivity.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}