{"id":"https://openalex.org/W2611814747","doi":"https://doi.org/10.1089/106652700750050844","title":"Optimal Amnesic Probabilistic Automata or How to Learn and Classify Proteins in Linear Time and Space","display_name":"Optimal Amnesic Probabilistic Automata or How to Learn and Classify Proteins in Linear Time and Space","publication_year":2000,"publication_date":"2000-08-01","ids":{"openalex":"https://openalex.org/W2611814747","doi":"https://doi.org/10.1089/106652700750050844","mag":"2611814747","pmid":"https://pubmed.ncbi.nlm.nih.gov/11108469"},"language":"en","primary_location":{"id":"doi:10.1089/106652700750050844","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652700750050844","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5029039590","display_name":"Alberto Apostolico","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alberto Apostolico","raw_affiliation_strings":["Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova,          Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, Purdue University, West Lafayette, IN 47907 and Dipartimento di Elettronica e Informatica, Universit\u00e0 di Padova, Padova,          Italy","institution_ids":[]}]},{"author_position":"last","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":["School of Computer Science and Engineering, The Hebrew University, Jerusalem 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The Hebrew University, Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029039590"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1267,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95591665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"3-4","first_page":"381","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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":0.9950000047683716,"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/probabilistic-automaton","display_name":"Probabilistic automaton","score":0.7305666208267212},{"id":"https://openalex.org/keywords/deterministic-automaton","display_name":"Deterministic automaton","score":0.6088888645172119},{"id":"https://openalex.org/keywords/b\u00fcchi-automaton","display_name":"B\u00fcchi automaton","score":0.5700024962425232},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5631442666053772},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5464618802070618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5412099361419678},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5255367159843445},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.49800848960876465},{"id":"https://openalex.org/keywords/timed-automaton","display_name":"Timed automaton","score":0.469117671251297},{"id":"https://openalex.org/keywords/quantum-finite-automata","display_name":"Quantum finite automata","score":0.46787306666374207},{"id":"https://openalex.org/keywords/deterministic-finite-automaton","display_name":"Deterministic finite automaton","score":0.4425602853298187},{"id":"https://openalex.org/keywords/continuous-automaton","display_name":"Continuous automaton","score":0.44085100293159485},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4274527430534363},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.41503292322158813},{"id":"https://openalex.org/keywords/two-way-deterministic-finite-automaton","display_name":"Two-way deterministic finite automaton","score":0.4108677804470062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35847634077072144},{"id":"https://openalex.org/keywords/nondeterministic-finite-automaton","display_name":"Nondeterministic finite automaton","score":0.3338507413864136},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.3094666004180908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2895135283470154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2733553647994995}],"concepts":[{"id":"https://openalex.org/C174784677","wikidata":"https://www.wikidata.org/wiki/Q176567","display_name":"Probabilistic automaton","level":3,"score":0.7305666208267212},{"id":"https://openalex.org/C194525867","wikidata":"https://www.wikidata.org/wiki/Q5265707","display_name":"Deterministic automaton","level":3,"score":0.6088888645172119},{"id":"https://openalex.org/C165753454","wikidata":"https://www.wikidata.org/wiki/Q1020380","display_name":"B\u00fcchi automaton","level":4,"score":0.5700024962425232},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5631442666053772},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5464618802070618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5412099361419678},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5255367159843445},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.49800848960876465},{"id":"https://openalex.org/C30788636","wikidata":"https://www.wikidata.org/wiki/Q7805517","display_name":"Timed automaton","level":3,"score":0.469117671251297},{"id":"https://openalex.org/C174327141","wikidata":"https://www.wikidata.org/wiki/Q176837","display_name":"Quantum finite automata","level":4,"score":0.46787306666374207},{"id":"https://openalex.org/C104091681","wikidata":"https://www.wikidata.org/wiki/Q837528","display_name":"Deterministic finite automaton","level":3,"score":0.4425602853298187},{"id":"https://openalex.org/C21720249","wikidata":"https://www.wikidata.org/wiki/Q5165460","display_name":"Continuous automaton","level":5,"score":0.44085100293159485},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4274527430534363},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.41503292322158813},{"id":"https://openalex.org/C139423837","wikidata":"https://www.wikidata.org/wiki/Q243800","display_name":"Two-way deterministic finite automaton","level":5,"score":0.4108677804470062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35847634077072144},{"id":"https://openalex.org/C158008952","wikidata":"https://www.wikidata.org/wiki/Q617295","display_name":"Nondeterministic finite automaton","level":4,"score":0.3338507413864136},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.3094666004180908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2895135283470154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2733553647994995},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":"D008390","descriptor_name":"Markov Chains","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":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"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":"Q000145","qualifier_name":"classification","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","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":3,"locations":[{"id":"doi:10.1089/106652700750050844","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652700750050844","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:11108469","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11108469","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:www.research.unipd.it:11577/1363075","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/1363075","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1972770363","https://openalex.org/W2001331793","https://openalex.org/W2003413450","https://openalex.org/W2014459399","https://openalex.org/W2024060531","https://openalex.org/W2059513841","https://openalex.org/W2082967074","https://openalex.org/W2096556032","https://openalex.org/W2099964107","https://openalex.org/W2121252285","https://openalex.org/W2148381206","https://openalex.org/W4213149192","https://openalex.org/W4234588445","https://openalex.org/W4236181223","https://openalex.org/W4252166161"],"related_works":["https://openalex.org/W2024315516","https://openalex.org/W186350370","https://openalex.org/W2042728676","https://openalex.org/W1645283535","https://openalex.org/W2408583837","https://openalex.org/W2522171317","https://openalex.org/W3135656023","https://openalex.org/W3133748972","https://openalex.org/W1482505495","https://openalex.org/W2404099564"],"abstract_inverted_index":{"Statistical":[0],"modeling":[1],"of":[2,8,70,76,81,108,113,123,135,145,149,169,173,187,213,216,239,251],"sequences":[3,124,137],"is":[4,131,142,164,190,247],"a":[5,118,146,155,170,214,248],"central":[6],"paradigm":[7],"machine":[9],"learning":[10,105,114,234],"that":[11],"finds":[12],"multiple":[13],"uses":[14],"in":[15,28,138,158,180],"computational":[16],"molecular":[17],"biology":[18],"and":[19,47,54,61,98,101,106,140,236,242],"many":[20],"other":[21],"domains.":[22],"The":[23,111,184],"probabilistic":[24,71],"automata":[25,41,72,193],"typically":[26],"built":[27,64],"these":[29],"contexts":[30],"are":[31],"subtended":[32],"by":[33,95,219],"uniform,":[34],"fixed-memory":[35],"Markov":[36,79],"models.":[37],"In":[38],"practice,":[39],"such":[40],"tend":[42],"to":[43,104,151,191,195],"be":[44,152],"unnecessarily":[45],"bulky":[46],"computationally":[48],"imposing":[49],"both":[50],"during":[51],"their":[52],"synthesis":[53],"use.":[55],"Recently,":[56],"D.":[57],"Ron,":[58],"Y.":[59],"Singer,":[60],"N.":[62],"Tishby":[63],"much":[65],"more":[66,252],"compact,":[67],"tree-shaped":[68],"variants":[69],"under":[73],"the":[74,115,132,136,143,159,162,167,181,199,203,220,227,229],"assumption":[75],"an":[77,232],"underlying":[78],"process":[80,112],"variable":[82],"memory":[83],"length.":[84],"These":[85],"variants,":[86],"called":[87],"Probabilistic":[88],"Suffix":[89],"Trees":[90],"(PSTs)":[91],"were":[92],"subsequently":[93],"adapted":[94],"G.":[96,99],"Bejerano":[97],"Yona":[100],"applied":[102],"successfully":[103],"prediction":[107],"protein":[109],"families.":[110],"automaton":[116,163,221],"from":[117],"given":[119],"training":[120],"set":[121],"S":[122,139,150],"requires":[125],"theta(Ln2)":[126],"worst-case":[127],"time,":[128],"where":[129],"n":[130],"total":[133],"length":[134,144],"L":[141],"longest":[147],"substring":[148],"considered":[153],"for":[154,205],"candidate":[156],"state":[157],"automaton.":[160],"Once":[161],"built,":[165],"predicting":[166],"likelihood":[168],"query":[171],"sequence":[172],"m":[174,217],"characters":[175],"may":[176],"cost":[177],"time":[178],"theta(m2)":[179],"worst":[182],"case.":[183],"main":[185],"contribution":[186],"this":[188],"paper":[189,230],"introduce":[192],"equivalent":[194],"PSTs":[196],"but":[197],"having":[198],"following":[200],"properties:":[201],"Learning":[202],"automaton,":[204],"any":[206],"L,":[207],"takes":[208,222],"O":[209,223],"(n)":[210],"time.":[211,225],"Prediction":[212],"string":[215],"symbols":[218],"(m)":[224],"Along":[226],"way,":[228],"presents":[231],"evolving":[233],"scheme":[235],"addresses":[237],"notions":[238],"empirical":[240],"probability":[241],"related":[243],"efficient":[244],"computation,":[245],"which":[246],"by-product":[249],"possibly":[250],"general":[253],"interest.":[254]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}