{"id":"https://openalex.org/W2008049302","doi":"https://doi.org/10.1109/tcbb.2013.36","title":"Improved Multiple Sequence Alignments Using Coupled Pattern Mining","display_name":"Improved Multiple Sequence Alignments Using Coupled Pattern Mining","publication_year":2013,"publication_date":"2013-05-02","ids":{"openalex":"https://openalex.org/W2008049302","doi":"https://doi.org/10.1109/tcbb.2013.36","mag":"2008049302","pmid":"https://pubmed.ncbi.nlm.nih.gov/24384701"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2013.36","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://people.cs.vt.edu/~naren/papers/msa-tcbb.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063233838","display_name":"K. S. M. Tozammel Hossain","orcid":"https://orcid.org/0000-0003-0136-2145"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.S.M.Tozammel Hossain","raw_affiliation_strings":["Dept. of Comput. Sci., Virginia Tech, Blacskburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Virginia Tech, Blacskburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103385426","display_name":"Debprakash Patnaik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debprakash Patnaik","raw_affiliation_strings":["[Amazon Inc., Seattle, WA, USA]"],"affiliations":[{"raw_affiliation_string":"[Amazon Inc., Seattle, WA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050748800","display_name":"Srivatsan Laxman","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srivatsan Laxman","raw_affiliation_strings":["Microsoft Research, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633144","display_name":"Prateek Jain","orcid":"https://orcid.org/0000-0002-9233-5160"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prateek Jain","raw_affiliation_strings":["Microsoft Research, Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030579910","display_name":"Chris Bailey\u2010Kellogg","orcid":"https://orcid.org/0000-0003-1860-0912"},"institutions":[{"id":"https://openalex.org/I107672454","display_name":"Dartmouth College","ror":"https://ror.org/049s0rh22","country_code":"US","type":"education","lineage":["https://openalex.org/I107672454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Bailey-Kellogg","raw_affiliation_strings":["Department of Computer Science; Dartmouth College; Hanover NH USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science; Dartmouth College; Hanover NH USA","institution_ids":["https://openalex.org/I107672454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035052603","display_name":"Naren Ramakrishnan","orcid":"https://orcid.org/0000-0002-1821-9743"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naren Ramakrishnan","raw_affiliation_strings":["Dept. of Comput. Sci., Virginia Tech, Blacskburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Virginia Tech, Blacskburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.258,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":6,"citation_normalized_percentile":{"value":0.591181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":83},"biblio":{"volume":"10","issue":"5","first_page":"1098","last_page":"1112"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9904,"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/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9656,"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/tweaking","display_name":"Tweaking","score":0.77034515},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6640943},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.6255645},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.59031016}],"concepts":[{"id":"https://openalex.org/C2780200862","wikidata":"https://www.wikidata.org/wiki/Q4453309","display_name":"Tweaking","level":2,"score":0.77034515},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6640943},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.6255645},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.59031016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5363779},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.48484576},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.47481024},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42334163},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.335024},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30367595},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.22220561},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20721552},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.14404759},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":"","qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017124","descriptor_name":"Conserved Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"","qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"","qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2013.36","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.1844","pdf_url":"http://people.cs.vt.edu/~naren/papers/msa-tcbb.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24384701","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":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.1844","pdf_url":"http://people.cs.vt.edu/~naren/papers/msa-tcbb.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life on land","score":0.67}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":43,"referenced_works":["https://openalex.org/W1553696291","https://openalex.org/W1567621547","https://openalex.org/W1599268939","https://openalex.org/W1680189815","https://openalex.org/W1694876563","https://openalex.org/W1834968294","https://openalex.org/W1974326986","https://openalex.org/W1983792126","https://openalex.org/W2002638840","https://openalex.org/W2005120335","https://openalex.org/W2020150461","https://openalex.org/W2028323959","https://openalex.org/W2033339460","https://openalex.org/W2036295979","https://openalex.org/W2039229115","https://openalex.org/W2051545676","https://openalex.org/W2054600139","https://openalex.org/W2061042699","https://openalex.org/W2090359754","https://openalex.org/W2092006899","https://openalex.org/W2101418959","https://openalex.org/W2106694138","https://openalex.org/W2106882534","https://openalex.org/W2110534451","https://openalex.org/W2120772351","https://openalex.org/W2127774996","https://openalex.org/W2132926880","https://openalex.org/W2136570298","https://openalex.org/W2140292630","https://openalex.org/W2140872496","https://openalex.org/W2142113273","https://openalex.org/W2144362290","https://openalex.org/W2149342630","https://openalex.org/W2149758239","https://openalex.org/W2151457629","https://openalex.org/W2151904894","https://openalex.org/W2153819533","https://openalex.org/W2155237411","https://openalex.org/W2162800127","https://openalex.org/W2169478909","https://openalex.org/W2169602699","https://openalex.org/W2169968198","https://openalex.org/W2407774140"],"related_works":["https://openalex.org/W4386770652","https://openalex.org/W2730968108","https://openalex.org/W2158700816","https://openalex.org/W2141411672","https://openalex.org/W2133116680","https://openalex.org/W2111937814","https://openalex.org/W2091678889","https://openalex.org/W2051969447","https://openalex.org/W187239587","https://openalex.org/W1482324242"],"abstract_inverted_index":{"We":[0,192],"present":[1],"alignment":[2,20],"refinement":[3],"by":[4,90,112],"mining":[5,119,127],"coupled":[6,83,138,148],"residues":[7],"(ARMiCoRe),":[8],"a":[9,13,32,96,116,129,137,151,199],"novel":[10],"approach":[11,120,153],"to":[12,57,121,167],"classical":[14],"bioinformatics":[15],"problem,":[16],"viz.,":[17],"multiple":[18,28],"sequence":[19,77,80],"(MSA)":[21],"of":[22,76,100,105,110,136,147,173,187,190,196,202],"gene":[23],"and":[24,43,50,140,145],"protein":[25],"sequences.":[26],"Aligning":[27],"biological":[29,48],"sequences":[30,49,62],"is":[31,102],"key":[33],"step":[34],"in":[35,61,86,93,185],"elucidating":[36],"evolutionary":[37],"relationships,":[38],"annotating":[39],"newly":[40],"sequenced":[41],"segments,":[42],"understanding":[44],"the":[45,106,134,143,171,194],"relationship":[46],"between":[47],"functions.":[51],"Classical":[52],"MSA":[53],"algorithms":[54],"are":[55,68,82,88,158,182],"designed":[56],"primarily":[58],"capture":[59],"conservations":[60],"whereas":[63],"couplings,":[64,176],"or":[65],"correlated":[66],"mutations,":[67],"well":[69],"known":[70],"as":[71,128],"an":[72],"additional":[73],"important":[74],"aspect":[75],"evolution.":[78],"(Two":[79],"positions":[81],"when":[84],"mutations":[85,92],"one":[87,104],"accompanied":[89],"compensatory":[91],"another).":[94],"As":[95],"result,":[97],"better":[98,159,174],"exposition":[99],"couplings":[101],"sometimes":[103],"reasons":[107],"for":[108,170],"hand-tweaking":[109],"MSAs":[111,156,169,181],"practitioners.":[113],"ARMiCoRe":[114,197],"introduces":[115],"distinctly":[117],"pattern":[118,139],"improving":[122],"MSAs:":[123],"using":[124,150],"frequent":[125],"episode":[126],"foundational":[130],"basis,":[131],"we":[132,164,177],"define":[133],"notion":[135],"demonstrate":[141,178,193],"how":[142],"discovery":[144],"tiling":[146],"patterns":[149],"max-flow":[152],"can":[154],"yield":[155],"that":[157,179],"than":[160],"conservation-based":[161],"alignments.":[162],"Although":[163],"were":[165],"motivated":[166],"improve":[168],"sake":[172],"exposing":[175],"our":[180],"also":[183],"improvements":[184],"terms":[186],"traditional":[188],"metrics":[189],"assessment.":[191],"effectiveness":[195],"on":[198],"large":[200],"collection":[201],"data":[203],"sets.":[204]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2008049302","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2024-12-07T21:15:28.565314","created_date":"2016-06-24"}
