{"id":"https://openalex.org/W4206319035","doi":"https://doi.org/10.1109/bibm52615.2021.9669282","title":"On identifying statistical redundancy at the level of amino acid subsequences","display_name":"On identifying statistical redundancy at the level of amino acid subsequences","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4206319035","doi":"https://doi.org/10.1109/bibm52615.2021.9669282"},"language":"en","primary_location":{"id":"doi:10.1109/bibm52615.2021.9669282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669282","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024746787","display_name":"Sandun Rajapaksa","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sandun Rajapaksa","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019059813","display_name":"Dinithi Sumanaweera","orcid":"https://orcid.org/0000-0003-4515-0988"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dinithi Sumanaweera","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083095334","display_name":"Mar\u00eda Garc\u00eda de la Banda","orcid":"https://orcid.org/0000-0002-6666-514X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maria Garcia de La Banda","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064839018","display_name":"Peter J. Stuckey","orcid":"https://orcid.org/0000-0003-2186-0459"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Stuckey","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000306843","display_name":"David Abramson","orcid":"https://orcid.org/0000-0003-0441-4596"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Abramson","raw_affiliation_strings":["Research Computing Centre, University of Queensland, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Computing Centre, University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065385022","display_name":"Lloyd Allison","orcid":"https://orcid.org/0000-0002-9020-3164"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lloyd Allison","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057325979","display_name":"Arthur M. Lesk","orcid":"https://orcid.org/0000-0002-2596-0601"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arthur Lesk","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Pennsylvania State University University Park, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Pennsylvania State University University Park, PA, U.S.A","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081792355","display_name":"Arun S. Konagurthu","orcid":"https://orcid.org/0000-0002-1610-8329"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Arun Konagurthu","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Clayton, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29348986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"64","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9983000159263611,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9983000159263611,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9955999851226807,"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":0.9945999979972839,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7342140674591064},{"id":"https://openalex.org/keywords/amino-acid","display_name":"Amino acid","score":0.5853601694107056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5042942762374878},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4940181374549866},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46843940019607544},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.46590930223464966},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4637138843536377},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4356764256954193},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4231528043746948},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.40043312311172485},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3600175976753235},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33788639307022095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3166593313217163},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31483587622642517},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.29070883989334106},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.26308268308639526},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16201522946357727},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13952729105949402}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7342140674591064},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.5853601694107056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5042942762374878},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4940181374549866},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46843940019607544},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.46590930223464966},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4637138843536377},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4356764256954193},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4231528043746948},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.40043312311172485},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3600175976753235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33788639307022095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3166593313217163},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31483587622642517},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.29070883989334106},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.26308268308639526},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16201522946357727},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13952729105949402},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm52615.2021.9669282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669282","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1534506107","https://openalex.org/W1864487875","https://openalex.org/W1967762061","https://openalex.org/W1969621320","https://openalex.org/W1995875735","https://openalex.org/W2021115755","https://openalex.org/W2031901496","https://openalex.org/W2042617000","https://openalex.org/W2046942889","https://openalex.org/W2049870911","https://openalex.org/W2065762664","https://openalex.org/W2068448872","https://openalex.org/W2074069606","https://openalex.org/W2080681712","https://openalex.org/W2109872885","https://openalex.org/W2110381504","https://openalex.org/W2132926880","https://openalex.org/W2142749069","https://openalex.org/W2164430902","https://openalex.org/W2491016140","https://openalex.org/W2526647724","https://openalex.org/W2548003600","https://openalex.org/W2745155021","https://openalex.org/W2767095293","https://openalex.org/W2768177014","https://openalex.org/W2790056550","https://openalex.org/W2791313537","https://openalex.org/W2800631698","https://openalex.org/W2962631801","https://openalex.org/W2990282754","https://openalex.org/W3157075513","https://openalex.org/W3160848901","https://openalex.org/W4287647507","https://openalex.org/W6783064236","https://openalex.org/W6794162778"],"related_works":["https://openalex.org/W2948014085","https://openalex.org/W2004215917","https://openalex.org/W2103737249","https://openalex.org/W1974956921","https://openalex.org/W2139695554","https://openalex.org/W1972247471","https://openalex.org/W1486249959","https://openalex.org/W2166325055","https://openalex.org/W2885386129","https://openalex.org/W3186624150"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,67,90],"framework":[4],"to":[5,59,70],"characterize":[6],"and":[7,35,107,115],"identify":[8],"local":[9,44,95],"sequences":[10,45,96],"of":[11,20,37,42,74,101],"proteins":[12,79],"that":[13],"are":[14,118],"statistically":[15],"redundant":[16],"under":[17],"the":[18,81],"measure":[19],"Shannon":[21],"information":[22],"content":[23],"while":[24],"accounting":[25],"for":[26,48],"variations":[27],"in":[28],"their":[29],"occurrences":[30],"over":[31],"evolutionary":[32],"insertions,":[33],"deletions,":[34],"substitutions":[36],"amino":[38,60,103],"acids.":[39],"The":[40,85,111],"identification":[41],"such":[43],"provides":[46],"insights":[47],"downstream":[49],"studies":[50],"on":[51],"proteins.":[52],"Here,":[53],"we":[54],"have":[55],"applied":[56],"our":[57],"methods":[58],"acid":[61],"sequence":[62],"data":[63,83],"sets":[64],"derived":[65],"from":[66,80,120],"database":[68],"corresponding":[69],"935,552":[71],"substructural":[72],"regions":[73],"varying":[75],"sizes,":[76],"covering":[77],"113,724":[78],"protein":[82],"bank.":[84],"results":[86],"identify,":[87],"among":[88],"others,":[89],"surjective":[91],"mapping":[92],"between":[93],"110,598":[94],"(with":[97],"an":[98],"average":[99],"length":[100],"82":[102],"acids":[104],"per":[105],"sequence)":[106],"1,493":[108],"topological":[109],"shapes.":[110],"C++":[112],"source":[113],"code":[114],"supporting":[116],"material":[117],"available":[119],"https://lcb.infotech.monash.edu.au/bibm2021.":[121]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}