{"id":"https://openalex.org/W4415584692","doi":"https://doi.org/10.1186/s12859-025-06261-7","title":"BioSet2Vec: extraction of k-mer dictionaries from multiple sets of biological sequences via big data technologies","display_name":"BioSet2Vec: extraction of k-mer dictionaries from multiple sets of biological sequences via big data technologies","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415584692","doi":"https://doi.org/10.1186/s12859-025-06261-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/41146034"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06261-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06261-7","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-025-06261-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012555693","display_name":"Ylenia Galluzzo","orcid":null},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ylenia Galluzzo","raw_affiliation_strings":["Department of Engineering, University of Palermo, Palermo, Italy. ylenia.galluzzo01@unipa.it","Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy. ylenia.galluzzo01@unipa.it","Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Palermo, Palermo, Italy. ylenia.galluzzo01@unipa.it","institution_ids":[]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy. ylenia.galluzzo01@unipa.it","institution_ids":[]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078881318","display_name":"Raffaele Giancarlo","orcid":"https://orcid.org/0000-0002-6286-8871"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Giancarlo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047319643","display_name":"Simona E. Rombo","orcid":"https://orcid.org/0000-0003-3833-835X"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simona E. Rombo","raw_affiliation_strings":["Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068361263","display_name":"Filippo Utro","orcid":"https://orcid.org/0000-0003-3226-7642"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Filippo Utro","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012555693"],"corresponding_institution_ids":["https://openalex.org/I900890020"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25431465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"264","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.26440000534057617,"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":0.26440000534057617,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.15970000624656677,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.12860000133514404,"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/big-data","display_name":"Big data","score":0.6730999946594238},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.447299987077713},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4350999891757965},{"id":"https://openalex.org/keywords/chromatin","display_name":"Chromatin","score":0.3896999955177307},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.33090001344680786},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.31790000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761999726295471},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6730999946594238},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.447299987077713},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4350999891757965},{"id":"https://openalex.org/C83640560","wikidata":"https://www.wikidata.org/wiki/Q180951","display_name":"Chromatin","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.33090001344680786},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25360000133514404}],"mesh":[{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002843","descriptor_name":"Chromatin","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D002843","descriptor_name":"Chromatin","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D002843","descriptor_name":"Chromatin","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-025-06261-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06261-7","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41146034","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41146034","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:ffab2f4eb24f4bafb79f8a05c169ef24","is_oa":true,"landing_page_url":"https://doaj.org/article/ffab2f4eb24f4bafb79f8a05c169ef24","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 26, Iss 1, Pp 1-23 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11369526","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12560420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:iris.unipa.it:10447/692745","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/692745","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06261-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06261-7","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5488169599","display_name":null,"funder_award_id":"E53C23001670001","funder_id":"https://openalex.org/F4320311030","funder_display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\""},{"id":"https://openalex.org/G5636153502","display_name":null,"funder_award_id":"E53C24001950001","funder_id":"https://openalex.org/F4320334079","funder_display_name":"Gruppo Nazionale per il Calcolo Scientifico"}],"funders":[{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1535743328","https://openalex.org/W2006075770","https://openalex.org/W2034337154","https://openalex.org/W2037589637","https://openalex.org/W2038412523","https://openalex.org/W2048306783","https://openalex.org/W2144086069","https://openalex.org/W2296312486","https://openalex.org/W2494121918","https://openalex.org/W2809334490","https://openalex.org/W2889326414","https://openalex.org/W2892087261","https://openalex.org/W2962807110","https://openalex.org/W3089088681","https://openalex.org/W3209469105","https://openalex.org/W3209528471","https://openalex.org/W4237212714","https://openalex.org/W4280499622","https://openalex.org/W4281946381","https://openalex.org/W4321368590","https://openalex.org/W4380883088","https://openalex.org/W4381046832","https://openalex.org/W4391099685"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1,89],"several":[2],"contexts":[3],"involving":[4],"large":[5],"collections":[6],"of":[7,9,17,21,50,56,76,83,86,103,113,132,138,158,165,176,178,192],"sets":[8,55],"biological":[10,57,122],"sequences,":[11],"a":[12,38,44,81],"relevant":[13],"problem":[14],"is":[15,41,98],"that":[16,23],"selecting":[18],"significant":[19],"groups":[20],"k-mers":[22,108],"characterize":[24],"one":[25],"set":[26],"with":[27,73,80],"regards":[28],"to":[29,64,141],"the":[30,33,48,65,74,101,111,130,136,156,163,174,185,190,193],"others":[31],"in":[32],"same":[34],"collection.":[35],"RESULTS:":[36],"Here":[37],"software":[39],"framework":[40,146],"proposed":[42,194],"implementing":[43],"novel":[45],"methodology":[46],"for":[47,69,121],"extraction":[49,102],"k-mer":[51],"dictionaries,":[52],"from":[53,116],"multiple":[54],"sequences.":[58,123],"It":[59],"has":[60,147],"been":[61,148],"implemented":[62],"according":[63,140],"most":[66],"recent":[67],"technologies":[68],"Big":[70],"Data":[71],"analytics,":[72],"perspective":[75],"allowing":[77,135],"its":[78],"usage":[79],"variety":[82],"input":[84],"datasets":[85,187],"any":[87],"size.":[88],"particular,":[90],"two":[91],"different":[92,142,152,159,168,179],"packages":[93],"are":[94],"provided.":[95],"The":[96,124,145],"first":[97],"BioFt,":[99],"enabling":[100],"recurrent":[104],"patterns":[105],"based":[106],"on":[107,150,184],"frequency":[109],"and":[110,170],"computation":[112],"other":[114],"metrics":[115],"information":[117],"retrieval,":[118],"here":[119],"specialized":[120],"second":[125],"package":[126],"BioSet2Vec,":[127],"instead,":[128],"extends":[129],"functionality":[131],"BioFt":[133],"by":[134],"creation":[137],"dictionaries":[139],"criteria.":[143],"CONCLUSIONS:":[144],"validated":[149],"three":[151],"case":[153],"studies:":[154],"(1)":[155],"characterization":[157],"chromatin":[160],"states;":[161],"(2)":[162],"study":[164],"association":[166],"between":[167],"diseases":[169],"related":[171],"genes;":[172],"(3)":[173],"analysis":[175],"genomes":[177],"organisms.":[180],"All":[181],"tests":[182],"performed":[183],"considered":[186],"have":[188],"shown":[189],"potentialities":[191],"approach.":[195]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-28T00:00:00"}
