{"id":"https://openalex.org/W7154151800","doi":"https://doi.org/10.1186/s12859-026-06442-y","title":"Efficient and interpretable DNA/RNA representation using Koml\u00f3s\u2013Hadamard transforms","display_name":"Efficient and interpretable DNA/RNA representation using Koml\u00f3s\u2013Hadamard transforms","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154151800","doi":"https://doi.org/10.1186/s12859-026-06442-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41975261"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06442-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06442-y","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/s12859-026-06442-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133552042","display_name":"Kareem Kabbani","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kareem Kabbani","raw_affiliation_strings":["Texas A&M University, College Station, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133514551","display_name":"Samir B. Belhaouari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Samir B. Belhaouari","raw_affiliation_strings":["CSE Department, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSE Department, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000064618","display_name":"Micha\u00ebl Aupetit","orcid":"https://orcid.org/0000-0001-6321-5242"},"institutions":[{"id":"https://openalex.org/I4210087899","display_name":"Qatar Mining (Qatar)","ror":"https://ror.org/005r9px72","country_code":"QA","type":"company","lineage":["https://openalex.org/I4210087899"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Micha\u00ebl Aupetit","raw_affiliation_strings":["QCAI, Qatar Computing Research Institute, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCAI, Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I4210087899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133489784","display_name":"Aisha Al-Qahtani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087899","display_name":"Qatar Mining (Qatar)","ror":"https://ror.org/005r9px72","country_code":"QA","type":"company","lineage":["https://openalex.org/I4210087899"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Aisha Al-Qahtani","raw_affiliation_strings":["QCAI, Qatar Computing Research Institute, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCAI, Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I4210087899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133485146","display_name":"Ahmad Halabi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Halabi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, Illinois, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133483599","display_name":"Sophia L. Haoudi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152471","display_name":"Weill Cornell Medical College in Qatar","ror":"https://ror.org/05v5hg569","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210152471"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Sophia L. Haoudi","raw_affiliation_strings":["Weill Cornell Medicine-Qatar, Education City, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weill Cornell Medicine-Qatar, Education City, Doha, Qatar","institution_ids":["https://openalex.org/I4210152471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013350725","display_name":"Halima Bensmail","orcid":"https://orcid.org/0000-0001-6700-5752"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Halima Bensmail","raw_affiliation_strings":["QCAI, Qatar Computing Research Institute, Doha, Qatar. hbensmail@hbku.edu.qa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCAI, Qatar Computing Research Institute, Doha, Qatar. hbensmail@hbku.edu.qa","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5013350725"],"corresponding_institution_ids":["https://openalex.org/I1301390666"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61903106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.6535999774932861,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.6535999774932861,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.09470000118017197,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.05950000137090683,"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/encoding","display_name":"Encoding (memory)","score":0.7631000280380249},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6761999726295471},{"id":"https://openalex.org/keywords/hadamard-transform","display_name":"Hadamard transform","score":0.5751000046730042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5185999870300293},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.448199987411499}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7631000280380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930999755859375},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6761999726295471},{"id":"https://openalex.org/C60292330","wikidata":"https://www.wikidata.org/wiki/Q1014065","display_name":"Hadamard transform","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5419999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2781142347","wikidata":"https://www.wikidata.org/wiki/Q1366592","display_name":"Hilbert curve","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06442-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06442-y","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:41975261","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41975261","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:e055353ac5e7423f93218cca1d405527","is_oa":true,"landing_page_url":"https://doaj.org/article/e055353ac5e7423f93218cca1d405527","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 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13185397","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13185397/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06442-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06442-y","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W2003347102","https://openalex.org/W2016386305","https://openalex.org/W2050742392","https://openalex.org/W2102771000","https://openalex.org/W2108797218","https://openalex.org/W2138785419","https://openalex.org/W2157548679","https://openalex.org/W2198606573","https://openalex.org/W2287984595","https://openalex.org/W2336509392","https://openalex.org/W2480184144","https://openalex.org/W2915489297","https://openalex.org/W2916230551","https://openalex.org/W2944021362","https://openalex.org/W2982461186","https://openalex.org/W3105910321","https://openalex.org/W3134163647","https://openalex.org/W3185541898","https://openalex.org/W3197375931","https://openalex.org/W3207938624","https://openalex.org/W4211002022","https://openalex.org/W4310720009","https://openalex.org/W4397049907","https://openalex.org/W4407869795"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"introduces":[2],"a":[3,22,140],"novel":[4,115],"encoding":[5,87,116],"scheme":[6,88],"for":[7,133],"DNA/RNA":[8,135],"sequences,":[9],"integrating":[10],"Koml\u00f3s":[11,42],"and":[12,48,76,143],"Hadamard":[13],"transforms.":[14],"Unlike":[15],"traditional":[16],"One-Hot":[17,108],"encoding,":[18],"this":[19,86,114],"approach":[20,145],"offers":[21],"more":[23,141],"informative":[24],"representation":[25],"of":[26,59],"omics":[27],"data":[28,136],"while":[29],"significantly":[30,101],"reducing":[31],"computational":[32,103],"complexity.":[33],"However,":[34],"it":[35],"is":[36],"important":[37],"to":[38,72,107,127,146],"note":[39],"that":[40,113],"the":[41,56,69],"transform":[43],"component":[44],"provides":[45],"fewer":[46],"features":[47],"does":[49],"not":[50],"utilize":[51],"sparse":[52],"codes.":[53],"By":[54],"leveraging":[55],"inherent":[57],"properties":[58],"these":[60],"transforms,":[61],"our":[62],"method":[63],"effectively":[64],"captures":[65],"complex":[66],"patterns":[67],"within":[68],"data,":[70],"leading":[71],"improved":[73],"model":[74],"accuracy":[75],"reduced":[77],"training":[78],"times.":[79],"When":[80],"combined":[81],"with":[82,100,121],"an":[83],"image":[84,128],"transformation,":[85],"demonstrates":[89],"particularly":[90,118],"efficient":[91,142],"results,":[92],"achieving":[93],"superior":[94],"performance":[95],"across":[96],"various":[97],"predictive":[98],"tasks":[99],"lower":[102],"resource":[104],"demands":[105],"compared":[106],"encoding.":[109],"Our":[110],"findings":[111],"suggest":[112],"scheme,":[117],"when":[119],"integrated":[120],"Hilbert":[122],"Curve":[123],"mapping":[124],"or":[125],"sequence":[126],"analysis,":[129],"holds":[130],"significant":[131],"promise":[132],"advancing":[134],"analysis":[137],"by":[138],"offering":[139],"effective":[144],"feature":[147],"representation.":[148]},"counts_by_year":[],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2026-04-14T00:00:00"}