{"id":"https://openalex.org/W7117727932","doi":"https://doi.org/10.1109/wincom65874.2025.11313377","title":"Alignment-Free DNA Sequence Clustering Using Deep Siamese BiLSTM and Attention Mechanisms","display_name":"Alignment-Free DNA Sequence Clustering Using Deep Siamese BiLSTM and Attention Mechanisms","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7117727932","doi":"https://doi.org/10.1109/wincom65874.2025.11313377"},"language":null,"primary_location":{"id":"doi:10.1109/wincom65874.2025.11313377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wincom65874.2025.11313377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Wireless Networks and Mobile Communications (WINCOM)","raw_type":"proceedings-article"},"type":"article","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/A5121678429","display_name":"Adnane Touiyate","orcid":null},"institutions":[{"id":"https://openalex.org/I3121676899","display_name":"Universit\u00e9 Ibn-Tofail","ror":"https://ror.org/02wj89n04","country_code":"MA","type":"education","lineage":["https://openalex.org/I3121676899"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Adnane Touiyate","raw_affiliation_strings":["National School of Applied Sciences, Ibn Tofail University,Engineering Science Laboratory,Kenitra,Morocco"],"affiliations":[{"raw_affiliation_string":"National School of Applied Sciences, Ibn Tofail University,Engineering Science Laboratory,Kenitra,Morocco","institution_ids":["https://openalex.org/I3121676899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061097540","display_name":"Tarik Boujiha","orcid":"https://orcid.org/0000-0001-7144-5144"},"institutions":[{"id":"https://openalex.org/I3121676899","display_name":"Universit\u00e9 Ibn-Tofail","ror":"https://ror.org/02wj89n04","country_code":"MA","type":"education","lineage":["https://openalex.org/I3121676899"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Tarik Boujiha","raw_affiliation_strings":["National School of Applied Sciences, Ibn Tofail University,Engineering Science Laboratory,Kenitra,Morocco"],"affiliations":[{"raw_affiliation_string":"National School of Applied Sciences, Ibn Tofail University,Engineering Science Laboratory,Kenitra,Morocco","institution_ids":["https://openalex.org/I3121676899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031978107","display_name":"Cha\u00efma\u00e2 Kissi","orcid":"https://orcid.org/0000-0002-2073-0890"},"institutions":[{"id":"https://openalex.org/I3121676899","display_name":"Universit\u00e9 Ibn-Tofail","ror":"https://ror.org/02wj89n04","country_code":"MA","type":"education","lineage":["https://openalex.org/I3121676899"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Chaima\u00e2 Kissi","raw_affiliation_strings":["National School of Applied Sciences, Ibn Tofail University,Advanced Systems Science Laboratory,Kenitra,Morocco"],"affiliations":[{"raw_affiliation_string":"National School of Applied Sciences, Ibn Tofail University,Advanced Systems Science Laboratory,Kenitra,Morocco","institution_ids":["https://openalex.org/I3121676899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092248492","display_name":"Idriss Moumen","orcid":"https://orcid.org/0000-0002-9981-6370"},"institutions":[{"id":"https://openalex.org/I3121676899","display_name":"Universit\u00e9 Ibn-Tofail","ror":"https://ror.org/02wj89n04","country_code":"MA","type":"education","lineage":["https://openalex.org/I3121676899"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Idriss Moumen","raw_affiliation_strings":["Ibn Tofail University,Faculty of Sciences,Department of Computer Science,Kenitra,Morocco"],"affiliations":[{"raw_affiliation_string":"Ibn Tofail University,Faculty of Sciences,Department of Computer Science,Kenitra,Morocco","institution_ids":["https://openalex.org/I3121676899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121678429"],"corresponding_institution_ids":["https://openalex.org/I3121676899"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65725786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.34940001368522644,"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":0.34940001368522644,"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":0.251800000667572,"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":0.22709999978542328,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6917999982833862},{"id":"https://openalex.org/keywords/rand-index","display_name":"Rand index","score":0.5529000163078308},{"id":"https://openalex.org/keywords/silhouette","display_name":"Silhouette","score":0.5254999995231628},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48539999127388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.43970000743865967}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.5529000163078308},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5220000147819519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48539999127388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4546000063419342},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.43970000743865967},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.42579999566078186},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.28459998965263367},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wincom65874.2025.11313377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wincom65874.2025.11313377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Wireless Networks and Mobile Communications (WINCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2124351063","https://openalex.org/W2138621090","https://openalex.org/W2156125289","https://openalex.org/W2935703330","https://openalex.org/W2950150251","https://openalex.org/W3193844559","https://openalex.org/W4220791336","https://openalex.org/W4226107243","https://openalex.org/W4292266001","https://openalex.org/W4385897776","https://openalex.org/W4388764760"],"related_works":[],"abstract_inverted_index":{"Clustering":[0],"of":[1,44,65,91,97,101],"genomic":[2,137],"sequences":[3],"is":[4],"critical":[5],"for":[6,136],"elucidating":[7],"biological":[8,19],"relationships,":[9],"yet":[10],"unsupervised":[11,134],"methods":[12],"often":[13],"compromise":[14],"between":[15],"accuracy,":[16],"generalizability,":[17],"and":[18,75,99,133,146],"interpretability.":[20],"We":[21,57],"propose":[22],"a":[23,62,130],"Siamese":[24],"Bidirectional":[25],"Long":[26],"ShortTerm":[27],"Memory":[28],"(BiLSTM)":[29],"network":[30],"with":[31,80,122,140],"an":[32],"attention":[33],"mechanism,":[34],"trained":[35],"via":[36],"contrastive":[37],"loss":[38],"to":[39,118],"learn":[40],"biologically":[41],"meaningful":[42],"representations":[43],"DNA":[45],"sequences,":[46],"entirely":[47],"without":[48],"supervision,":[49],"augmentation,":[50],"or":[51],"hand-crafted":[52],"<tex":[53,111],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54,112],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$k$</tex>-mer":[55],"features.":[56],"evaluate":[58],"our":[59],"model":[60,104],"on":[61],"challenging":[63],"benchmark":[64],"Betacoronavirus":[66],"genomes.":[67],"The":[68],"resulting":[69],"embeddings":[70,85],"capture":[71],"both":[72],"sequence-level":[73],"similarity":[74],"evolutionary":[76,147],"patterns.":[77],"When":[78],"paired":[79],"standard":[81],"clustering":[82],"algorithms,":[83],"these":[84],"yield":[86],"highquality":[87],"partitions:":[88],"silhouette":[89],"score":[90],"0.814,":[92],"Adjusted":[93],"Rand":[94],"Index":[95],"(ARI)":[96],"0.713,":[98],"purity":[100],"0.864.":[102],"Our":[103],"also":[105],"reduces":[106],"intra-cluster":[107],"embedding":[108],"variance":[109],"by":[110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{2}":[113],"\\boldsymbol{-}":[114],"\\mathbf{4}":[115],"\\boldsymbol{\\times}$</tex>":[116],"compared":[117],"baselines,":[119],"aligning":[120],"closely":[121],"known":[123],"taxonomic":[124],"subgenera.":[125],"Overall,":[126],"this":[127],"framework":[128],"offers":[129],"scalable,":[131],"interpretable,":[132],"solution":[135],"sequence":[138],"clustering,":[139],"strong":[141],"potential":[142],"in":[143],"comparative":[144],"genomics":[145],"biology.":[148]},"counts_by_year":[],"updated_date":"2026-01-01T23:40:50.289205","created_date":"2025-12-31T00:00:00"}
