{"id":"https://openalex.org/W7225426121","doi":"https://doi.org/10.64898/2026.11.04.764207","title":"Learning Strand-Equivariant Tokenizations of DNA with MirrorDNA","display_name":"Learning Strand-Equivariant Tokenizations of DNA with MirrorDNA","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225426121","doi":"https://doi.org/10.64898/2026.11.04.764207"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.04.764207","doi":"https://doi.org/10.64898/2026.11.04.764207","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764207","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.04.764207.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.04.764207.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139139487","display_name":"Nirjhor Datta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]},{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Nirjhor Datta","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh; Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh; Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh;","institution_ids":["https://openalex.org/I183697816","https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067504579","display_name":"Swakkhar Shatabda","orcid":"https://orcid.org/0000-0003-0669-072X","observed_orcids":["https://orcid.org/0000-0003-0669-072X","https://orcid.org/0000-0003-4954-524X"]},"institutions":[{"id":"https://openalex.org/I5518804","display_name":"BRAC University","ror":"https://ror.org/00sge8677","country_code":"BD","type":"education","lineage":["https://openalex.org/I5518804"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Swakkhar Shatabda","raw_affiliation_strings":["Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh;","institution_ids":["https://openalex.org/I5518804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063693993","display_name":"Md. Shamsuzzoha Bayzid","orcid":"https://orcid.org/0000-0002-5640-0615","observed_orcids":["https://orcid.org/0000-0002-5640-0615"]},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Shamsuzzoha Bayzid","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161046383","display_name":"M. Sohel Rahman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"M. Sohel Rahman","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I183697816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5161046383"],"corresponding_institution_ids":["https://openalex.org/I183697816"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8866999745368958,"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":0.8866999745368958,"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":0.038100000470876694,"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":0.029600000008940697,"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/dna-language-models","display_name":"DNA language models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/reverse-complement","display_name":"reverse complement","score":0.6589999794960022},{"id":"https://openalex.org/keywords/mirror-symmetry","display_name":"mirror symmetry","score":0.6679999828338623},{"id":"https://openalex.org/keywords/transcription-factor-binding-prediction","display_name":"transcription factor binding prediction","score":0.6119999885559082},{"id":"https://openalex.org/keywords/nucleotide-transformer","display_name":"Nucleotide Transformer","score":0.7250000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621999740600586},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5983999967575073},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517799973487854},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4156000018119812},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C512185932","wikidata":"https://www.wikidata.org/wiki/Q28745","display_name":"Nucleotide","level":3,"score":0.3499999940395355},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C191961535","wikidata":"https://www.wikidata.org/wiki/Q2360205","display_name":"A-DNA","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.04.764207","doi":"https://doi.org/10.64898/2026.11.04.764207","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764207","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.04.764207.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.04.764207","doi":"https://doi.org/10.64898/2026.11.04.764207","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.04.764207","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.04.764207.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225426121.pdf","grobid_xml":"https://content.openalex.org/works/W7225426121.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3157286395","https://openalex.org/W4389326242","https://openalex.org/W4398157405","https://openalex.org/W6929539434","https://openalex.org/W7118498117","https://openalex.org/W7201856157"],"related_works":["https://openalex.org/W7163577811","https://openalex.org/W4416257947","https://openalex.org/W7214165820","https://openalex.org/W7214542190","https://openalex.org/W4416823932","https://openalex.org/W7116848816","https://openalex.org/W7118498117","https://openalex.org/W4409280685","https://openalex.org/W7153990007","https://openalex.org/W4415797058"],"abstract_inverted_index":{"DNA":[0,22,78],"has":[1],"two":[2,55],"strands,":[3,56,154],"and":[4,13,28,44,57,60,130,164,182],"for":[5],"most":[6],"regulatory":[7],"label":[8,123],"prediction":[9,229],"tasks":[10],"a":[11,34,76,82,109,256],"sequence":[12],"its":[14,95,236],"reverse":[15],"complement":[16],"should":[17],"get":[18],"same":[19,112,180,218],"answer.":[20],"Yet":[21],"language":[23,79],"models":[24,176],"are":[25,71,150,238],"tokenized,":[26],"trained":[27,177,215,220],"tested":[29],"on":[30,53,118,127,152,178,190,197,206],"one":[31,228],"strand":[32],"at":[33],"time.":[35],"We":[36,73,98],"show":[37],"that":[38,85,100,149],"this":[39,101],"makes":[40],"them":[41],"inconsistent.":[42],"BPE":[43],"$k$-mer":[45],"tokenizers":[46],"split":[47],"92--100\\%":[48],"of":[49,64,94,161],"transcription-factor":[50],"motifs":[51],"differently":[52],"the":[54,68,105,111,122,128,134,159,174,179,198,233,246,251],"NT-v2,":[58,162],"DNABERT-2":[59,163,195],"HyenaDNA":[61],"change":[62],"25-31\\%":[63],"their":[65],"predictions":[66,148],"when":[67,121,137],"test":[69],"sequences":[70],"reverse-complemented.":[72],"introduce":[74],"{\\model},":[75],"compact":[77],"model":[80,113,143,219],"with":[81,221,232],"learned":[83,96],"tokenizer":[84,247],"guarantees":[86],"mirror-symmetric":[87],"token":[88],"boundaries":[89],"across":[90],"reverse-complement":[91,222],"sequences,":[92],"regardless":[93],"parameters.":[97],"prove":[99],"symmetry":[102],"holds":[103],"through":[104],"whole":[106],"model.":[107],"As":[108],"result,":[110],"can":[114,131,144],"give":[115],"identical":[116],"answers":[117],"both":[119,153,241],"strands":[120,135],"does":[124],"not":[125,183],"depend":[126],"strand,":[129,234],"still":[132,225],"tell":[133],"apart":[136],"it":[138,169,213],"does,":[139],"which":[140],"no":[141],"strand-blind":[142],"learn.":[145],"Counting":[146],"only":[147],"correct":[151],"\\model\\":[155],"more":[156,171],"than":[157,173,211],"doubles":[158],"MCC":[160],"HyenaDNA.":[165],"With":[166],"2.3M":[167],"parameters,":[168],"is":[170],"accurate":[172,205],"Caduceus":[175],"data,":[181],"significantly":[184],"different":[185],"from":[186,194],"NT-v2":[187],"(98M":[188],"parameters)":[189],"Genomic":[191],"Benchmarks":[192],"or":[193],"(117M)":[196],"Nucleotide":[199],"Transformer":[200],"tasks.":[201],"It":[202],"also":[203],"stays":[204],"inputs":[207],"sixteen":[208],"times":[209],"longer":[210],"those":[212],"was":[214],"on.":[216],"The":[217],"augmentation":[223],"instead":[224],"changes":[226],"about":[227],"in":[230,255],"ten":[231],"unless":[235],"outputs":[237],"averaged":[239],"over":[240],"strands.":[242],"Without":[243],"any":[244],"annotation,":[245],"learns":[248],"to":[249],"keep":[250],"splice-donor":[252],"signal":[253],"\\texttt{AGGT}":[254],"single":[257],"token.":[258],"Code:":[259],"https://github.com/NIRJHOR-DATTA/MirrorDNA.":[260]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-07T00:00:00"}