{"id":"https://openalex.org/W7221574431","doi":"https://doi.org/10.64898/2026.10.10.757278","title":"Alignment-Aware Genomic Coordinate Encoding for Long-Range DNA Modeling","display_name":"Alignment-Aware Genomic Coordinate Encoding for Long-Range DNA Modeling","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7221574431","doi":"https://doi.org/10.64898/2026.10.10.757278"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.10.757278","doi":"https://doi.org/10.64898/2026.10.10.757278","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.10.757278","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.10.757278.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"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/2026/10/12/2026.10.10.757278.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103653193","display_name":"Xu Yang","orcid":"https://orcid.org/0009-0001-4517-3648","observed_orcids":["https://orcid.org/0009-0001-4517-3648"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["Tencent AI for Life Sciences Lab","The Hong Kong University of Science and Technology (Guangzhou)"],"raw_orcid":"https://orcid.org/0009-0001-4517-3648","affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056461668","display_name":"Chenchen Qin","orcid":"https://orcid.org/0009-0002-8663-1657","observed_orcids":["https://orcid.org/0009-0002-8663-1657"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Qin","raw_affiliation_strings":["Tencent AI for Life Sciences Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158432539","display_name":"Fang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Wang","raw_affiliation_strings":["Tencent AI for Life Sciences Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654854","display_name":"Bing He","orcid":"https://orcid.org/0000-0003-1719-9290","observed_orcids":["https://orcid.org/0000-0003-1719-9290","https://orcid.org/0000-0002-8797-7919"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing He","raw_affiliation_strings":["Tencent AI for Life Sciences Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158514281","display_name":"Yu Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Tencent AI for Life Sciences Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158496762","display_name":"Jiayang Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayang Wu","raw_affiliation_strings":["Jinan University","Tencent AI for Life Sciences Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jinan University","institution_ids":["https://openalex.org/I159948400"]},{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424688","display_name":"Yanlin Zhang","orcid":"https://orcid.org/0000-0003-4002-443X","observed_orcids":["https://orcid.org/0000-0003-4002-443X"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100695406","display_name":"Jianhua Yao","orcid":"https://orcid.org/0000-0001-9157-9596","observed_orcids":["https://orcid.org/0000-0001-9157-9596"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianhua Yao","raw_affiliation_strings":["Tencent AI for Life Sciences Lab"],"raw_orcid":"https://orcid.org/0000-0001-9157-9596","affiliations":[{"raw_affiliation_string":"Tencent AI for Life Sciences Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100695406"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"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":0.6606000065803528,"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":0.6606000065803528,"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":0.13099999725818634,"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":0.0917000025510788,"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/genomic-foundation-models","display_name":"genomic foundation models","score":0.996999979019165},{"id":"https://openalex.org/keywords/coordinate-reference-systems","display_name":"coordinate reference systems","score":0.7419999837875366},{"id":"https://openalex.org/keywords/variant-effect-prediction","display_name":"variant effect prediction","score":0.6700000166893005},{"id":"https://openalex.org/keywords/human-population-variation","display_name":"human population variation","score":0.8759999871253967}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6704999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158000230789185},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6079000234603882},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5717999935150146},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.45590001344680786},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.37779998779296875},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.37049999833106995},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.3479999899864197},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33410000801086426},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.32910001277923584},{"id":"https://openalex.org/C17757408","wikidata":"https://www.wikidata.org/wiki/Q4135516","display_name":"genomic DNA","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.26489999890327454},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C22322919","wikidata":"https://www.wikidata.org/wiki/Q5533501","display_name":"Genomic organization","level":4,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.10.757278","doi":"https://doi.org/10.64898/2026.10.10.757278","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.10.757278","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.10.757278.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.10.757278","doi":"https://doi.org/10.64898/2026.10.10.757278","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.10.757278","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.10.757278.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221574431.pdf","grobid_xml":"https://content.openalex.org/works/W7221574431.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108234281","https://openalex.org/W2171777347","https://openalex.org/W2789843538","https://openalex.org/W2796153844","https://openalex.org/W2953263404","https://openalex.org/W3127238141","https://openalex.org/W3129831491","https://openalex.org/W3203588026","https://openalex.org/W4367597910","https://openalex.org/W4388979610","https://openalex.org/W4396721167","https://openalex.org/W4401103147","https://openalex.org/W4404349982","https://openalex.org/W4404821554","https://openalex.org/W4405995672","https://openalex.org/W4416334793","https://openalex.org/W4417514206","https://openalex.org/W7125967877"],"related_works":["https://openalex.org/W7126172560","https://openalex.org/W4382603228","https://openalex.org/W7223242776","https://openalex.org/W7165358424","https://openalex.org/W6910847958","https://openalex.org/W7222232364","https://openalex.org/W7130721914","https://openalex.org/W7127366769","https://openalex.org/W4406419344","https://openalex.org/W7221194587"],"abstract_inverted_index":{"Abstract":[0],"Current":[1],"genomic":[2,77,91,189,204],"foundation":[3,92],"models":[4],"(GFMs)":[5],"largely":[6],"inherit":[7],"the":[8,30,58,117,141,147,175],"language-modeling":[9],"paradigm":[10],"over":[11,153],"contiguous":[12],"token":[13],"sequences,":[14],"treating":[15],"DNA":[16],"as":[17,35],"ordinary":[18],"text.":[19],"The":[20,160,213],"genome,":[21],"however,":[22],"is":[23,162,216],"a":[24,45,90,166],"coordinate-based":[25],"system":[26,61,144],"of":[27,48],"sparse":[28],"signals:":[29],"entities":[31],"that":[32,104,120,133,146,171],"matter,":[33],"such":[34],"individual":[36],"variants,":[37],"regulatory":[38,208],"elements,":[39],"and":[40,51,75,84,113,126,156,181,194,210],"distal":[41],"gene":[42],"interactions,":[43],"occupy":[44],"vanishing":[46],"fraction":[47],"chromosome-scale":[49],"sequences":[50,190],"are":[52,81,123],"defined":[53],"by":[54,64],"their":[55],"positions":[56],"in":[57],"reference":[59,118,142],"coordinate":[60,143],"rather":[62],"than":[63],"linear":[65],"proximity.":[66],"This":[67],"mismatch":[68],"limits":[69],"pure":[70],"DNA-sequence":[71],"modeling":[72],"on":[73,95,140,187],"individualized":[74],"non-contiguous":[76,135,154],"tasks,":[78,205],"where":[79],"inputs":[80],"naturally":[82],"variant-centric":[83],"sparsely":[85],"sampled.":[86],"We":[87],"present":[88],"USM-AA,":[89],"model":[93,148,161],"built":[94],"two":[96],"complementary":[97],"components:":[98],"an":[99,127],"alignment":[100,106],"embedding":[101],"module":[102],"(AEM)":[103],"represents":[105],"information,":[107],"capturing":[108],"each":[109],"token\u2019s":[110],"chromosome,":[111],"strand,":[112],"comparison":[114],"outcome":[115],"against":[116],"so":[119,145],"variant":[121],"signals":[122],"explicitly":[124],"represented;":[125],"Alignment-Aware":[128],"Rotary":[129],"Position":[130],"Embedding":[131],"(AARoPE)":[132],"performs":[134],"positional":[136,151],"encoding,":[137],"placing":[138],"tokens":[139],"maintains":[149],"correct":[150],"relationships":[152],"input":[155],"supports":[157],"end-to-end":[158],"training.":[159],"further":[163],"trained":[164],"with":[165],"reverse-complement":[167],"masked":[168],"learning":[169],"strategy":[170],"operates":[172],"purely":[173],"at":[174,219],"loss":[176],"level,":[177],"adding":[178],"no":[179,183],"parameters":[180],"requiring":[182],"architectural":[184],"modification.":[185],"Pretrained":[186],"large-scale":[188],"spanning":[191],"cross-species":[192],"evolution":[193],"human":[195],"population":[196],"variation,":[197],"USM-AA":[198],"achieves":[199],"state-of-the-art":[200],"performance":[201],"across":[202],"multiple":[203],"including":[206],"long-range":[207],"prediction":[209],"variant-effect":[211],"prediction.":[212],"source":[214],"code":[215],"publicly":[217],"available":[218],"https://github.com/Jimmy0743/USM-AA":[220],".":[221]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-13T00:00:00"}