{"id":"https://openalex.org/W7225735870","doi":"https://doi.org/10.64898/2026.11.07.765118","title":"CPDD: Adapting an autoregressive DNA language model for bidirectional phage genome modeling","display_name":"CPDD: Adapting an autoregressive DNA language model for bidirectional phage genome modeling","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225735870","doi":"https://doi.org/10.64898/2026.11.07.765118"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.07.765118","doi":"https://doi.org/10.64898/2026.11.07.765118","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765118","pdf_url":null,"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://doi.org/10.64898/2026.11.07.765118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136422929","display_name":"Hao Ding","orcid":"https://orcid.org/0009-0001-1866-7183","observed_orcids":["https://orcid.org/0009-0001-1866-7183"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"hao ding","raw_affiliation_strings":["CreatiPhage Biotechnology Co., Ltd.;"],"raw_orcid":"https://orcid.org/0009-0001-1866-7183","affiliations":[{"raw_affiliation_string":"CreatiPhage Biotechnology Co., Ltd.;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059306287","display_name":"Nannan Wu","orcid":"https://orcid.org/0000-0003-1244-0030","observed_orcids":["https://orcid.org/0000-0003-1244-0030","https://orcid.org/0009-0004-9053-7182"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nannan Wu","raw_affiliation_strings":["CreatiPhage Biotechnology Co., Ltd.;"],"raw_orcid":"https://orcid.org/0000-0003-1244-0030","affiliations":[{"raw_affiliation_string":"CreatiPhage Biotechnology Co., Ltd.;","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108279374","display_name":"Tianyi Qiu","orcid":"https://orcid.org/0009-0003-4554-3201","observed_orcids":["https://orcid.org/0009-0003-4554-3201"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Qiu","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5059306287"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.5273000001907349,"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":0.5273000001907349,"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":0.23929999768733978,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.06199999898672104,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8410999774932861},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327000260353088},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46480000019073486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4498000144958496},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.44200000166893005},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.3160000145435333},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2727999985218048},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C32795469","wikidata":"https://www.wikidata.org/wiki/Q5156430","display_name":"Complementary sequences","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.07.765118","doi":"https://doi.org/10.64898/2026.11.07.765118","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765118","pdf_url":null,"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:10.64898/2026.11.07.765118","doi":"https://doi.org/10.64898/2026.11.07.765118","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.07.765118","pdf_url":null,"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"DNA":[1,29],"language":[2,30],"models":[3],"generate":[4],"sequences":[5],"ef\ufb01ciently":[6],"from":[7,51],"left":[8],"to":[9,170],"right,":[10],"but":[11],"many":[12],"genome-analysis":[13],"and":[14,34,64,79,86,93,102,125,150,167],"sequence-editing":[15],"problems":[16],"are":[17],"naturally":[18],"conditioned":[19],"on":[20,164],"both":[21],"\ufb02anks.":[22],"We":[23],"introduce":[24],"CreatiPhage,":[25],"a":[26,44,72,97,107,121,132,183],"144.5M-parameter":[27],"autoregressive":[28],"model":[31,49,124],"for":[32],"bacteriophages,":[33],"its":[35],"diffusion":[36,48,123],"extension,":[37],"CreatiPhage":[38,54],"Diffusion":[39],"DNA-LM":[40],"(CPDD).":[41],"CPDD":[42,56,114,143],"is":[43],"147.5M-parameter":[45],"bidirectional":[46],"discrete":[47],"initialized":[50],"the":[52,58],"six-epoch":[53],"checkpoint.":[55],"retains":[57],"pretrained":[59],"Transformer,":[60],"block":[61],"attention":[62],"residuals,":[63],"Engram":[65],"conditional":[66],"memory,":[67],"while":[68],"introducing":[69],"non-causal":[70],"attention,":[71],"MASK-aware":[73],"base-5":[74],"Engram,":[75],"centered":[76],"depthwise":[77],"convolution,":[78],"position-aligned":[80],"nucleotide":[81],"readout.":[82],"Training":[83],"combines":[84],"masked":[85],"GIDD-style":[87],"uniformly":[88],"substituted":[89],"bases":[90],"with":[91],"nucleotide-":[92],"amino-acid-level":[94],"losses":[95],"over":[96],"10":[98],"kb,":[99,101],"32":[100],"whole-source":[103],"context":[104,166],"curriculum.":[105],"On":[106],"screened":[108],"panel":[109],"of":[110,138,188],"522":[111],"phage":[112,152,189],"CDSs,":[113],"achieves":[115],"higher":[116],"random-mask":[117],"restoration":[118,162],"accuracy":[119],"than":[120],"comparable":[122],"performs":[126],"well":[127],"above":[128],"codon-level":[129],"references.":[130],"In":[131],"mixed-corruption":[133],"test,":[134],"it":[135],"restores":[136],"42.4%":[137],"visible":[139,165],"incorrect":[140],"bases.":[141],"Frozen":[142],"representations":[144],"also":[145],"support":[146,178],"infA":[147],"\ufb01tness":[148],"prediction":[149],"seven-class":[151],"virion":[153],"protein":[154],"subtype":[155],"classi\ufb01cation.":[156],"Controlled":[157],"evaluations":[158],"further":[159],"characterize":[160],"how":[161],"depends":[163],"identify":[168],"opportunities":[169],"improve":[171],"longer-range":[172],"sequence":[173,180],"recovery.":[174],"Together,":[175],"these":[176],"results":[177],"scaffold-conditioned":[179],"modeling":[181],"as":[182],"step":[184],"towards":[185],"modular":[186],"design":[187],"genomes.":[190]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}