{"id":"https://openalex.org/W7225378676","doi":"https://doi.org/10.64898/2026.11.05.764536","title":"Towards a foundation model for raw nanopore signal through discrete tokenization","display_name":"Towards a foundation model for raw nanopore signal through discrete tokenization","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225378676","doi":"https://doi.org/10.64898/2026.11.05.764536"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.05.764536","doi":"https://doi.org/10.64898/2026.11.05.764536","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764536","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.05.764536.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/2026/11/06/2026.11.05.764536.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081728397","display_name":"Guangzhao Cheng","orcid":"https://orcid.org/0009-0008-6160-3637","observed_orcids":["https://orcid.org/0009-0008-6160-3637"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Guangzhao Cheng","raw_affiliation_strings":["University of Helsinki"],"raw_orcid":"https://orcid.org/0009-0008-6160-3637","affiliations":[{"raw_affiliation_string":"University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004439161","display_name":"Esa Pitk\u00e4nen","orcid":"https://orcid.org/0000-0002-9818-6370","observed_orcids":["https://orcid.org/0000-0002-9818-6370"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Esa Pitk\u00e4nen","raw_affiliation_strings":["University of Helsinki"],"raw_orcid":"https://orcid.org/0000-0002-9818-6370","affiliations":[{"raw_affiliation_string":"University of Helsinki","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004439161"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8734999895095825,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8734999895095825,"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":0.04309999942779541,"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/T11582","display_name":"Nanopore and Nanochannel Transport Studies","score":0.020500000566244125,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nanopore-sequencing","display_name":"nanopore sequencing","score":0.9340000152587891},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.8460000157356262},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.8050000071525574},{"id":"https://openalex.org/keywords/masked-token-prediction","display_name":"masked token prediction","score":0.8240000009536743},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.722000002861023},{"id":"https://openalex.org/keywords/species-identification","display_name":"species identification","score":0.6140000224113464},{"id":"https://openalex.org/keywords/base-calling","display_name":"base calling","score":0.7250000238418579},{"id":"https://openalex.org/keywords/transferable-representations","display_name":"transferable representations","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713699996471405},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C141795571","wikidata":"https://www.wikidata.org/wiki/Q580942","display_name":"Nanopore","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4731999933719635},{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.46299999952316284},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2781188995","wikidata":"https://www.wikidata.org/wiki/Q6934982","display_name":"Multiplex","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.05.764536","doi":"https://doi.org/10.64898/2026.11.05.764536","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764536","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.05.764536.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:10.64898/2026.11.05.764536","doi":"https://doi.org/10.64898/2026.11.05.764536","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764536","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/06/2026.11.05.764536.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":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225378676.pdf","grobid_xml":"https://content.openalex.org/works/W7225378676.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4307323391"],"related_works":["https://openalex.org/W4402829493","https://openalex.org/W7215609852","https://openalex.org/W7164890260","https://openalex.org/W7125788291","https://openalex.org/W4405728194","https://openalex.org/W2949279762","https://openalex.org/W4412950017","https://openalex.org/W7140204373","https://openalex.org/W7221542830","https://openalex.org/W7118483724"],"abstract_inverted_index":{"Nanopore":[0],"sequencing":[1,149],"reads":[2,98],"nucleic":[3],"acids":[4],"as":[5,117,119,157],"changes":[6],"in":[7,101],"ionic":[8],"current":[9],"that":[10],"carry":[11],"information":[12],"beyond":[13],"the":[14,66,84],"base":[15],"sequence.":[16],"Self-supervised":[17],"pretrained":[18,137],"models":[19],"have":[20],"advanced":[21],"genomic":[22],"sequence":[23],"modeling":[24],"and":[25,38,111,146],"single-cell":[26],"analysis,":[27],"but":[28],"remain":[29],"underexplored":[30],"for":[31,60,160],"raw":[32,72,164],"nanopore":[33,73,165],"signals,":[34],"which":[35],"are":[36],"continuous":[37],"lack":[39],"a":[40,58,120,158],"native":[41],"token":[42],"vocabulary.":[43],"Here":[44],"we":[45],"present":[46],"Brieno,":[47],"an":[48],"approach":[49],"combining":[50],"reconstruction-based":[51],"tokenization":[52],"through":[53],"residual":[54],"vector":[55],"quantization":[56],"with":[57,131],"Transformer":[59,67],"contextual":[61,138],"representation":[62],"learning.":[63],"We":[64],"pretrain":[65],"using":[68],"masked-token":[69],"prediction":[70],"on":[71],"signals":[74],"from":[75],"118":[76],"million":[77],"reads.":[78],"With":[79],"frozen":[80],"or":[81],"fine-tuned":[82],"features,":[83],"model":[85,116],"identifies":[86],"species":[87],"without":[88],"requiring":[89],"reference":[90],"genomes.":[91],"It":[92],"complements":[93],"Dorado":[94],"by":[95],"accurately":[96],"classifying":[97],"left":[99],"unclassified":[100],"native-barcode":[102],"demultiplexing,":[103],"approaches":[104],"Dorado's":[105,113],"basecalling":[106],"performance":[107,142],"across":[108,148],"six":[109],"genomes,":[110],"exceeds":[112],"specialized":[114],"5-methylcytosine":[115],"well":[118],"dedicated":[121],"6-methyladenine":[122],"caller.":[123],"Brieno":[124],"also":[125],"supports":[126],"accurate":[127],"CpG":[128],"methylation":[129],"detection":[130],"limited":[132],"labeled":[133],"data.":[134],"Across":[135],"tasks,":[136],"representations":[139,162],"improve":[140],"downstream":[141],"over":[143],"non-pretrained":[144],"baselines":[145],"generalize":[147],"runs.":[150],"Together,":[151],"these":[152],"findings":[153],"support":[154],"self-supervised":[155],"pretraining":[156],"basis":[159],"transferable":[161],"of":[163],"signals.":[166]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-07T00:00:00"}