{"id":"https://openalex.org/W7224454152","doi":"https://doi.org/10.64898/2026.10.28.762238","title":"Scooby-2: fine-tuning AlphaGenome for single-cell genomic track prediction","display_name":"Scooby-2: fine-tuning AlphaGenome for single-cell genomic track prediction","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224454152","doi":"https://doi.org/10.64898/2026.10.28.762238"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.28.762238","doi":"https://doi.org/10.64898/2026.10.28.762238","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762238","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/29/2026.10.28.762238.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/29/2026.10.28.762238.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043432989","display_name":"Johannes Hingerl","orcid":"https://orcid.org/0000-0002-8260-032X","observed_orcids":["https://orcid.org/0000-0002-8260-032X"]},"institutions":[{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Hingerl","raw_affiliation_strings":["Munich Center for Machine Learning, Munich, Germany","School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8260-032X","affiliations":[{"raw_affiliation_string":"Munich Center for Machine Learning, Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000244333","display_name":"Julien Gagneur","orcid":"https://orcid.org/0000-0002-8924-8365","observed_orcids":["https://orcid.org/0000-0002-8924-8365"]},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I4405260296","display_name":"Institut f\u00fcr Humangenetik","ror":"https://ror.org/03hxyy717","country_code":"DE","type":"facility","lineage":["https://openalex.org/I3018771216","https://openalex.org/I4405260296","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julien Gagneur","raw_affiliation_strings":["Computational Health Center, Helmholtz Center Munich, Neuherberg, Germany","Institute of Human Genetics, School of Medicine, Technical University of Munich, Munich, Germany","Munich Center for Machine Learning, Munich, Germany","School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8924-8365","affiliations":[{"raw_affiliation_string":"Computational Health Center, Helmholtz Center Munich, Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Institute of Human Genetics, School of Medicine, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4405260296","https://openalex.org/I62916508"]},{"raw_affiliation_string":"Munich Center for Machine Learning, Munich, Germany","institution_ids":["https://openalex.org/I4403386549"]},{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043432989"],"corresponding_institution_ids":["https://openalex.org/I4403386549","https://openalex.org/I62916508"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.4927000105381012,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.4927000105381012,"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":0.3310999870300293,"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":0.039500001817941666,"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/alphagenome","display_name":"AlphaGenome","score":0.9129999876022339},{"id":"https://openalex.org/keywords/chromatin-accessibility","display_name":"chromatin accessibility","score":0.9919999837875366},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.8230000138282776},{"id":"https://openalex.org/keywords/variant-effect-prediction","display_name":"variant effect prediction","score":0.9409999847412109}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5828999876976013},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285000205039978},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4163999855518341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C17757408","wikidata":"https://www.wikidata.org/wiki/Q4135516","display_name":"genomic DNA","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2660999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.28.762238","doi":"https://doi.org/10.64898/2026.10.28.762238","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762238","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/29/2026.10.28.762238.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.28.762238","doi":"https://doi.org/10.64898/2026.10.28.762238","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.28.762238","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/29/2026.10.28.762238.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4288477973","display_name":null,"funder_award_id":"TRR_267","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5037647986","display_name":"TRR 267: Nichtkodierende RNA im kardiovaskul\u00e4ren System","funder_award_id":"403584255","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G730358326","display_name":"IT Infrastruktur f\u00fcr Computational Molecular Medicine","funder_award_id":"461264291","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224454152.pdf","grobid_xml":"https://content.openalex.org/works/W7224454152.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2795783309","https://openalex.org/W3121334524","https://openalex.org/W3168867926","https://openalex.org/W3196426274","https://openalex.org/W3203588026","https://openalex.org/W4223893712","https://openalex.org/W4361001523","https://openalex.org/W4389304909","https://openalex.org/W4406178430","https://openalex.org/W4415407404","https://openalex.org/W7125967877","https://openalex.org/W7161548980"],"related_works":["https://openalex.org/W4415407404","https://openalex.org/W7125967877","https://openalex.org/W4411249796","https://openalex.org/W7127293915","https://openalex.org/W7149523116","https://openalex.org/W7131089226","https://openalex.org/W4385333137","https://openalex.org/W7203969884","https://openalex.org/W7152126181","https://openalex.org/W7223056167"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Sequence-to-function":[2],"models":[3],"predict":[4,70],"genomic":[5,76],"tracks":[6,32,77],"from":[7,78,136,141],"DNA":[8,79],"sequence.":[9,80],"AlphaGenome":[10,54,64,127,157,186,192],"has":[11,44],"been":[12],"shown":[13],"to":[14,47,69,143],"outperform":[15],"previous":[16],"models,":[17],"including":[18],"Borzoi,":[19],"on":[20,98],"most":[21],"track-prediction":[22],"and":[23,40,74,93,162,187],"variant-effect":[24],"benchmarks.":[25],"However,":[26],"like":[27],"its":[28],"predecessors,":[29],"it":[30],"predicts":[31],"only":[33],"for":[34,121],"predefined,":[35],"mostly":[36],"bulk-derived":[37],"cell":[38],"types":[39],"tissues.":[41],"While":[42],"Scooby":[43],"extended":[45],"Borzoi":[46,159],"single-cell":[48,51,71,103],"resolution,":[49],"a":[50,66,107],"adaptation":[52],"of":[53,110,133,156,185,196],"is":[55,168],"still":[56],"lacking.":[57],"Results":[58],"We":[59],"present":[60],"Scooby-2,":[61],"which":[62],"combines":[63],"with":[65,119,154],"cell-specific":[67],"decoder":[68],"RNA-seq":[72],"coverage":[73],"chromatin-accessibility":[75],"The":[81],"package":[82],"provides":[83],"the":[84,86,90,99,125,137,173,191],"implementation,":[85],"parameter-efficient":[87],"fine-tuning":[88],"setup,":[89],"training":[91,166],"pipeline":[92],"inference":[94],"scripts.":[95],"When":[96,123],"evaluated":[97],"NeurIPS":[100],"bone":[101],"marrow":[102],"dataset,":[104],"Scooby-2":[105,164],"achieved":[106],"Pearson":[108],"correlation":[109,147],"0.56":[111],"when":[112],"predicting":[113],"cell-type-specific":[114],"gene":[115],"expression":[116],"differences,":[117],"compared":[118],"0.53":[120],"Scooby.":[122],"using":[124],"distilled":[126],"backbone,":[128],"variant":[129],"effect":[130],"prediction":[131],"concordance":[132],"fine-mapped":[134],"eQTLs":[135],"OneK1K":[138],"cohort":[139],"improved":[140],"0.37":[142],"0.47":[144],"Spearman\u2019s":[145],"rank":[146],"across":[148],"all":[149],"associations,":[150],"an":[151],"improvement":[152],"consistent":[153],"that":[155],"over":[158],"itself.":[160],"Availability":[161],"implementation":[163],"alongside":[165],"code":[167],"available":[169],"at":[170],"github.com/gagneurlab/scooby":[171],"under":[172,190],"MIT":[174],"license.":[175],"Trained":[176],"weights":[177],"(":[178],"huggingface.co/johahi/neurips-scooby-2":[179],",":[180],"huggingface.co/johahi/onek1k-scooby-2":[181],")":[182],"are":[183,188],"derivatives":[184],"distributed":[189],"Model":[193],"Parameters":[194],"Terms":[195],"Use.":[197],"Contact":[198],"hingerl@in.tum.de":[199],";":[200],"gagneur@in.tum.de":[201]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-30T00:00:00"}