{"id":"W4403338304","doi":"10.1038/s41587-024-02414-w","title":"A community effort to optimize sequence-based deep learning models of gene regulation","year":2024,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"U.S. National Library of Medicine; National Human Genome Research Institute; National Institutes of Health; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Novo Nordisk Fonden; Seoul National University; University of British Columbia; National Research Foundation of Korea; National Research Foundation; Iran Telecommunication Research Center; Michael Smith Health Research BC; Russian Science Foundation; Stem Cell Network","keywords":"Computer science; Modular design; Machine learning; Artificial intelligence; Deep learning; Genomics; Sequence (biology); Suite; Artificial neural network; Competitor analysis; Computational biology; Data science; Gene; Genome; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002231743,0.0001334839,0.000150555,0.0001458985,0.00007808764,0.00001460405,0.0002968533,0.001135812,0.000005918469],"category_scores_gemma":[0.0000657843,0.0001314699,0.00007770213,0.0002269692,0.00008768881,0.000002638346,0.0001289627,0.0007385678,0.000003386393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003780944,"about_ca_system_score_gemma":0.00006674742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002050854,"about_ca_topic_score_gemma":0.00003770509,"domain_scores_codex":[0.9992636,0.00004501019,0.000182502,0.0002496284,0.0000820018,0.0001771846],"domain_scores_gemma":[0.9993879,0.0000128294,0.00005287785,0.0004402775,0.00006960624,0.00003646824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003268935,0.0000228214,0.00003177978,0.00004668226,0.00003610938,0.000002321841,0.00003886832,0.0692856,0.9220325,0.002753251,0.00009003108,0.005627388],"study_design_scores_gemma":[0.000216299,0.0004001059,0.0001096618,0.00003683442,0.00002203438,0.00002343011,0.0000619073,0.2261031,0.7638232,0.001713483,0.007298264,0.0001917213],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9013868,0.00166102,0.09529155,0.0009071033,0.0001580611,0.0001778987,0.00002802819,0.0000896828,0.0002998717],"genre_scores_gemma":[0.9658069,0.00007978066,0.03351955,0.00014419,0.00003833992,0.0000126344,0.0002758975,0.00002505623,0.00009767605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1582093,"threshold_uncertainty_score":0.8760421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01107123646308194,"score_gpt":0.2448127783256297,"score_spread":0.2337415418625478,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}