{"id":"W3165417486","doi":"10.1038/s41467-021-23143-7","title":"Discovery of widespread transcription initiation at microsatellites predictable by sequence-based deep neural network","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia; McGill University","funders":"National Cancer Institute; RIKEN; Institut National de la Santé et de la Recherche Médicale; Ministry of Education, Culture, Sports, Science and Technology; Agence Nationale de la Recherche; Wellcome Trust; Centre National de la Recherche Scientifique; Sanofi","keywords":"Biology; Microsatellite; Enhancer; Genetics; Transcription (linguistics); Promoter; Minion; Tandem repeat; Computational biology; Gene; DNA sequencing; Transcription factor; Genome; Gene expression; Nanopore sequencing; Allele","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003344555,0.000518,0.0003497016,0.000419864,0.0001663746,0.0003618968,0.0005172966,0.0004643345,0.000609951],"category_scores_gemma":[0.0007708968,0.0002583528,0.0004058967,0.0003043668,0.0003288544,0.0003292236,0.0003568766,0.0007537883,0.0002627812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005940109,"about_ca_system_score_gemma":0.0004585255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003946226,"about_ca_topic_score_gemma":0.006744246,"domain_scores_codex":[0.9998703,0.00002091401,0.000004431245,0.00005460615,0.00002009049,0.00002961846],"domain_scores_gemma":[0.9997211,0.0001319235,0.0000443838,0.00001831012,0.00005737652,0.00002701383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005949123,0.0003812356,0.03341265,0.0002235106,0.0002142592,0.0003399034,0.0001577489,0.6342072,0.1244042,0.005500788,0.005548882,0.1950147],"study_design_scores_gemma":[0.000004460495,0.00001780472,0.001412543,0.000003699009,0.000006437776,0.000009544461,0.000006563617,0.9940675,0.003077695,0.001240342,0.0001492229,0.000004167849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7136115,0.0007119252,0.2803854,0.0004759147,0.00006934933,0.00003478487,0.000917113,0.00150136,0.00229259],"genre_scores_gemma":[0.9575216,0.000183427,0.03837409,0.0001585908,0.0000227812,0.00004051787,0.001654756,0.00005509595,0.001989078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003946226,"threshold_uncertainty_score":0.007846475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0123007431256369,"score_gpt":0.2509197836877461,"score_spread":0.2386190405621092,"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."}}