{"id":"W3040708325","doi":"10.1101/2020.07.10.195636","title":"Discovery of widespread transcription initiation at microsatellites predictable by sequence-based deep neural network","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"","keywords":"Enhancer; Biology; Microsatellite; Transcription (linguistics); Genetics; Tandem repeat; Promoter; Gene; Computational biology; DNA sequencing; Minion; DNA; 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":[0.0003237496,0.0005310889,0.0003231572,0.0003440818,0.0001526434,0.0003644206,0.0004986029,0.0005047272,0.000598219],"category_scores_gemma":[0.00074189,0.0002979559,0.0003838567,0.0002760674,0.0003622233,0.0003579528,0.0003583388,0.000818229,0.0002529723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006555454,"about_ca_system_score_gemma":0.0004334156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003648403,"about_ca_topic_score_gemma":0.006150659,"domain_scores_codex":[0.9998709,0.00002127041,0.000003964598,0.00005827746,0.00001948383,0.00002614108],"domain_scores_gemma":[0.9997428,0.000120644,0.00003723146,0.00002116068,0.00005221077,0.00002603916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004585809,0.0002858331,0.01994778,0.0001899227,0.0001728086,0.0002618431,0.0001428468,0.6646564,0.1441714,0.007622724,0.005365561,0.1567242],"study_design_scores_gemma":[0.000003697744,0.00001075246,0.0007781623,0.000002552788,0.000004295697,0.000005776513,0.000004536473,0.994486,0.003135049,0.00143504,0.0001309343,0.000003167077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6407516,0.0005657452,0.3527936,0.0005960804,0.00008352513,0.00003063898,0.000911055,0.00176319,0.002504521],"genre_scores_gemma":[0.9439296,0.0001756409,0.05162714,0.0001638237,0.00002435745,0.00004213863,0.001475688,0.00007790772,0.002483679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003648403,"threshold_uncertainty_score":0.007254303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01190563610247968,"score_gpt":0.203107986156192,"score_spread":0.1912023500537123,"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."}}