{"id":"W4295241395","doi":"10.1016/j.biosystems.2022.104771","title":"Genome-scale prediction of bacterial promoters","year":2022,"lang":"en","type":"article","venue":"Biosystems","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Promoter; Biology; Genome; Genetics; Computational biology; Gene; RNA polymerase; DNA; Consensus sequence; Transcription (linguistics); DNA sequencing; RNA; Gene expression; Base sequence","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":[0.0001370156,0.00007017955,0.0001014899,0.00002283479,0.00009052521,0.000004755494,0.0001145756,0.00003139595,0.00003199451],"category_scores_gemma":[0.000004251895,0.00007084911,0.00005709305,0.00004542394,0.00002354705,2.223641e-7,0.0001538536,0.0000267621,0.000001361752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001282644,"about_ca_system_score_gemma":0.00002880108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001753191,"about_ca_topic_score_gemma":0.000006057489,"domain_scores_codex":[0.9994121,0.0000457384,0.0001691293,0.000176018,0.00009029239,0.0001067424],"domain_scores_gemma":[0.9996738,0.000001772339,0.00008055694,0.0001905189,0.00002776051,0.00002562666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003894451,0.00003110363,0.003686726,0.00001830589,0.00004273927,2.730171e-7,0.0001400208,0.00003900736,0.995535,0.000005119326,0.0003384268,0.0001243338],"study_design_scores_gemma":[0.001021061,0.001558747,0.06055222,0.000006326457,0.00003670941,0.00004044044,0.0009622257,0.00004300541,0.3121582,0.00002095691,0.6233554,0.000244753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974077,0.0006336303,0.00003256217,0.00002170804,0.0007285753,0.0002058425,0.000404078,0.000002968307,0.0005628951],"genre_scores_gemma":[0.9992009,0.00003060813,0.00006686695,0.00001171373,0.0002946511,0.00004822446,0.0001329535,0.00001095574,0.0002031697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6833768,"threshold_uncertainty_score":0.2889143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00943816777362904,"score_gpt":0.1927187262435288,"score_spread":0.1832805584698997,"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."}}