{"id":"W4225684933","doi":"10.1186/s12859-022-04647-5","title":"Supervised promoter recognition: a benchmark framework","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Benchmark (surveying); Benchmarking; Machine learning; Deep learning; Computer science; Artificial intelligence; Promoter; DNA microarray; Computational biology; Process (computing); Data mining; Biology; Gene; 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":[0.0002076024,0.0001420637,0.00011463,0.00004360714,0.0002449003,0.00004370777,0.0002758139,0.00009629872,0.0004394794],"category_scores_gemma":[0.00005114363,0.0001479069,0.0001041597,0.0001207866,0.00003544203,0.000005054528,0.0003517993,0.00016515,0.00005030389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002839507,"about_ca_system_score_gemma":0.0001113734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002276857,"about_ca_topic_score_gemma":0.000005241609,"domain_scores_codex":[0.9990837,0.00003721051,0.0003105175,0.000150153,0.0001809619,0.000237473],"domain_scores_gemma":[0.999359,0.00001354445,0.0001112611,0.0003972573,0.00004712937,0.00007186959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002977478,0.005857665,0.08492426,0.00620231,0.002320694,0.00009254423,0.03163832,0.05521834,0.1041487,0.01293804,0.2855562,0.4081254],"study_design_scores_gemma":[0.004033272,0.003121738,0.004570625,0.00009299967,0.0001650873,0.0006086239,0.008730187,0.6542172,0.008309063,0.01411198,0.2992164,0.002822741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9207349,0.0002060972,0.06885178,0.0001538094,0.0005614277,0.0005353702,0.0003373381,0.0000443344,0.008574921],"genre_scores_gemma":[0.3824683,0.00009207315,0.6109046,0.002063711,0.0003572657,0.0002162406,0.002956302,0.00006032876,0.0008811328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5989989,"threshold_uncertainty_score":0.6031469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396104983278703,"score_gpt":0.2211159421678905,"score_spread":0.2071548923351035,"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."}}