{"id":"W4394989484","doi":"10.1038/s41598-024-59487-5","title":"DeepReg: a deep learning hybrid model for predicting transcription factors in eukaryotic and prokaryotic genomes","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Consejo Nacional de Ciencia y Tecnología","keywords":"Overfitting; Convolutional neural network; Deep learning; Computer science; Artificial intelligence; Computational biology; Transcription factor; Variance (accounting); Genome; Machine learning; Promoter; Artificial neural network; Biology; Gene; Genetics; Gene expression","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000927769,0.0001496006,0.0001308233,0.0001599982,0.0001815331,0.0002681469,0.00007564337,0.0000747171,0.000003657838],"category_scores_gemma":[0.0002544663,0.0001358981,0.00007610027,0.0001370992,0.00009968574,0.00002365474,0.00005200408,0.0001640069,0.000001041396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002566716,"about_ca_system_score_gemma":0.000086356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004749965,"about_ca_topic_score_gemma":0.00002566667,"domain_scores_codex":[0.9985639,0.00002985709,0.0003985713,0.0005530501,0.0001745579,0.0002800782],"domain_scores_gemma":[0.999509,0.00002052485,0.00009640223,0.0002551871,0.00004881192,0.00007006247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005830326,0.0001234205,0.3940602,0.002175558,0.0001327386,0.0000974112,0.01232309,0.2719972,0.2934144,0.000206012,0.00100164,0.02441008],"study_design_scores_gemma":[0.0001133209,0.00006858934,0.002061198,0.00007375678,0.000026636,0.0001506436,0.0001685208,0.9843373,0.008982409,0.001073078,0.002761101,0.0001834435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9505953,0.001549962,0.04589962,0.00003019563,0.0010844,0.0004455432,0.000002974787,0.00005823562,0.000333771],"genre_scores_gemma":[0.9952809,0.00002790884,0.002503703,0.000009714085,0.00004989333,0.0000374846,0.0002598313,0.00002574191,0.001804778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7123401,"threshold_uncertainty_score":0.5541764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126188512834832,"score_gpt":0.2475397775262073,"score_spread":0.2362778923978589,"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."}}