{"id":"W4410139616","doi":"10.1038/s41467-025-58862-8","title":"Predictive biophysical neural network modeling of a compendium of in vivo transcription factor DNA binding profiles for Escherichia coli","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Diffusion and Search Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Consejo Nacional de Ciencia y Tecnología; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Consejo Nacional de Ciencia y Tecnología, Guatemala; Universidad Nacional Autónoma de México","keywords":"Compendium; Escherichia coli; Transcription factor; Computational biology; DNA; In vivo; DNA binding site; Biology; Genetics; Bioinformatics; Promoter; Gene; Gene expression; Geography","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":[0.00009807842,0.00007487398,0.0001431603,0.00006164495,0.00006680618,0.000006127552,0.0003981038,0.0001903344,0.00000165887],"category_scores_gemma":[0.00006969486,0.00007371526,0.00008438569,0.0002119842,0.00008636923,0.000004775421,0.0001269528,0.0002379291,5.932061e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000141286,"about_ca_system_score_gemma":0.00007365966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001057363,"about_ca_topic_score_gemma":0.0001534959,"domain_scores_codex":[0.9994074,0.00007968707,0.0002098357,0.0001226672,0.00006537596,0.0001150512],"domain_scores_gemma":[0.9992854,0.00004860858,0.00006314783,0.0004428535,0.0001385009,0.00002146042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000140837,0.0001916769,0.001381118,0.00003927785,0.00003503588,2.379099e-8,0.00009122333,0.002978313,0.9890968,0.005753475,0.0001692012,0.0001230702],"study_design_scores_gemma":[0.0007947507,0.0001646781,0.003682894,0.00009858725,0.00002835,1.645122e-7,0.0002184324,0.9265586,0.06674302,0.0002722575,0.001327303,0.0001110178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927252,0.0004726901,0.005278003,0.0003525639,0.00008545998,0.0004403977,0.0002543841,0.000006951645,0.0003843333],"genre_scores_gemma":[0.9954024,0.0002073645,0.00391764,0.00005654304,0.00001836235,0.00005296389,0.0002753211,0.000007374749,0.00006201935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9235802,"threshold_uncertainty_score":0.3006021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01958683255642572,"score_gpt":0.3071372252944508,"score_spread":0.287550392738025,"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."}}