{"id":"W1983546999","doi":"10.1186/1471-2105-9-s12-s7","title":"Extracting transcription factor binding sites from unaligned gene sequences with statistical models","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alpha Technologies (Canada)","funders":"National Science Council","keywords":"DNA binding site; Chromatin immunoprecipitation; Computational biology; DNA microarray; Transcription factor; Computer science; False positive paradox; Bayes' theorem; Genetics; Binding site; Biology; Statistical model; Gene; Data mining; Bayesian probability; Gene expression; Artificial intelligence; Promoter","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":[0.00006889226,0.0001901212,0.0001653371,0.00004043966,0.0001792421,0.00005040793,0.0001581222,0.0001383079,0.00002349016],"category_scores_gemma":[0.00002270381,0.0001593234,0.00005346198,0.00006569104,0.00009573883,0.00002641029,0.00003305668,0.00008393238,0.00001489188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002535289,"about_ca_system_score_gemma":0.0001286536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003858629,"about_ca_topic_score_gemma":0.00009152442,"domain_scores_codex":[0.9990041,0.00002183866,0.000350937,0.0001792167,0.0001913615,0.000252528],"domain_scores_gemma":[0.9994167,0.0000313406,0.00016067,0.0002322595,0.0000621858,0.00009685655],"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":[0.0001885777,0.000110447,0.01324566,0.0001475863,0.0001712876,0.00001540175,0.002497729,0.02122588,0.9603227,0.0004525398,0.0002667152,0.001355433],"study_design_scores_gemma":[0.001393426,0.0005002453,0.004775171,0.00004725981,0.00007397382,0.0001874268,0.001581356,0.8780153,0.1117048,0.00053795,0.00036316,0.0008199154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6369091,0.00006259094,0.3622646,0.000006485062,0.0000393224,0.00009860199,0.0003146604,0.000016268,0.0002883345],"genre_scores_gemma":[0.6933221,0.0001145606,0.3054278,0.00004421083,0.0000604913,0.000005971331,0.000950901,0.00001649247,0.00005747833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8567895,"threshold_uncertainty_score":0.6497021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03288224196300695,"score_gpt":0.2342696851814729,"score_spread":0.2013874432184659,"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."}}