{"id":"W1976093396","doi":"10.1186/1471-2105-13-151","title":"Towards a theoretical understanding of false positives in DNA motif finding","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Motif (music); False positive paradox; DNA microarray; Computational biology; Sequence motif; DNA; Computer science; True positive rate; DNA sequencing; Biology; Artificial intelligence; Genetics; Gene; 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":[0.0003219976,0.0001215244,0.0001500488,0.00007218234,0.00003559413,0.00001705916,0.0001398685,0.0001345658,0.00001452004],"category_scores_gemma":[0.00008406669,0.0001111048,0.00007283187,0.00009029291,0.0001349776,0.00001087605,0.0001265503,0.00006701236,0.00000514056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004703522,"about_ca_system_score_gemma":0.00005950144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002654485,"about_ca_topic_score_gemma":0.000008955441,"domain_scores_codex":[0.9991562,0.00002589092,0.0003475458,0.00007504148,0.0001092947,0.0002859863],"domain_scores_gemma":[0.9995682,0.00002130649,0.0001179112,0.0001974096,0.00002155677,0.0000736607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002155155,0.0005405865,0.1377891,0.001066727,0.0001652663,0.00000181187,0.008834257,0.001710287,0.09129922,0.7551141,0.0003132133,0.002949877],"study_design_scores_gemma":[0.006536521,0.001450031,0.1239898,0.0006422298,0.0002075939,0.0002115188,0.04536963,0.5249416,0.2608222,0.0320375,0.001087184,0.0027042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8698318,0.0001205825,0.1232258,0.00002017128,0.0001011834,0.0001314819,0.000027827,0.000005997357,0.006535141],"genre_scores_gemma":[0.9645219,0.00004794109,0.03525428,0.00004403596,0.00004514424,0.000003447348,0.00005351114,0.00001228181,0.00001738794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7230766,"threshold_uncertainty_score":0.4530722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02154658368688884,"score_gpt":0.2546371448631202,"score_spread":0.2330905611762313,"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."}}