{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0494888,0.002841056,0.002825187,0.005869756,0.001948781,0.006446593,0.008583241,0.006873647,0.004353175],"category_scores_gemma":[0.3361687,0.002368532,0.003065075,0.003107875,0.01393092,0.01584047,0.005815167,0.01047711,0.0009147492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005066419,"about_ca_system_score_gemma":0.003713226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900385,"about_ca_topic_score_gemma":0.001132775,"domain_scores_codex":[0.9699314,0.01412132,0.001504853,0.004157886,0.009067167,0.001217342],"domain_scores_gemma":[0.397993,0.558378,0.01564253,0.01644189,0.009957822,0.001586842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002663452,0.000292458,0.01597308,0.001149414,0.000261027,0.0009061917,0.0008517885,0.5205154,0.003831822,0.404635,0.003494275,0.04782321],"study_design_scores_gemma":[0.00003022546,0.00008119026,0.0007785112,0.0001654054,0.0000382944,0.0004027243,0.00006491313,0.7380286,0.001973696,0.2577921,0.0005921141,0.00005217006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02267709,0.001187033,0.9702845,0.002186927,0.0001121318,0.00009157357,0.0001329367,0.0005132363,0.002814567],"genre_scores_gemma":[0.5558975,0.002181438,0.4347646,0.00257108,0.0006441847,0.001029167,0.0005606789,0.0005829445,0.001768353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0494888,"threshold_uncertainty_score":0.2617249,"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."}}