{"id":"W2044937161","doi":"10.1093/nar/gkq217","title":"De novo motif identification improves the accuracy of predicting transcription factor binding sites in ChIP-Seq data analysis","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Biology; Chromatin immunoprecipitation; DNA binding site; CTCF; Computational biology; Transcription factor; Binding site; Genetics; Gene; Chromatin; Sequence motif; DNA sequencing; Gene expression; Promoter; Enhancer","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":[0.003277615,0.001189052,0.001693025,0.002164124,0.0004142954,0.001200207,0.001471626,0.001088771,0.001364002],"category_scores_gemma":[0.009938596,0.000691848,0.001019738,0.00115541,0.0003122471,0.001214527,0.0009191288,0.001266906,0.001110586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00042273,"about_ca_system_score_gemma":0.0008381308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002823748,"about_ca_topic_score_gemma":0.006142864,"domain_scores_codex":[0.9985785,0.0004245073,0.0001375025,0.0004957376,0.0002649683,0.00009874134],"domain_scores_gemma":[0.9910902,0.006363509,0.0003821457,0.001086515,0.0009006438,0.0001771094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001658102,0.0009427751,0.09253432,0.0009973675,0.0008209608,0.0006938054,0.000324477,0.2145824,0.2791684,0.003756212,0.006195203,0.3983259],"study_design_scores_gemma":[0.00005892754,0.0001010476,0.008488666,0.00001917457,0.00006849608,0.000239611,0.00004647494,0.9526224,0.03358522,0.002093624,0.002637343,0.00003901234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3415719,0.001136623,0.6443352,0.0001700397,0.0000856513,0.0001328964,0.003075711,0.008607672,0.0008843311],"genre_scores_gemma":[0.4182091,0.00038483,0.5700471,0.0001382676,0.00004742321,0.000176107,0.009464867,0.0004594809,0.001072778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003277615,"threshold_uncertainty_score":0.01733387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04630122204744271,"score_gpt":0.3468438154730166,"score_spread":0.3005425934255739,"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."}}