{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001533136,0.00008491985,0.000114235,0.0001871911,0.0001427312,0.00009851311,0.0008625924,0.0001465438,0.0000282079],"category_scores_gemma":[0.0007829657,0.00006973428,0.00006248598,0.0004908429,0.0001366121,0.00001624577,0.0002702486,0.000359784,0.00000345739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002162791,"about_ca_system_score_gemma":0.00009338687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001218704,"about_ca_topic_score_gemma":0.0008132825,"domain_scores_codex":[0.9987166,0.000120088,0.0002823215,0.000345618,0.0002542076,0.0002811445],"domain_scores_gemma":[0.9987085,0.00007634377,0.00009608066,0.0009471933,0.0001242819,0.00004758248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001645597,0.00004266723,0.07607087,0.00002236324,0.00007417688,3.883607e-7,0.000331898,0.0000484828,0.9202522,0.00003804926,0.0000200183,0.003082428],"study_design_scores_gemma":[0.0003353557,0.00008299232,0.5785159,0.00001007047,0.00006123116,0.000003865193,0.0009856789,0.0889544,0.3303867,0.0001769051,0.0003436426,0.0001432319],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985089,0.00005880355,0.0007540496,0.000160488,0.00004962221,0.0001999138,0.0001630156,0.000005360599,0.00009988084],"genre_scores_gemma":[0.9984821,0.0001068246,0.0006563105,0.000007369838,0.00008808953,0.00001133885,0.0005342835,0.00001490186,0.00009877494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5898654,"threshold_uncertainty_score":0.2843682,"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."}}