{"id":"W2538873949","doi":"10.1093/bioinformatics/btw672","title":"Optimizing ChIP-seq peak detectors using visual labels and supervised machine learning","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; ENCODE; Artificial intelligence; Set (abstract data type); Genome browser; Pattern recognition (psychology); Supervised learning; Labeled data; Machine learning; Genome; Genomics; Artificial neural network; Gene; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001563638,0.0001747271,0.0001456968,0.00005076488,0.0001472755,0.00005242346,0.0001199795,0.0001268061,0.00001469333],"category_scores_gemma":[0.00006858945,0.0001306007,0.00005400078,0.00004900898,0.00006396918,0.00001248471,0.0001981234,0.00007011327,0.000007698011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002237835,"about_ca_system_score_gemma":0.0000429406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001021468,"about_ca_topic_score_gemma":0.00001166136,"domain_scores_codex":[0.9991817,0.00002295715,0.0002850358,0.0001448562,0.00009980497,0.0002656276],"domain_scores_gemma":[0.9995469,0.00001589972,0.0001203398,0.0001729529,0.00004475226,0.00009919479],"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":[0.00002995076,0.00002382344,0.006500222,0.0000828062,0.00006331924,0.000001504406,0.000366842,0.0004817016,0.9757366,0.00004261511,0.00001824717,0.01665239],"study_design_scores_gemma":[0.00310776,0.0008054032,0.002950455,0.0001545257,0.00008825892,0.0001211362,0.0007926099,0.8401496,0.1445574,0.00006785169,0.006087629,0.001117336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836759,0.0002735183,0.01554777,0.00003155726,0.00008231293,0.0001064192,0.00002245477,0.00002224424,0.0002378366],"genre_scores_gemma":[0.9675518,0.0003569543,0.03170745,0.00008034097,0.00007727683,0.000002662322,0.00004618174,0.00002855121,0.0001488325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.839668,"threshold_uncertainty_score":0.5325742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009643948078409036,"score_gpt":0.2276355124034637,"score_spread":0.2179915643250547,"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."}}