{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004691932,0.001926492,0.001305932,0.001196254,0.0008744076,0.001473474,0.003001553,0.001866415,0.002188374],"category_scores_gemma":[0.01236125,0.0009272662,0.001443225,0.00100394,0.001663446,0.001669596,0.001349352,0.002010511,0.001528344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001934489,"about_ca_system_score_gemma":0.001921776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004696876,"about_ca_topic_score_gemma":0.006951138,"domain_scores_codex":[0.9978119,0.0006752771,0.00008760067,0.0009341554,0.0003513878,0.0001398383],"domain_scores_gemma":[0.9926278,0.004652947,0.0005252648,0.001054093,0.0009062995,0.0002336541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007840553,0.0005062353,0.01269967,0.0006972728,0.0002819154,0.0001027569,0.0001891824,0.7090918,0.05111833,0.004662102,0.01196132,0.2079054],"study_design_scores_gemma":[0.00004011315,0.00004703148,0.0010275,0.00001378569,0.00001794088,0.00002176393,0.00002046612,0.9780542,0.01406312,0.006004483,0.000668406,0.00002118353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08150484,0.0003225815,0.8980415,0.0002984065,0.00006839279,0.0001914211,0.00159175,0.0165993,0.001381657],"genre_scores_gemma":[0.2783922,0.0001165961,0.7125394,0.0003910659,0.00004970048,0.0005474219,0.004930894,0.001699483,0.001333235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004696876,"threshold_uncertainty_score":0.02481359,"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."}}