{"id":"W2951901532","doi":"10.1186/s12859-018-2187-1","title":"Genome-wide prediction of cis-regulatory regions using supervised deep learning methods","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":129,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; BC Children's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Michael Smith Health Research BC; Genome British Columbia; National Institute of General Medical Sciences; Western Canada Research Grid; Compute Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Genome; ENCODE; Human genome; Computational biology; Genomics; Biology; Genome project; Enhancer; Regulatory sequence; DNA sequencing; Functional genomics; Gene Annotation; Noncoding DNA; DNA microarray; Deep learning; Gene; Genetics; Regulation of gene expression; Computer science; Artificial intelligence; Transcription factor; Gene expression","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004069051,0.0001546589,0.0001777961,0.00007950501,0.0001562457,0.00002287269,0.0001999811,0.0001916393,0.00002139282],"category_scores_gemma":[0.0001213433,0.0001550302,0.0001145607,0.0001098576,0.000172775,0.00001058452,0.0001529439,0.00008947474,0.00000879396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003015329,"about_ca_system_score_gemma":0.0001064446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004979079,"about_ca_topic_score_gemma":0.0000138223,"domain_scores_codex":[0.9989488,0.00006824246,0.0004864079,0.0001428087,0.0001231735,0.0002305599],"domain_scores_gemma":[0.9990466,0.00002399071,0.0002576977,0.0004116657,0.0001817809,0.00007824363],"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":[0.0001200665,0.0001147275,0.03135775,0.0005568459,0.000244726,4.879359e-7,0.002596337,0.01938983,0.9378222,0.0004062867,0.0001818604,0.007208935],"study_design_scores_gemma":[0.0005919801,0.0004310105,0.01812095,0.00002653113,0.00007002051,0.00002510071,0.001220392,0.9433293,0.03067315,0.0001546836,0.005097614,0.0002592387],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.503708,0.0001094069,0.495127,0.000003561549,0.0001101213,0.0001045826,0.00001206153,0.00001383971,0.0008114296],"genre_scores_gemma":[0.4338661,0.0000743429,0.56552,0.00005388251,0.0001630405,0.000003908775,0.0001755134,0.00002568727,0.0001174181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9239395,"threshold_uncertainty_score":0.6321949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.021935659757517,"score_gpt":0.2688406461527417,"score_spread":0.2469049863952247,"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."}}