{"id":"W2890716356","doi":"10.1186/s12919-018-0121-1","title":"A deep neural network based regression model for triglyceride concentrations prediction using epigenome-wide DNA methylation profiles","year":2018,"lang":"en","type":"article","venue":"BMC Proceedings","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"George & Fay Yee Centre for Healthcare Innovation; University of Manitoba","funders":"National Institute of General Medical Sciences; Manitoba Health Research Council; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Research Manitoba; National Heart, Lung, and Blood Institute","keywords":"dNaM; DNA methylation; Epigenetics; Epigenome; Triglyceride; Regression; Support vector machine; Methylation; Medicine; Computational biology; Artificial intelligence; Bioinformatics; Machine learning; Biology; Internal medicine; Computer science; Genetics; Statistics; Cholesterol; DNA; Gene; Gene expression; Mathematics","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":[0.0004137129,0.0001945411,0.0001543089,0.00005693151,0.0003854133,0.00007402393,0.000126523,0.0002077986,0.00000647463],"category_scores_gemma":[0.0002900064,0.0001831297,0.0001068554,0.000167129,0.00008592181,0.00002392091,0.00004219457,0.00006212944,0.000001195169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004488802,"about_ca_system_score_gemma":0.0001267021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003653395,"about_ca_topic_score_gemma":0.00001814014,"domain_scores_codex":[0.9986627,0.00002105985,0.0003501845,0.0004401699,0.0001744912,0.0003514196],"domain_scores_gemma":[0.9989949,0.00002911205,0.0002455757,0.0001393358,0.000494506,0.00009653925],"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":[0.0004031703,0.00003949939,0.03451996,0.00006182713,0.00001932038,5.331348e-8,0.0001423466,0.05173483,0.911714,0.0001959813,0.0003356134,0.0008334119],"study_design_scores_gemma":[0.0005580088,0.0002434809,0.002157363,0.00002263821,0.00004189092,3.434851e-7,0.00002675129,0.7169459,0.2783009,0.0007242052,0.0008257434,0.0001528023],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5311902,0.0003061967,0.4676172,0.00004068633,0.0001489793,0.0005255195,0.00001514632,0.00002709714,0.0001289141],"genre_scores_gemma":[0.9327329,0.00002345307,0.06547799,0.0001087694,0.001142916,0.0001130643,0.0002532519,0.00003910751,0.0001085862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.665211,"threshold_uncertainty_score":0.7467812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03973634621849528,"score_gpt":0.2927621155865253,"score_spread":0.2530257693680301,"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."}}