{"id":"W2790370540","doi":"10.3389/fgene.2018.00083","title":"Adjusting for Batch Effects in DNA Methylation Microarray Data, a Lesson Learned","year":2018,"lang":"en","type":"article","venue":"Frontiers in Genetics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research; BC Children's Hospital","keywords":"Computer science; DNA methylation; Confounding; Sample (material); Sample size determination; Process (computing); Computational biology; Data mining; Biology; Statistics; Genetics; Mathematics; Gene; Chemistry; Chromatography","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":[0.0003388308,0.0001204399,0.000137071,0.0001075633,0.00004910878,0.00001917225,0.0003101168,0.0001806095,0.000002850892],"category_scores_gemma":[0.0001718591,0.0001293785,0.00002838218,0.0001691176,0.00005871473,0.000005039617,0.0001053465,0.00007114871,0.000002030808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003413024,"about_ca_system_score_gemma":0.00007450028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008317656,"about_ca_topic_score_gemma":0.00009995141,"domain_scores_codex":[0.998889,0.00008663273,0.0002245192,0.0004747113,0.00008886783,0.000236277],"domain_scores_gemma":[0.9992539,0.00001372636,0.00009062991,0.0005365064,0.00006206067,0.00004311984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001334193,0.00004191955,0.01657283,0.00004986525,0.00001261711,3.774995e-7,0.0001967527,0.0001290893,0.8659991,0.000007486804,0.02555816,0.09129839],"study_design_scores_gemma":[0.001666126,0.0002681283,0.01872949,0.00005732806,0.00002027157,9.254145e-7,0.0003481546,0.01250316,0.821749,0.0004689499,0.1439117,0.0002767167],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6660491,0.003699261,0.3276117,0.0002589379,0.001392079,0.0006161251,0.00002251622,0.00001125697,0.0003389528],"genre_scores_gemma":[0.9243826,0.0003869673,0.07366918,0.0001673518,0.0004440322,0.00007161289,0.0003727698,0.0000296486,0.0004758085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2583335,"threshold_uncertainty_score":0.52759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03346328224768329,"score_gpt":0.3161218921411407,"score_spread":0.2826586098934574,"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."}}