{"id":"W2512452276","doi":"10.1093/bioinformatics/btw538","title":"BatchQC: interactive software for evaluating sample and batch effects in genomic data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Institute of Cancer Research; University of Toronto; University Health Network","funders":"National Institutes of Health","keywords":"Bioconductor; Computer science; Pipeline (software); Software; Data mining; A priori and a posteriori; Sample (material); Batch processing; Data science; Operating system","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002290114,0.00008153132,0.00008494366,0.00003669301,0.00003779431,0.00001995154,0.0001801747,0.00006848959,0.000003967655],"category_scores_gemma":[0.0009531155,0.00006030645,0.00001547457,0.00004139764,0.000025138,0.00001747721,0.0002067226,0.00002610757,0.000004227122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002036475,"about_ca_system_score_gemma":0.00006993184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005404174,"about_ca_topic_score_gemma":0.00001670893,"domain_scores_codex":[0.9994242,0.00002135631,0.0001923457,0.0001667437,0.000063297,0.0001321001],"domain_scores_gemma":[0.9992943,0.0001303129,0.00009672223,0.0003857213,0.00005261919,0.00004031242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001664358,0.00002299509,0.00660362,0.0001843905,0.00002798065,1.250236e-7,0.0003718481,0.00000694234,0.4727378,0.00006223859,0.005051102,0.5147645],"study_design_scores_gemma":[0.01947877,0.002977969,0.1298711,0.001340939,0.0001718941,0.00003558019,0.00259057,0.1047688,0.4640916,0.004920696,0.267496,0.002256081],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4966349,0.0002551675,0.5017316,0.0002348328,0.0002168375,0.0005897471,0.0002228459,0.00001459868,0.00009953421],"genre_scores_gemma":[0.8641968,0.0001905269,0.1344381,0.0003267222,0.0001103953,0.0001007747,0.0004732331,0.00001931051,0.0001441293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5125084,"threshold_uncertainty_score":0.2459226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04013611400870473,"score_gpt":0.3309031692002055,"score_spread":0.2907670551915008,"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."}}