{"id":"W4243426183","doi":"10.12688/f1000research.9471.2","title":"Whose sample is it anyway? Widespread misannotation of samples in transcriptomics studies","year":2016,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Sample (material); Annotation; Reliability (semiconductor); Confidence interval; Sample size determination; Statistics; Set (abstract data type); Reproducibility; Data set; Computer science; Biology; Bioinformatics; Mathematics","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":[0.0006044388,0.0002217486,0.0003259087,0.0002542295,0.00004762741,0.00002674582,0.0005108134,0.0003571287,0.0001006648],"category_scores_gemma":[0.0006577827,0.000190149,0.0001405208,0.000153146,0.0002234065,0.000005164399,0.0004149453,0.0002587853,0.000008783459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007488539,"about_ca_system_score_gemma":0.0003949935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001441893,"about_ca_topic_score_gemma":0.0001465951,"domain_scores_codex":[0.9979194,0.0002334866,0.0004767692,0.0006408315,0.0004121861,0.0003173447],"domain_scores_gemma":[0.9984226,0.0001328172,0.0001691122,0.0007501088,0.0004435572,0.0000818463],"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":[0.0002949648,0.00009509612,0.004797356,0.0003740577,0.0001081584,9.156245e-7,0.001227852,0.00004427572,0.931515,0.0001578789,0.05178493,0.009599473],"study_design_scores_gemma":[0.000876578,0.0001589232,0.006541974,0.0005876386,0.00001922569,8.914368e-7,0.001460615,0.00008125183,0.8993732,0.006572903,0.08400062,0.0003261626],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690307,0.01206569,0.00813954,0.006610859,0.0006611999,0.001130942,0.001142458,0.00002032491,0.001198277],"genre_scores_gemma":[0.9849579,0.01118619,0.0011124,0.0002122512,0.0002093949,0.000257236,0.0003841914,0.00004294412,0.001637439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0322157,"threshold_uncertainty_score":0.775405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1718735376716192,"score_gpt":0.4305569874046562,"score_spread":0.258683449733037,"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."}}