{"id":"W2509088678","doi":"10.1101/064626","title":"Whose sample is it anyway? Widespread misannotation of samples in transcriptomics studies","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Sample (material); Reliability (semiconductor); Annotation; Set (abstract data type); Computer science; Confidence interval; Data set; Sample size determination; Statistics; Reproducibility; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003789939,0.0003703884,0.0004500606,0.0002068075,0.00005444182,0.00003436142,0.0003972419,0.0004715817,0.00002216697],"category_scores_gemma":[0.0004207864,0.000352246,0.0001527371,0.0002093489,0.0001515771,0.00001120882,0.0001922581,0.0001972192,0.00000527974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001016004,"about_ca_system_score_gemma":0.0004049161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003895874,"about_ca_topic_score_gemma":0.00001444855,"domain_scores_codex":[0.9978884,0.0001313108,0.0006091309,0.0008268844,0.0002360585,0.000308258],"domain_scores_gemma":[0.9979429,0.00005418406,0.0004344039,0.0009777268,0.0004896542,0.0001010859],"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":[0.00009234889,0.00008290536,0.006128431,0.000281655,0.0001220503,0.000001065062,0.00007262787,0.00001879034,0.9898601,0.0001349898,0.003188489,0.00001658566],"study_design_scores_gemma":[0.0006249871,0.00006052747,0.01946948,0.0005506246,0.00004540867,4.951321e-9,0.00004848032,0.00002144704,0.9585577,0.00002393032,0.020191,0.0004064093],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984928,0.005405665,0.006717174,0.0009046907,0.0008010008,0.0004990944,0.0007021606,0.00003264597,0.000009607645],"genre_scores_gemma":[0.9923856,0.004063837,0.002718862,0.0003392059,0.0002278596,0.0001848016,0.000002862342,0.00006290613,0.00001409242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03130237,"threshold_uncertainty_score":0.999893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04184005282366721,"score_gpt":0.286059165772216,"score_spread":0.2442191129485488,"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."}}