{"id":"W4393577040","doi":"10.1101/2024.04.01.587602","title":"Beyond Normalization: Incorporating Scale Uncertainty in Microbiome and Gene Expression Analysis","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"National Institutes of Health","keywords":"False positive paradox; Normalization (sociology); Computer science; False positives and false negatives; Scale (ratio); Context (archaeology); Sample (material); False discovery rate; Statistics; Data mining; Artificial intelligence; Machine learning; Mathematics; Biology","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":[0.0004021775,0.0003809571,0.0003780555,0.0005146155,0.0000979468,0.0001787768,0.0002860736,0.0005678031,0.0000147],"category_scores_gemma":[0.00003853037,0.000392515,0.0001368639,0.0009446473,0.00009809546,0.000008501753,0.0008485204,0.0003551991,0.000007233395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009472595,"about_ca_system_score_gemma":0.0003103785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004475561,"about_ca_topic_score_gemma":0.00002766917,"domain_scores_codex":[0.9977612,0.0001319939,0.0004883867,0.001139192,0.0001945618,0.0002846513],"domain_scores_gemma":[0.9984663,0.000007853329,0.0002939906,0.000866078,0.0002095497,0.0001562084],"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":[0.00002673321,0.00004510897,0.01588743,0.0001591225,0.0001189319,0.000006624192,0.00001214162,0.001375954,0.9819314,0.00003978203,0.0003940142,0.000002739093],"study_design_scores_gemma":[0.0003102226,0.00002916077,0.02699009,0.000194501,0.0002004134,1.900778e-8,0.000009249688,0.001256676,0.9691371,0.00001183738,0.001332646,0.0005281352],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924935,0.003794683,0.002522176,0.0001428589,0.0004481862,0.0003437579,0.0001724451,0.00006242679,0.00001997732],"genre_scores_gemma":[0.9951822,0.0004227745,0.003642353,0.0001386049,0.0003587027,0.0001578778,0.00001594472,0.0000638692,0.000017635],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01279437,"threshold_uncertainty_score":0.9998527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007420996002226026,"score_gpt":0.2225939207479362,"score_spread":0.2151729247457101,"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."}}