{"id":"W2487801161","doi":"10.17713/ajs.v45i4.122","title":"Compositional uncertainty should not be ignored in high-throughput sequencing data analysis","year":2016,"lang":"en","type":"article","venue":"Austrian Journal of Statistics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Throughput; Compositional data; Data mining; Bayesian probability; Selection (genetic algorithm); False discovery rate; Sampling (signal processing); Machine learning; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.001087473,0.0001358248,0.0003551353,0.0001963515,0.00007247231,0.00007655301,0.001349999,0.00007536385,0.0001271894],"category_scores_gemma":[0.0007625225,0.00009737505,0.00005654011,0.0006071522,0.00009387146,0.0004511079,0.0002962206,0.0002286225,0.000004435018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001679023,"about_ca_system_score_gemma":0.0003165531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001326486,"about_ca_topic_score_gemma":0.00009883908,"domain_scores_codex":[0.9981492,0.0001245609,0.000671747,0.0002926045,0.0004919865,0.0002699235],"domain_scores_gemma":[0.9978054,0.0006271934,0.0004983008,0.0006104733,0.000328626,0.0001299908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004278148,0.0006417167,0.04135925,0.0001746928,0.003740663,0.008300626,0.002495808,0.1396991,0.0601003,0.4878456,0.1025238,0.1526905],"study_design_scores_gemma":[0.0196423,0.00174627,0.1637799,0.001393204,0.002623222,0.002139467,0.00226305,0.38182,0.02373715,0.3601907,0.03721434,0.003450423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01737791,0.00001466367,0.9678634,0.01380594,0.0002008514,0.00004156721,0.0005823165,0.00001098071,0.0001024228],"genre_scores_gemma":[0.8265391,0.0000182589,0.1729547,0.0002458092,0.000103561,5.077012e-7,0.00005060184,0.000001981437,0.00008550133],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8091612,"threshold_uncertainty_score":0.3970839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1261449559398285,"score_gpt":0.3089215916465224,"score_spread":0.1827766357066939,"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."}}