{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04320988,0.001170753,0.002482615,0.00246491,0.001799166,0.005470361,0.003473659,0.003153156,0.0008034165],"category_scores_gemma":[0.1909682,0.001350719,0.001688283,0.003339542,0.004953144,0.007097504,0.003579403,0.004745583,0.0004758046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001518635,"about_ca_system_score_gemma":0.002170865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002017398,"about_ca_topic_score_gemma":0.002906851,"domain_scores_codex":[0.9728768,0.01630462,0.001738725,0.003550443,0.005083235,0.0004462162],"domain_scores_gemma":[0.8677372,0.1043325,0.007145855,0.01643354,0.003768977,0.0005817791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006541281,0.0001643895,0.04867861,0.002469369,0.001558306,0.001580696,0.002561937,0.2051254,0.02530523,0.3803885,0.007314892,0.3241985],"study_design_scores_gemma":[0.00003182719,0.0001011232,0.008042703,0.0002862718,0.0001322117,0.0005510839,0.0002819825,0.230495,0.01087951,0.7372332,0.01183073,0.000134316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01089052,0.0007358823,0.98626,0.0009165767,0.0000909746,0.00004783206,0.0001877216,0.0003021477,0.0005682303],"genre_scores_gemma":[0.3428682,0.001715219,0.6500382,0.002064229,0.0005092667,0.0004903849,0.0009021696,0.0004263344,0.0009860386],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04320988,"threshold_uncertainty_score":0.2285184,"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."}}