{"id":"W2975619549","doi":"10.1093/gigascience/giz107","title":"A field guide for the compositional analysis of any-omics data","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":369,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Normalization (sociology); Compositional data; Computer science; Extant taxon; Data mining; Sample size determination; Computational biology; Data set; Field (mathematics); Bioinformatics; Statistics; Biology; Mathematics; Artificial intelligence; Machine learning; Evolutionary 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":[0.0006430928,0.00004923733,0.0001054433,0.0000419291,0.0000985779,0.00004792129,0.002714193,0.00002312096,0.00003465763],"category_scores_gemma":[0.0001898398,0.00003405938,0.00005693161,0.0007217675,0.00006455126,0.0002122852,0.000596902,0.00004269243,0.000004852576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000544275,"about_ca_system_score_gemma":0.00006495335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961841,"about_ca_topic_score_gemma":0.000005712841,"domain_scores_codex":[0.9992049,0.00001090246,0.0001438711,0.0003084645,0.0001850715,0.0001467483],"domain_scores_gemma":[0.9980963,0.0005600291,0.0000821392,0.001135157,0.0001010432,0.00002532154],"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":[0.0000634495,0.0003055972,0.07419118,0.0001658721,0.0009735666,0.000006582794,0.002015419,0.08565492,0.2709541,0.4751092,0.05082994,0.03973012],"study_design_scores_gemma":[0.00008043314,0.00004006162,0.008585357,0.000005268243,0.00004458241,0.000003171794,0.00003594771,0.9559097,0.007485098,0.00152471,0.02621639,0.00006933065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02067662,0.00005789802,0.9656833,0.007833241,0.0001916598,0.000144728,0.00003485868,0.00002110018,0.005356584],"genre_scores_gemma":[0.9668074,0.000004199375,0.0313688,0.0008332946,0.00001771362,0.000005000067,0.00001900516,4.880532e-7,0.0009440963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9461308,"threshold_uncertainty_score":0.5043691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03295175102729838,"score_gpt":0.2817874691237989,"score_spread":0.2488357180965005,"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."}}