{"id":"W3112134181","doi":"10.1186/s13062-020-00287-y","title":"Systematic evaluation of supervised machine learning for sample origin prediction using metagenomic sequencing data","year":2020,"lang":"en","type":"article","venue":"Biology Direct","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Metagenomics; Lasso (programming language); Artificial intelligence; Regression; Machine learning; Biology; Sample (material); Shotgun sequencing; Multivariate statistics; Sample size determination; Computer science; Statistics; Data mining; DNA sequencing; Mathematics; Genetics","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":[0.001785014,0.00009057724,0.0002994381,0.00002134895,0.0001603445,0.000003306769,0.0003356957,0.00009457819,0.0008524823],"category_scores_gemma":[0.00130872,0.00008015676,0.00004041746,0.0001031032,0.00009879504,0.00008468467,0.0002446422,0.0001095869,0.00001733139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001218956,"about_ca_system_score_gemma":0.00003901204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000890611,"about_ca_topic_score_gemma":0.0002721737,"domain_scores_codex":[0.9980363,0.001244457,0.0002753776,0.000248003,0.00005243303,0.0001434801],"domain_scores_gemma":[0.9989519,0.0005513713,0.00016213,0.0002839727,0.00001895575,0.00003171901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006465006,0.00002182341,0.03282757,0.0005147243,0.0001233545,1.047467e-7,0.0006098752,0.02203006,0.9433717,0.00002672632,0.0001138657,0.0002955497],"study_design_scores_gemma":[0.0005285729,0.0002241669,0.001620756,0.0000530245,0.0003757435,0.000002553752,0.00009527963,0.9925968,0.003623293,0.0002843436,0.0004800515,0.0001153924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940661,0.000268475,0.004334065,0.00004523884,0.0001199095,0.0006969729,0.0002586896,0.00003299242,0.0001776182],"genre_scores_gemma":[0.9964442,0.00001363405,0.002450053,0.00009538959,0.00003278816,0.00001818239,0.0009330799,0.00000800247,0.000004718423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9705667,"threshold_uncertainty_score":0.9334084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2225167887248018,"score_gpt":0.3360370779095436,"score_spread":0.1135202891847418,"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."}}