{"id":"W6920956602","doi":"10.6084/m9.figshare.13364261","title":"Additional file 2 of Systematic evaluation of supervised machine learning for sample origin prediction using metagenomic sequencing data","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Sample (material); Metagenomics; Pattern recognition (psychology); Plot (graphics); Line (geometry); Supervised learning; Sample size determination","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007996073,0.00185006,0.001658627,0.003430822,0.001279254,0.002239046,0.003636141,0.001523905,0.7341912],"category_scores_gemma":[0.06796369,0.0009132983,0.002069228,0.004507913,0.0006062348,0.00209739,0.001719006,0.001457277,0.1295598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332131,"about_ca_system_score_gemma":0.003540642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005939932,"about_ca_topic_score_gemma":0.01527753,"domain_scores_codex":[0.9972156,0.0007527266,0.0004053329,0.0007193035,0.0006927446,0.0002141977],"domain_scores_gemma":[0.9280187,0.06021002,0.001763738,0.003964366,0.005151164,0.0008919259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008126175,0.0001792453,0.004739741,0.005930709,0.0002610039,0.0001578911,0.0001497048,0.001726431,0.0006190457,0.0009930595,0.9673657,0.01706484],"study_design_scores_gemma":[0.01345037,0.001027762,0.04782514,0.00533324,0.001066338,0.0009695066,0.0008133732,0.02437423,0.007070953,0.02012279,0.8774461,0.0005002665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0004381311,0.00002407293,0.001923606,0.00008742954,0.00004639975,0.0002068357,0.9938883,0.002814921,0.0005702737],"genre_scores_gemma":[0.01208458,0.0000995485,0.03262653,0.0005244664,0.0001206757,0.004203929,0.939269,0.005183048,0.005888227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7341912,"threshold_uncertainty_score":0.3791439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2748138855222503,"score_gpt":0.3383230787570075,"score_spread":0.06350919323475723,"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."}}