{"id":"W6939313971","doi":"10.6084/m9.figshare.13364258.v1","title":"Additional file 1 of Systematic evaluation of supervised machine learning for sample origin prediction using metagenomic sequencing data","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Metagenomics; Sample (material); Supervised learning; Training set; DNA sequencing; Support vector machine","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006359622,0.001744854,0.00144306,0.003761624,0.001413517,0.002052508,0.003240129,0.00143005,0.7214012],"category_scores_gemma":[0.05543631,0.0007895672,0.001850149,0.005626588,0.0006106639,0.002262064,0.001791209,0.001487486,0.1273281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386842,"about_ca_system_score_gemma":0.003151976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007336962,"about_ca_topic_score_gemma":0.01968084,"domain_scores_codex":[0.9978755,0.0005642581,0.0003203984,0.0006499583,0.0004227214,0.000167274],"domain_scores_gemma":[0.9397923,0.05111651,0.001534312,0.003132815,0.003698949,0.0007250612],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006175918,0.0001378359,0.004127975,0.006465995,0.0001916066,0.00009649287,0.0001221597,0.001371937,0.0003852661,0.0008599873,0.9741743,0.01144884],"study_design_scores_gemma":[0.01401457,0.0009408431,0.05132913,0.00675483,0.001265796,0.0008510139,0.00112306,0.01705972,0.004875218,0.02038928,0.8809911,0.0004053783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0002914677,0.00002031586,0.0007612648,0.00005291489,0.00002276199,0.0001027602,0.9973864,0.0009916476,0.0003703597],"genre_scores_gemma":[0.007291749,0.00008963207,0.01449524,0.0003062531,0.00005962333,0.002293471,0.9708755,0.001581089,0.003007465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9936404,"threshold_uncertainty_score":0.3973873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3118360200365737,"score_gpt":0.2968742833006444,"score_spread":0.01496173673592927,"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."}}