{"id":"W4304783041","doi":"10.3389/fmicb.2022.1018237","title":"Development of a data science CURE in microbiology using publicly available microbiome datasets","year":2022,"lang":"en","type":"article","venue":"Frontiers in Microbiology","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"University of British Columbia","keywords":"Undergraduate research; Big data; Data science; Microbiome; Computer science; Dissemination; Medical education; Biology; Bioinformatics; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002573085,0.0002289891,0.0004061466,0.0007858247,0.000212966,0.00002248337,0.002510476,0.0002183845,0.0001251523],"category_scores_gemma":[0.000165076,0.0002316699,0.00004110837,0.0008915098,0.001217812,0.00002955735,0.004323334,0.0003632252,0.00001172278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002167505,"about_ca_system_score_gemma":0.001669459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009326712,"about_ca_topic_score_gemma":0.000283081,"domain_scores_codex":[0.9970406,0.0001968284,0.0008199192,0.0009045536,0.0001248864,0.0009132723],"domain_scores_gemma":[0.9984891,0.00001535608,0.0002214184,0.001079174,0.00008498458,0.0001099875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001087087,0.0001930066,0.005963214,0.00004812328,0.00003131289,0.000006424769,0.0001749165,0.00002012276,0.9569437,0.000003183902,0.03428794,0.002219354],"study_design_scores_gemma":[0.001392461,0.0002142122,0.000210232,0.00002237377,0.000008146735,0.0001576397,0.001095943,0.0006887756,0.2642752,0.00001392451,0.7315335,0.0003875887],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990559,0.002126687,0.002095636,0.0001483233,0.001034078,0.0005123619,0.003364592,0.000007815524,0.0001514623],"genre_scores_gemma":[0.5055166,0.0006884008,0.4567847,0.0008867673,0.0001369768,0.00006445232,0.0353789,0.00006449323,0.00047871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6972456,"threshold_uncertainty_score":0.9447225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03681867717887056,"score_gpt":0.2968595048081784,"score_spread":0.2600408276293078,"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."}}