{"id":"W2969455443","doi":"10.2196/14667","title":"Developing a Reproducible Microbiome Data Analysis Pipeline Using the Amazon Web Services Cloud for a Cancer Research Group: Proof-of-Concept Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Nursing Research; Amazon Web Services","keywords":"Microbiome; Computer science; Cloud computing; Pipeline (software); Workflow; Data science; Database; Data mining; Operating system; Bioinformatics; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002913814,0.0001462119,0.0003312741,0.000150155,0.0001616356,0.00004300099,0.001066111,0.0001882073,0.0000447617],"category_scores_gemma":[0.00009421812,0.00009887385,0.00007559119,0.0007891007,0.0001336506,0.00001936566,0.0008648974,0.0002516487,0.000003010857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004283262,"about_ca_system_score_gemma":0.000742618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000242452,"about_ca_topic_score_gemma":0.001021816,"domain_scores_codex":[0.9979621,0.0001195378,0.0007380429,0.0003422912,0.000421867,0.0004162317],"domain_scores_gemma":[0.9978362,0.00005750295,0.0002656973,0.001410511,0.0003287144,0.0001013928],"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":[0.001715833,0.003770833,0.06219517,0.01600525,0.007088505,0.000008315278,0.08332842,0.001197986,0.7450025,0.0004271711,0.0373593,0.04190068],"study_design_scores_gemma":[0.01097229,0.003226313,0.003449669,0.001592694,0.001514061,0.00006333379,0.09910771,0.2823753,0.1475304,0.0001109301,0.4481392,0.001918096],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992811,0.0004494285,0.004083434,0.0004899824,0.0001820126,0.001778828,0.0001695344,0.00000820959,0.00002752576],"genre_scores_gemma":[0.9926357,0.00007661183,0.004994265,0.000691189,0.0003797607,0.00007964405,0.0009694276,0.00001885938,0.0001545035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5974722,"threshold_uncertainty_score":0.4031959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08900118521627388,"score_gpt":0.4351221958647004,"score_spread":0.3461210106484265,"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."}}