{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.01425123,0.0009810765,0.0009429762,0.0006722134,0.0009555134,0.001815159,0.002281177,0.001251059,0.004272267],"category_scores_gemma":[0.01099896,0.0006969317,0.00126656,0.0005615553,0.0008927389,0.001633529,0.002591037,0.001865884,0.001893753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008438,"about_ca_system_score_gemma":0.004827838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008435,"about_ca_topic_score_gemma":0.002082286,"domain_scores_codex":[0.99243,0.001688836,0.0004111597,0.0009408597,0.003616893,0.0009122743],"domain_scores_gemma":[0.9899427,0.00192761,0.0007701886,0.001594707,0.004394794,0.001370007],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004282135,0.005093043,0.01672397,0.002235966,0.0005993638,0.002338818,0.001117464,0.02258814,0.7304227,0.008518023,0.03234575,0.1737348],"study_design_scores_gemma":[0.002281367,0.0140079,0.01156228,0.0002574265,0.0002968501,0.001727725,0.0005418893,0.1300878,0.7508548,0.002650581,0.08544891,0.0002825675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3390481,0.0009844917,0.6209305,0.002985157,0.001195224,0.01507774,0.004024798,0.009433272,0.006320819],"genre_scores_gemma":[0.3975611,0.0007078388,0.5821223,0.001242072,0.0001361558,0.009918432,0.00410832,0.0008765519,0.003327271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9977188,"threshold_uncertainty_score":0.07536864,"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."}}