{"id":"W4327569177","doi":"10.1038/s41587-023-01696-w","title":"Contamination source modeling with SCRuB improves cancer phenotype prediction from microbiome data","year":2023,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute; Canadian Institute for Advanced Research; U.S. Department of Health and Human Services","keywords":"Microbiome; Contamination; In silico; Robustness (evolution); Computer science; Computational biology; Biology; Bioinformatics; Ecology; Genetics; Gene","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0001214782,0.000166172,0.0001548628,0.0001476039,0.0001175604,0.00001784046,0.0004518273,0.001380783,0.000009250609],"category_scores_gemma":[0.00004416901,0.0001445826,0.00002327245,0.0003232097,0.00009110441,0.000008771099,0.000321006,0.0004849973,0.0000193832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003407125,"about_ca_system_score_gemma":0.0001233629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002691336,"about_ca_topic_score_gemma":0.000655024,"domain_scores_codex":[0.9987561,0.00002319886,0.0001644598,0.0006703881,0.00007911072,0.0003067506],"domain_scores_gemma":[0.9990265,0.000007234353,0.00008262073,0.0007618852,0.00008163493,0.0000401279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009187621,0.00001995508,0.0002467166,0.00001680057,0.00006287887,0.000001732602,0.00002225674,0.0001000484,0.9860239,0.00006903756,0.004260027,0.009084774],"study_design_scores_gemma":[0.002498796,0.0005786895,0.007410367,0.0001176733,0.0001416938,0.00003011201,0.0004020219,0.03654164,0.6695461,0.0001696829,0.2818711,0.0006921572],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9828988,0.002987821,0.009501034,0.00295456,0.0004106559,0.0002603535,0.0007208015,0.000235317,0.0000306999],"genre_scores_gemma":[0.9915795,0.001089981,0.001123637,0.0004672471,0.0003218438,0.00001615575,0.005085655,0.00003621417,0.0002797494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3164778,"threshold_uncertainty_score":0.9999157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01241199143986364,"score_gpt":0.2707195113540372,"score_spread":0.2583075199141735,"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."}}