{"id":"W4383186706","doi":"10.1128/msystems.00531-23","title":"Gene-based microbiome representation enhances host phenotype classification","year":2023,"lang":"en","type":"article","venue":"mSystems","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact; Institut universitaire de cardiologie et de pneumologie de Québec; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Australian Government; Canada Excellence Research Chairs, Government of Canada; Government of Canada; Compute Canada; Université Laval","keywords":"Metagenomics; Microbiome; Computational biology; Biology; Human Microbiome Project; Identification (biology); Host (biology); Representation (politics); Machine learning; Computer science; Artificial intelligence; Human microbiome; Gene; Bioinformatics; Genetics; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006612146,0.0004960002,0.0004992494,0.001355717,0.0001660465,0.0007997497,0.0003246728,0.0005143326,0.0008813462],"category_scores_gemma":[0.00217143,0.00008946606,0.0004784386,0.001143179,0.0002624649,0.0006699855,0.0006187488,0.0004788152,0.0004204976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003023375,"about_ca_system_score_gemma":0.0002964443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001037513,"about_ca_topic_score_gemma":0.0008580625,"domain_scores_codex":[0.9995878,0.0001363707,0.00002223814,0.0001289901,0.00007075386,0.00005374879],"domain_scores_gemma":[0.9992014,0.0003560703,0.0001305577,0.0001134641,0.0001524841,0.00004606011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003005845,0.0012157,0.1552984,0.0005603026,0.0004550074,0.0004571238,0.000243377,0.1364424,0.1907967,0.002604103,0.006420508,0.5025005],"study_design_scores_gemma":[0.00003317149,0.0004180869,0.05513878,0.00005433138,0.0001404048,0.0002683584,0.0001582211,0.9045241,0.03192122,0.004653538,0.002635534,0.00005430345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9172196,0.001083075,0.07607307,0.0003540429,0.00008976911,0.000045945,0.00243545,0.001199234,0.001499789],"genre_scores_gemma":[0.9754087,0.0001795482,0.02151983,0.00005948359,0.0000274089,0.00001958915,0.002395825,0.0000328441,0.0003567137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001355717,"threshold_uncertainty_score":0.003496826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03297279643678541,"score_gpt":0.3075070970252788,"score_spread":0.2745343005884934,"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."}}