{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001885102,0.00009593955,0.0001041708,0.00007223312,0.00009699317,0.00003008945,0.0001186575,0.0001160883,0.0000142875],"category_scores_gemma":[0.00002106426,0.00009376661,0.00005201156,0.0002497673,0.00003423288,0.000002372208,0.00002439378,0.0000398678,0.0003454687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002078815,"about_ca_system_score_gemma":0.00008068192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008562356,"about_ca_topic_score_gemma":0.00005303277,"domain_scores_codex":[0.999137,0.00007195523,0.0002025798,0.0003096388,0.00007383037,0.0002049479],"domain_scores_gemma":[0.9994674,0.000009263456,0.00009730132,0.0003148233,0.00006155527,0.00004971218],"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":[0.00002163695,0.00001650505,0.002272849,0.00005484714,0.00001110755,9.826687e-7,0.00004003485,0.00001702462,0.9893398,0.00001967863,0.007953697,0.0002518763],"study_design_scores_gemma":[0.0003480724,0.00008427849,0.03058072,0.00002124151,0.000007875427,0.000003897275,0.0001231755,0.0002453011,0.9160924,0.000005072494,0.05234451,0.000143483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972534,0.0002679258,0.0006647123,0.0003625328,0.000515859,0.0002711317,0.00004780961,0.00005733836,0.0005592656],"genre_scores_gemma":[0.996141,0.0000540268,0.000158303,0.0001442833,0.0003163838,0.00003749336,0.001527711,0.00001885756,0.00160196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07324739,"threshold_uncertainty_score":0.4440417,"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."}}