{"id":"W4406292104","doi":"10.1093/bioinformatics/btaf014","title":"PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microbiome; Computer science; Trait; Sample (material); Set (abstract data type); Machine learning; Phylogenetic tree; Raw data; Artificial intelligence; Phylogenetics; Data mining; Biology; Bioinformatics","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":[0.0002861893,0.0001457738,0.0001377619,0.00007532397,0.0001940544,0.00005761036,0.0001142345,0.0002309448,0.00001452963],"category_scores_gemma":[0.00006996991,0.0001522509,0.00008134632,0.0001890014,0.00002159703,0.00002188352,0.00006480094,0.00009854532,0.00003091389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001844026,"about_ca_system_score_gemma":0.0001576423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000219211,"about_ca_topic_score_gemma":0.00004129296,"domain_scores_codex":[0.9989616,0.00003235594,0.0004587971,0.0001594912,0.0001034402,0.000284264],"domain_scores_gemma":[0.9994039,0.00001499519,0.0002350067,0.000200839,0.0001108345,0.00003445294],"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":[0.00002155855,0.00003632266,0.001730909,0.0001880448,0.00007355987,1.23966e-7,0.0005095596,0.00003280192,0.9789893,0.0001469417,0.01655369,0.001717191],"study_design_scores_gemma":[0.002140046,0.0002520961,0.02663128,0.0001956994,0.0001116286,0.000009430784,0.001374883,0.001302846,0.836987,0.000206283,0.1303607,0.0004280549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8720597,0.0004564695,0.1107041,0.0004569458,0.001568909,0.0007628845,0.0002639225,0.00009787812,0.01362916],"genre_scores_gemma":[0.9625306,0.0003981598,0.02814844,0.002728866,0.0003502375,0.0000329073,0.001676874,0.00002533155,0.00410863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1420023,"threshold_uncertainty_score":0.620861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006999816828427663,"score_gpt":0.259212224529735,"score_spread":0.2522124077013073,"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."}}