{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003119326,0.00179897,0.00116907,0.001090132,0.0006729839,0.001045053,0.001938126,0.001357145,0.00254217],"category_scores_gemma":[0.008586866,0.000694462,0.001703149,0.0009996106,0.001019794,0.002277835,0.002541934,0.002798919,0.001119465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005933077,"about_ca_system_score_gemma":0.001159028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003006869,"about_ca_topic_score_gemma":0.004445718,"domain_scores_codex":[0.9988637,0.0004632686,0.00004455366,0.0003916051,0.0001650864,0.00007183951],"domain_scores_gemma":[0.9966244,0.002232321,0.0002499008,0.0004883882,0.000271739,0.0001333727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001624376,0.0006575346,0.0337336,0.0006025501,0.000562369,0.0003823721,0.0005135005,0.4718584,0.03571175,0.00597952,0.01478563,0.4335884],"study_design_scores_gemma":[0.00004157868,0.00009272244,0.001074696,0.00001791496,0.00003455153,0.00006064149,0.00002400618,0.9873455,0.004928168,0.004350599,0.002008034,0.00002158302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1193644,0.001763002,0.855571,0.001060655,0.0001905378,0.0001732114,0.002581035,0.01756473,0.001731434],"genre_scores_gemma":[0.4205316,0.0005306105,0.5650623,0.001120433,0.0001869395,0.0004703166,0.008542538,0.0008465089,0.002708707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003119326,"threshold_uncertainty_score":0.01649672,"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."}}