{"id":"W4409886452","doi":"10.1093/bioinformatics/btaf269","title":"PICRUSt2-SC: an update to the reference database used for functional prediction within PICRUSt2","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Database; Computer science; Source code; Code (set theory); Process (computing); Genome; Information retrieval; Set (abstract data type); Programming language; Biology","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":[0.004341065,0.003891847,0.002619522,0.004674602,0.001866089,0.004966551,0.005914381,0.002310663,0.01988776],"category_scores_gemma":[0.01038827,0.002149283,0.00303379,0.005829804,0.0007660479,0.004171262,0.003599813,0.004307148,0.02965902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001276647,"about_ca_system_score_gemma":0.003293687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003752118,"about_ca_topic_score_gemma":0.003448869,"domain_scores_codex":[0.9972476,0.0002956551,0.0004086547,0.0007039478,0.001042333,0.0003016249],"domain_scores_gemma":[0.9955088,0.0009679694,0.0006035315,0.0009917093,0.00127425,0.0006537412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005668045,0.0004179834,0.0130976,0.006811248,0.0008062106,0.001572505,0.0009689431,0.004924497,0.08975204,0.009147656,0.7216094,0.1452239],"study_design_scores_gemma":[0.0005498394,0.0005000227,0.01198315,0.0006433747,0.0005424583,0.002442502,0.0002127974,0.01704302,0.05215144,0.005568441,0.9079081,0.0004548454],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.06412566,0.008881992,0.1548486,0.001983727,0.003198675,0.0006277594,0.4342625,0.3033862,0.02868477],"genre_scores_gemma":[0.02146214,0.001324217,0.07651686,0.000595607,0.0002159884,0.0004817061,0.8721174,0.02344938,0.003836751],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01988776,"threshold_uncertainty_score":0.06653124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02756884682379836,"score_gpt":0.2633363834784288,"score_spread":0.2357675366546304,"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."}}