{"id":"W4377013047","doi":"10.1186/s13059-023-02958-1","title":"SPUMONI 2: improved classification using a pangenome index of minimizer digests","year":2023,"lang":"en","type":"article","venue":"Genome biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Division of Biological Infrastructure; National Human Genome Research Institute; Office of Advanced Cyberinfrastructure; Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University; National Science Foundation","keywords":"Metagenomics; Biology; Sequence (biology); Biological classification; Computational biology; Class (philosophy); Genomics; Artificial intelligence; Pattern recognition (psychology); Computer science; Genetics; Evolutionary biology; Gene; Genome","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":[0.001265549,0.001360771,0.0009782321,0.002365275,0.0005161869,0.001619495,0.0009754703,0.0007256375,0.00197389],"category_scores_gemma":[0.003800766,0.0004546818,0.0005326361,0.001507623,0.000200825,0.001356723,0.001024801,0.0006507662,0.0009831515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005791332,"about_ca_system_score_gemma":0.0007476762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002781851,"about_ca_topic_score_gemma":0.006855686,"domain_scores_codex":[0.9992895,0.0001237179,0.0000534418,0.0002224691,0.0002406764,0.0000701118],"domain_scores_gemma":[0.9987621,0.0004101593,0.0001184304,0.0002310221,0.0003795784,0.00009864634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001612353,0.0003452853,0.0436439,0.0003807533,0.0002742585,0.0002896337,0.0002931892,0.03064661,0.2950561,0.002060235,0.01090016,0.6144975],"study_design_scores_gemma":[0.00005768579,0.0002827747,0.01990338,0.00001735746,0.00005375897,0.000350584,0.0001225414,0.8553302,0.1151115,0.001430749,0.007263219,0.00007628458],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4738439,0.0005414934,0.4998768,0.0003172485,0.0001192029,0.0001900561,0.002630321,0.01906635,0.003414582],"genre_scores_gemma":[0.4538033,0.0001532664,0.5313615,0.0001223532,0.00005270247,0.0001628494,0.008609842,0.001011783,0.0047224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002781851,"threshold_uncertainty_score":0.006693006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03848016728623602,"score_gpt":0.2845407386134647,"score_spread":0.2460605713272287,"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."}}