{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000169728,0.0001522889,0.0002209309,0.000100641,0.00007000616,0.000005653366,0.0002000918,0.000192641,0.00001013786],"category_scores_gemma":[0.00004046672,0.0001440218,0.00009271519,0.0001835179,0.0001483865,5.260769e-7,0.0002053529,0.00004603465,0.00001503992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001477464,"about_ca_system_score_gemma":0.00006814797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004137725,"about_ca_topic_score_gemma":0.00001718418,"domain_scores_codex":[0.9989505,0.0000532293,0.0002766546,0.0003657874,0.00004169134,0.0003120903],"domain_scores_gemma":[0.9993464,0.00001645206,0.0001461686,0.0003489673,0.00008940049,0.00005256325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004606283,0.00001884722,0.02959781,0.00001154368,0.00009030828,5.046986e-7,0.00007851436,0.00007140804,0.9688893,0.00006808917,0.00002449844,0.001103124],"study_design_scores_gemma":[0.001163568,0.0006649644,0.8725945,0.00000662669,0.00006102357,0.00001477662,0.0003948059,0.001100614,0.06599969,0.0007836432,0.05666424,0.0005515965],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971672,0.001455432,0.0003412278,0.00008044849,0.0002276935,0.0002009846,0.00009728266,0.000008877586,0.0004208064],"genre_scores_gemma":[0.9981905,0.0005891616,0.0004978415,0.0000627746,0.0002255866,0.00002504175,0.0001668896,0.00002306881,0.0002191664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9028896,"threshold_uncertainty_score":0.5873041,"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."}}