{"id":"W4403228370","doi":"10.1038/s41587-024-02412-y","title":"Rapid species-level metagenome profiling and containment estimation with sylph","year":2024,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Metagenomics; Genome; Computational biology; Biology; RefSeq; Genetics; Gene","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":[0.0001104455,0.0001555153,0.0001423179,0.00008344081,0.0000663606,0.0000280669,0.0001061173,0.0005192304,0.000006053308],"category_scores_gemma":[0.00003175039,0.0001185364,0.00003255439,0.0001080337,0.0001487462,8.680768e-7,0.000122423,0.0002693427,0.000003536786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001743838,"about_ca_system_score_gemma":0.00003967424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002762969,"about_ca_topic_score_gemma":0.00001033574,"domain_scores_codex":[0.9992093,0.00001319788,0.0001134835,0.0004061006,0.00007118405,0.0001867588],"domain_scores_gemma":[0.9996742,0.00001195513,0.00002954686,0.0002247282,0.00003046129,0.00002909059],"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":[0.00004246167,0.00001401231,0.0001962665,0.00004154301,0.0002296743,0.00001409202,0.00003190518,0.00001900098,0.9655948,0.01090597,0.0003160017,0.0225943],"study_design_scores_gemma":[0.0003608499,0.000672737,0.003238122,0.00002352545,0.00007371883,0.0001220975,0.000163339,0.0005294423,0.7837521,0.0005573063,0.2102222,0.0002844973],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9090028,0.08244441,0.004575385,0.002680817,0.0002796982,0.0003368132,0.0000657303,0.00004108315,0.0005732501],"genre_scores_gemma":[0.9829247,0.002466688,0.01404702,0.0001428258,0.00009878695,0.00002414685,0.00003860107,0.00001952955,0.0002377044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2099062,"threshold_uncertainty_score":0.4833774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009960746472811999,"score_gpt":0.2296689821726567,"score_spread":0.2197082356998447,"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."}}