{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002242845,0.001385584,0.0009710181,0.001921692,0.0006744941,0.00178317,0.001343326,0.0009258867,0.005522169],"category_scores_gemma":[0.006958802,0.001029186,0.001316167,0.001654637,0.0004436253,0.001825905,0.002256432,0.001618485,0.003269267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004969027,"about_ca_system_score_gemma":0.0009500735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00114391,"about_ca_topic_score_gemma":0.003888041,"domain_scores_codex":[0.998231,0.0002631892,0.0001436768,0.0006503617,0.0005943058,0.0001175552],"domain_scores_gemma":[0.9976138,0.0008718027,0.00038044,0.0006098706,0.0003919977,0.0001321497],"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":[0.001952952,0.0002816116,0.04765722,0.001655862,0.0008032713,0.0004790741,0.001821298,0.005816075,0.6707088,0.004923738,0.01999266,0.2439073],"study_design_scores_gemma":[0.0002122224,0.0009893961,0.05588431,0.0002003283,0.0002781614,0.001001976,0.000680641,0.1748305,0.682996,0.009071312,0.07355419,0.0003009375],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1507477,0.001020933,0.7312595,0.00043033,0.0002126924,0.0006127859,0.04359412,0.06684217,0.005279717],"genre_scores_gemma":[0.137225,0.0003427858,0.8280714,0.0002634678,0.00005606041,0.0007747068,0.02779957,0.003724132,0.001742816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005522169,"threshold_uncertainty_score":0.01847345,"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."}}