{"id":"W4404507391","doi":"10.52843/cassyni.gq2yrj","title":"Rapid species-level metagenome profiling and containment estimation with sylph","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Profiling (computer programming); Metagenomics; Computational biology; Computer science; Environmental science; Biology; Genetics; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001994404,0.002182402,0.00140421,0.002563244,0.0008107469,0.002314066,0.001691572,0.001281317,0.01136051],"category_scores_gemma":[0.007869183,0.001247124,0.001776046,0.001976005,0.0004631951,0.002317372,0.002737793,0.002094419,0.009812004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004857528,"about_ca_system_score_gemma":0.001125638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001473975,"about_ca_topic_score_gemma":0.004492744,"domain_scores_codex":[0.9983102,0.0002190633,0.0001104584,0.0006293129,0.0005901952,0.0001407929],"domain_scores_gemma":[0.9981462,0.0006092798,0.0002279227,0.0005874088,0.0003098289,0.0001193026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002258597,0.0004427024,0.0576917,0.00362417,0.001633689,0.0009116746,0.002207445,0.01107594,0.3799619,0.01057411,0.1557043,0.3739137],"study_design_scores_gemma":[0.0004865973,0.0008466328,0.05292089,0.000418975,0.0004506638,0.001556231,0.001022335,0.2844476,0.3981331,0.03517173,0.224061,0.0004842161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07166635,0.001645707,0.6162776,0.0006243723,0.0005160313,0.0005251443,0.1197406,0.1806935,0.008310596],"genre_scores_gemma":[0.1034774,0.0006101349,0.7847446,0.0004833912,0.0001242047,0.0009130447,0.0934693,0.0128996,0.00327828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01136051,"threshold_uncertainty_score":0.03800476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03505967575881603,"score_gpt":0.2395734967509844,"score_spread":0.2045138209921684,"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."}}