{"id":"W4386923678","doi":"10.1038/s41592-023-02018-3","title":"Fast and robust metagenomic sequence comparison through sparse chaining with skani","year":2023,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; 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; Chaining; Genome; Computational biology; Computer science; Sequence (biology); k-mer; Data mining; Biology; 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":[0.003056238,0.002107441,0.001986219,0.002621588,0.001902223,0.002289177,0.002214019,0.001379221,0.01168867],"category_scores_gemma":[0.01385243,0.00144609,0.00189426,0.002985084,0.0008419685,0.00274329,0.004535234,0.002963959,0.009511406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006288943,"about_ca_system_score_gemma":0.002221687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002201798,"about_ca_topic_score_gemma":0.009068079,"domain_scores_codex":[0.9979153,0.0004911723,0.0001984048,0.0006808754,0.0005499272,0.0001642446],"domain_scores_gemma":[0.9966707,0.001258276,0.0003233434,0.000948243,0.0006039133,0.000195624],"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":[0.002965228,0.0006032065,0.01686434,0.00381062,0.002290174,0.0008024829,0.001816753,0.02935235,0.3110377,0.02253472,0.1239827,0.4839398],"study_design_scores_gemma":[0.0006959129,0.0006767389,0.01096207,0.000498804,0.0004855385,0.001355633,0.0008071671,0.652784,0.1520615,0.06196798,0.1172236,0.0004810103],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06012263,0.001052687,0.8277427,0.000441558,0.0004805191,0.0003341183,0.01299346,0.09329871,0.003533588],"genre_scores_gemma":[0.100432,0.0003351214,0.8589034,0.0003989077,0.00008592194,0.0006849453,0.02973728,0.007534233,0.001888166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01168867,"threshold_uncertainty_score":0.03910255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06632126381695887,"score_gpt":0.3795433704802162,"score_spread":0.3132221066632574,"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."}}