{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004971983,0.0001900626,0.0002521478,0.00003561414,0.000138147,0.00002780577,0.0001516807,0.0002292526,0.000003904897],"category_scores_gemma":[0.00008106361,0.0001523747,0.00004658382,0.0001856944,0.0001130479,0.000001109825,0.0001883151,0.0002507987,0.000003644697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008674602,"about_ca_system_score_gemma":0.00003493441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001420587,"about_ca_topic_score_gemma":0.00003268564,"domain_scores_codex":[0.9989215,0.0001422499,0.0001518578,0.0004273286,0.00008657212,0.0002704575],"domain_scores_gemma":[0.9994708,0.00005552312,0.00007859521,0.0002855899,0.0000562234,0.0000533222],"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":[0.00007715217,0.00001795604,0.006096333,0.00003218738,0.0002619617,0.000009053029,0.0008736438,0.003511577,0.9658575,0.0005214334,0.001192271,0.02154895],"study_design_scores_gemma":[0.002020586,0.001176219,0.05479792,0.00006242313,0.0003224707,0.0001375422,0.003647525,0.005355725,0.6426977,0.001521867,0.2867913,0.001468713],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9548817,0.01153226,0.02957554,0.0003182076,0.0003355533,0.0002290475,0.00002760512,0.00002408773,0.00307598],"genre_scores_gemma":[0.6873432,0.0007070418,0.3109125,0.0003546926,0.0001751277,0.00001809703,0.00003287948,0.00002850001,0.0004279928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3231598,"threshold_uncertainty_score":0.6213658,"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."}}