{"id":"W4317600535","doi":"10.1101/2023.01.18.524587","title":"Fast and robust metagenomic sequence comparison through sparse chaining with skani","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chaining; Metagenomics; Computer science; Sequence (biology); Genome; Data mining; Computational biology; Biology; Gene; Genetics","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":[0.003583902,0.001566438,0.001996482,0.003281614,0.001481954,0.001966707,0.002230473,0.001246541,0.007478457],"category_scores_gemma":[0.01325765,0.001348773,0.001598351,0.003558471,0.000909848,0.002456743,0.003651925,0.002352825,0.005620774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005492616,"about_ca_system_score_gemma":0.001729418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002021462,"about_ca_topic_score_gemma":0.005650816,"domain_scores_codex":[0.997555,0.0007024892,0.0001980056,0.0006098317,0.0007667634,0.0001679286],"domain_scores_gemma":[0.9958739,0.001549779,0.0004304495,0.001031067,0.0008953773,0.0002194637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00293274,0.000561112,0.01278276,0.002200469,0.001486388,0.0007820356,0.001170738,0.06312588,0.2538522,0.02387238,0.05356509,0.5836682],"study_design_scores_gemma":[0.000272608,0.0002898835,0.003883566,0.0001257258,0.0001503302,0.0004600438,0.0002681196,0.8834603,0.06059198,0.02715312,0.0231775,0.000166771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04657608,0.0004113534,0.9163397,0.0002109345,0.0002182339,0.0002205978,0.002817997,0.03168125,0.001523896],"genre_scores_gemma":[0.08878942,0.000140629,0.898847,0.0001575416,0.00005582147,0.0003983771,0.008289245,0.002314218,0.001007889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007478457,"threshold_uncertainty_score":0.02501792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04852002238559341,"score_gpt":0.2472383702977815,"score_spread":0.1987183479121881,"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."}}