{"id":"W4220928475","doi":"10.1101/2022.03.10.22272213","title":"Cov2clusters: genomic clustering of SARS-CoV-2 sequences","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Centre for Disease Control; Public Health Agency of Canada; Simon Fraser University","funders":"British Columbia Centre for Disease Control; Michael Smith Health Research BC; Government of Canada; Australian Government","keywords":"Phylogenetic tree; Cluster analysis; Whole genome sequencing; Biology; Computational biology; Pandemic; Genome; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Sequence (biology); Coronavirus disease 2019 (COVID-19); Clade; Genetics; Evolutionary biology; Computer science; Gene; Infectious disease (medical specialty); Disease; Medicine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001488874,0.001294635,0.0007755695,0.002622437,0.001141975,0.001775022,0.001031762,0.0008523941,0.00470069],"category_scores_gemma":[0.004153081,0.0006491733,0.001011006,0.001838168,0.0005059991,0.0006314995,0.001396086,0.0009341358,0.002930595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108907,"about_ca_system_score_gemma":0.001518794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009189929,"about_ca_topic_score_gemma":0.01256609,"domain_scores_codex":[0.9987575,0.0002387901,0.00007688707,0.0005217312,0.0002855028,0.0001195294],"domain_scores_gemma":[0.9989342,0.0002496924,0.0001365106,0.0002793624,0.0003039938,0.000096245],"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":[0.002871503,0.0005138156,0.05887162,0.001639484,0.001082566,0.001251812,0.002435539,0.06345835,0.4914639,0.01182029,0.07450151,0.2900896],"study_design_scores_gemma":[0.0004426354,0.0004900658,0.06305834,0.0002117005,0.0002565425,0.001296149,0.001590569,0.576187,0.2498854,0.0171167,0.08921156,0.000253419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4267911,0.001043095,0.4890521,0.001044681,0.0005422921,0.0008025105,0.03518197,0.03840485,0.00713738],"genre_scores_gemma":[0.3426975,0.000328654,0.5827669,0.0002096031,0.0001066988,0.000401079,0.06283626,0.005462624,0.005190712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009189929,"threshold_uncertainty_score":0.01827288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04283215011622016,"score_gpt":0.291965591512611,"score_spread":0.2491334413963909,"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."}}