{"id":"W4403393007","doi":"10.1099/mgen.0.001293","title":"The Canadian VirusSeq Data Portal and Duotang: open resources for SARS-CoV-2 viral sequences and genomic epidemiology","year":2024,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; AIDS Vancouver; Mila - Quebec Artificial Intelligence Institute; Genome Canada; Michael Smith Health Research BC; Sunnybrook Health Science Centre; BC Centre for Disease Control; Women and Children’s Health Research Institute; Ontario Genomics; University of Alberta; Indoc Research; Université de Montréal; McGill Genome Centre; University of Toronto; Western University; McGill University; Simon Fraser University; Public Health Agency of Canada; Ontario Institute for Cancer Research; University of British Columbia; Montreal Heart Institute","funders":"National Cancer Institute; Canadian Institutes of Health Research; Institut de Valorisation des Données; Fonds de Recherche du Québec - Santé; Michael Smith Health Research BC; Alliance de recherche numérique du Canada; Genome Alberta; Public Health Agency of Canada; Simon Fraser University; Government of Ontario; Genome Canada; National Institutes of Health; Ontario Genomics; Government of Canada; Public Health Agency; Innovation, Science and Economic Development Canada; Canarie","keywords":"Data sharing; Pandemic; Interoperability; Big data; Suite; Genomics; Data access; Computer science; Data science; World Wide Web; Genome; Coronavirus disease 2019 (COVID-19); Database; Biology; Political science; Medicine; Data mining; Genetics","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.005383679,0.001377011,0.0009875525,0.007238703,0.004031363,0.007062501,0.003603836,0.001694351,0.07546107],"category_scores_gemma":[0.02100052,0.001067772,0.001124045,0.01183462,0.00144707,0.005267449,0.00837648,0.002397944,0.03544753],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01345262,"about_ca_system_score_gemma":0.05439309,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7835557,"about_ca_topic_score_gemma":0.8251986,"domain_scores_codex":[0.9960413,0.0004111616,0.0002813948,0.0005725044,0.002066546,0.0006271591],"domain_scores_gemma":[0.9848844,0.002323601,0.0005643513,0.003510154,0.005177789,0.003539671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002629564,0.00003598497,0.002890524,0.0004894616,0.00003632172,0.0002096551,0.0008812234,0.0006275706,0.001236719,0.01241655,0.9242038,0.05670927],"study_design_scores_gemma":[0.00004333607,0.000007421235,0.002498608,0.0001936826,0.00001042708,0.00004571543,0.0003229861,0.0005998247,0.0006871425,0.003911223,0.9915953,0.00008422745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.003764948,0.001179907,0.02336772,0.005539802,0.0006953225,0.0006751738,0.8162709,0.04369985,0.1048063],"genre_scores_gemma":[0.02451197,0.002569724,0.09292758,0.003301428,0.0002882011,0.0006507391,0.8181289,0.01513606,0.04248536],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.9963962,"threshold_uncertainty_score":0.435438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1304469555089388,"score_gpt":0.3958323842994825,"score_spread":0.2653854287905437,"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."}}