{"id":"W4404333429","doi":"10.1093/nargab/lqae145","title":"Refining SARS-CoV-2 intra-host variation by leveraging large-scale sequencing data","year":2024,"lang":"en","type":"article","venue":"NAR Genomics and Bioinformatics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Montreal Heart Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Canada Foundation for Innovation","keywords":"Workflow; Computational biology; Host (biology); DNA sequencing; Computer science; Cluster analysis; Visualization; Biology; Data mining; Genetics; Artificial intelligence; DNA; Database","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":[0.0009824208,0.0001827446,0.0002506103,0.0001902634,0.0001732329,0.0003221194,0.0002278448,0.0001448146,0.000004410714],"category_scores_gemma":[0.00008597637,0.0001579679,0.00004433131,0.0002853907,0.0000474885,0.0004451659,0.0003189487,0.0003923065,0.00008413548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002633574,"about_ca_system_score_gemma":0.0004226823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001302382,"about_ca_topic_score_gemma":0.00003396641,"domain_scores_codex":[0.9985276,0.0000166095,0.0004701776,0.0002766224,0.0003086245,0.0004002906],"domain_scores_gemma":[0.9992204,0.00008575957,0.00007383039,0.0005105725,0.00006815726,0.00004127293],"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":[0.0001125015,0.00007002256,0.001774159,0.001906391,0.0002626949,0.00007404178,0.01900078,0.000001916209,0.8972982,0.0004341234,0.01516514,0.0639],"study_design_scores_gemma":[0.0006400109,0.00009666858,0.00007720057,0.0001981788,0.00007656134,0.0001246683,0.001365328,0.5161564,0.03971944,0.00006422629,0.4412618,0.0002195742],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9633734,0.002425485,0.02694477,0.0007924984,0.0003768727,0.0003222607,0.0004453265,0.0001759984,0.005143424],"genre_scores_gemma":[0.8372538,0.0006448654,0.07744149,0.08203439,0.0010681,0.00002744358,0.001170713,0.0001744945,0.0001846808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8575788,"threshold_uncertainty_score":0.6441746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06431370519734829,"score_gpt":0.3304385491763903,"score_spread":0.266124843979042,"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."}}