{"id":"W4387104490","doi":"10.1101/2023.09.26.559465","title":"<i>In silico</i> analyses identifies sequence contamination thresholds for Nanopore-generated SARS-CoV2 sequences","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biosensors and Analytical Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada; Genome Canada","keywords":"Nanopore sequencing; In silico; DNA sequencing; Biology; Whole genome sequencing; Computational biology; Minion; Genomics; Lineage (genetic); Phylogenetic tree; Genome; Genetics; Data mining; Evolutionary biology; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00244513,0.000625598,0.0006987203,0.0006428206,0.000656406,0.001090344,0.0006722506,0.001078431,0.001635215],"category_scores_gemma":[0.006691602,0.0004096629,0.0009860942,0.0005493546,0.0006355222,0.0005514336,0.0005335705,0.001036815,0.0006861584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007097312,"about_ca_system_score_gemma":0.0004093526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002142904,"about_ca_topic_score_gemma":0.002368751,"domain_scores_codex":[0.9972751,0.0005579832,0.0002773369,0.0007211298,0.0009158222,0.0002527437],"domain_scores_gemma":[0.9946466,0.002925975,0.0006788837,0.0003514319,0.001200322,0.0001967624],"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":[0.0008239523,0.0004167451,0.02513041,0.0003999487,0.0001348069,0.0004206076,0.000298982,0.02712012,0.9370407,0.0005300079,0.0006166011,0.007067085],"study_design_scores_gemma":[0.00001284079,0.0009342455,0.01334214,0.000048273,0.0001003734,0.0002859591,0.0001828477,0.09025576,0.8927945,0.0003484747,0.001622819,0.00007178238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755568,0.0005422711,0.02069128,0.0001628623,0.00006461122,0.0001001061,0.001514049,0.0003324237,0.001035459],"genre_scores_gemma":[0.9629209,0.0002535391,0.031888,0.0002318205,0.00002172936,0.0001273756,0.003894646,0.0001637972,0.0004981276],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00244513,"threshold_uncertainty_score":0.01293123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05701310118342916,"score_gpt":0.2896932277297185,"score_spread":0.2326801265462893,"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."}}