{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000577551,0.0005622945,0.0006797682,0.0005390316,0.0001302336,0.0003407578,0.0003981969,0.0006795537,0.00001189311],"category_scores_gemma":[0.0002016539,0.0006014127,0.0002229795,0.0009819022,0.000136574,0.0003123589,0.0001187375,0.0005570489,0.00005126685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003841009,"about_ca_system_score_gemma":0.0001422502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001909463,"about_ca_topic_score_gemma":0.00005288601,"domain_scores_codex":[0.9973904,0.00006937407,0.0007367377,0.0008553882,0.0003506054,0.00059742],"domain_scores_gemma":[0.998562,0.00008657434,0.0001882187,0.0006390298,0.0003951245,0.0001290707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001040813,0.00002601019,0.0006356636,0.0005799793,0.0001326207,0.00004226006,0.000007440142,0.008382295,0.9892482,0.0002339054,0.0006984865,0.000002729769],"study_design_scores_gemma":[0.0002927951,0.00003316149,0.008913339,0.0003436821,0.0001184818,2.265747e-8,0.000004064511,0.0824865,0.9064946,0.00004189391,0.0005522999,0.0007191444],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909334,0.0004675383,0.003533144,0.0002228436,0.002437515,0.0007796251,0.0004942805,0.001124028,0.000007599135],"genre_scores_gemma":[0.997588,0.0006180452,0.0007746146,0.00008504361,0.0004251366,0.0003221018,0.000002745833,0.0001554241,0.00002884137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08275359,"threshold_uncertainty_score":0.9996437,"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."}}