{"id":"W4292623580","doi":"10.1101/2022.08.18.504476","title":"How to optimally sample a sequence for rapid analysis","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Sequence (biology); Sampling (signal processing); Computer science; Intuition; Sequence analysis; Heuristic; Sample (material); Algorithm; Artificial intelligence; Biology; Genetics; DNA","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005524568,0.001035024,0.001899129,0.001630713,0.0010149,0.001907135,0.001541072,0.001361913,0.003489919],"category_scores_gemma":[0.027796,0.001203238,0.00101843,0.001530648,0.001772448,0.004333304,0.002128575,0.002553844,0.002302424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007488938,"about_ca_system_score_gemma":0.001914272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109038,"about_ca_topic_score_gemma":0.001314754,"domain_scores_codex":[0.9942111,0.002797816,0.0003886892,0.0007727715,0.001522768,0.000306782],"domain_scores_gemma":[0.984526,0.01066003,0.0006821332,0.001807219,0.001825614,0.0004989127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001409385,0.0004116261,0.00852776,0.001175004,0.0002686807,0.0005578178,0.0009660948,0.2164117,0.1599472,0.0686367,0.01568625,0.5260019],"study_design_scores_gemma":[0.00009436527,0.0002317527,0.001206212,0.0001118337,0.00006642093,0.0003288164,0.0003722687,0.756055,0.06857967,0.1654308,0.007452915,0.0000699602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04079614,0.0003688241,0.9543681,0.0009967805,0.00008758439,0.0001240672,0.000201059,0.002024998,0.001032557],"genre_scores_gemma":[0.1651407,0.0003030217,0.8315693,0.0004609313,0.00009213325,0.0002362776,0.000633617,0.0008348616,0.0007291326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005524568,"threshold_uncertainty_score":0.029217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02283024309007482,"score_gpt":0.2419532378083273,"score_spread":0.2191229947182524,"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."}}