{"id":"W4318193482","doi":"10.1093/bioinformatics/btad057","title":"How to optimally sample a sequence for rapid analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Japan Science and Technology Agency; U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Sequence (biology); Computer science; Source code; Sampling (signal processing); Sample (material); Sequence analysis; Sequence alignment; Algorithm; Biology; Peptide sequence; Genetics; DNA; Programming language","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":[0.006303701,0.001532136,0.001733221,0.001592161,0.001222735,0.002031274,0.001790054,0.001816331,0.00508777],"category_scores_gemma":[0.04395114,0.001199871,0.001201314,0.001796115,0.002290186,0.005163869,0.002227971,0.002719414,0.005046855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008519666,"about_ca_system_score_gemma":0.002880398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001504956,"about_ca_topic_score_gemma":0.001818259,"domain_scores_codex":[0.992568,0.003294781,0.0005747819,0.001461822,0.001777185,0.0003233236],"domain_scores_gemma":[0.9772719,0.01636114,0.001109582,0.002117085,0.002451996,0.0006883409],"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":[0.001340404,0.0004385092,0.009683511,0.002659439,0.0002936536,0.0008162846,0.001216006,0.1874639,0.09930953,0.05685391,0.03512733,0.6047975],"study_design_scores_gemma":[0.0001809029,0.0003434753,0.00189355,0.0004140825,0.0001381491,0.00105351,0.0005732815,0.6426622,0.05985806,0.274561,0.01819361,0.0001281128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02192017,0.0007859478,0.970036,0.001737007,0.0001264463,0.0002029579,0.0005279894,0.003208767,0.001454687],"genre_scores_gemma":[0.0984957,0.0005964594,0.8961909,0.0007375285,0.0001494347,0.0003374115,0.001418759,0.001279649,0.0007941325],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006303701,"threshold_uncertainty_score":0.03333753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03516069343064127,"score_gpt":0.2718266799308762,"score_spread":0.236665986500235,"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."}}