{"id":"W4226119586","doi":"10.1093/bioinformatics/btac226","title":"Syotti: scalable bait design for DNA enrichment","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Agencia Nacional de Investigación y Desarrollo; United States - Israel Binational Science Foundation; National Institutes of Health; National Science Foundation","keywords":"Metagenomics; Scalability; Computer science; Heuristic; Set (abstract data type); Computational biology; DNA; Process (computing); Protocol (science); Data mining; Algorithm; Biology; Database; Genetics; Artificial intelligence; Programming language; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002708044,0.0001167472,0.0001118112,0.00003018153,0.0003095924,0.0000203969,0.0001961668,0.00003701731,0.00002588386],"category_scores_gemma":[0.00002851108,0.0001145948,0.00007836884,0.00005865304,0.00002657256,7.783107e-7,0.0002565761,0.00003924823,0.00000831383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002551057,"about_ca_system_score_gemma":0.00007161343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002497675,"about_ca_topic_score_gemma":0.000001006392,"domain_scores_codex":[0.9992747,0.00002036487,0.0002273353,0.0001237172,0.0001161296,0.0002377196],"domain_scores_gemma":[0.9995594,0.00002023226,0.00008669434,0.0002383829,0.00004616334,0.00004912017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007571231,0.0006176676,0.003184975,0.0004293984,0.0009983858,0.000003285534,0.002933262,0.0508595,0.4393737,0.003664198,0.4601148,0.03706369],"study_design_scores_gemma":[0.001135384,0.001316482,0.0006361649,0.000003263755,0.00004705364,0.00001796946,0.0008453082,0.01306008,0.04896261,0.0004870337,0.9330854,0.000403267],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7160695,0.004544344,0.2595409,0.0008226599,0.001993075,0.003456704,0.0007765344,0.00004067789,0.01275564],"genre_scores_gemma":[0.9025821,0.0002337996,0.0928413,0.001220935,0.000213359,0.0005553044,0.0001904707,0.00003379546,0.002128906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4729706,"threshold_uncertainty_score":0.4673042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02003392150478879,"score_gpt":0.2320438933731872,"score_spread":0.2120099718683984,"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."}}