{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001932414,0.002427319,0.002387912,0.00153506,0.0009680945,0.002192584,0.003304906,0.002190402,0.0147421],"category_scores_gemma":[0.006135635,0.00164289,0.002485624,0.001571402,0.001327446,0.003093275,0.003642775,0.00287707,0.01216337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00129214,"about_ca_system_score_gemma":0.001838154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001633101,"about_ca_topic_score_gemma":0.002828652,"domain_scores_codex":[0.9980648,0.000304634,0.0001610133,0.0006268105,0.0006746931,0.0001680886],"domain_scores_gemma":[0.9978422,0.00105081,0.0001503118,0.0005438162,0.0002700311,0.0001428253],"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":[0.002691856,0.0005275969,0.004871472,0.005463731,0.0005119351,0.0007156405,0.000680187,0.04606927,0.4304122,0.02083855,0.1118868,0.3753309],"study_design_scores_gemma":[0.0007590253,0.0006954388,0.002649271,0.0002798861,0.000192921,0.001100049,0.0002077787,0.5002762,0.3399153,0.0462978,0.1073111,0.0003152202],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01344553,0.0013083,0.8465508,0.0004752474,0.0002322248,0.0006614096,0.007911769,0.1264469,0.002967805],"genre_scores_gemma":[0.05838007,0.0006986032,0.9079943,0.0008385853,0.00007540685,0.001427798,0.02182382,0.00521754,0.003543858],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0147421,"threshold_uncertainty_score":0.04931724,"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."}}