{"id":"W3211840676","doi":"10.1101/2021.11.05.467426","title":"Syotti: Scalable Bait Design for DNA Enrichment","year":2021,"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":"Dalhousie University","funders":"","keywords":"Scalability; Metagenomics; Heuristic; Computer science; Set (abstract data type); Time complexity; DNA sequencing; Matching (statistics); Computational biology; Algorithm; DNA; Biology; Mathematics; Genetics; Artificial intelligence; Gene; Database; Statistics","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":[0.001048596,0.001451337,0.001642285,0.001144545,0.0006865672,0.001284331,0.002254419,0.001255547,0.008022855],"category_scores_gemma":[0.002977005,0.0008454174,0.001436317,0.001251965,0.0009667468,0.001900891,0.002367865,0.001908627,0.004336941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001266823,"about_ca_system_score_gemma":0.001268285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001363925,"about_ca_topic_score_gemma":0.001737383,"domain_scores_codex":[0.9989325,0.0001752188,0.0000748916,0.0003042357,0.00038551,0.0001275729],"domain_scores_gemma":[0.9987533,0.0005640921,0.00009691295,0.000311929,0.0001798231,0.00009394129],"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":[0.001377149,0.0004749275,0.00200046,0.001712401,0.0001333407,0.0003710214,0.0003085783,0.0936177,0.4399458,0.03732366,0.02618379,0.3965513],"study_design_scores_gemma":[0.0002024117,0.0004228087,0.0006057912,0.00005797827,0.00005473736,0.0003309132,0.00007652388,0.7165319,0.2297852,0.0275325,0.02430662,0.00009261738],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02014746,0.0005512972,0.9548232,0.0002221411,0.00008259822,0.000376736,0.000863379,0.02038176,0.002551408],"genre_scores_gemma":[0.1147174,0.0003511076,0.8772415,0.0003325846,0.00002881057,0.0005744211,0.002925445,0.0008409944,0.002987699],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008022855,"threshold_uncertainty_score":0.02683908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01759921680636086,"score_gpt":0.2210297769149958,"score_spread":0.2034305601086349,"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."}}