{"id":"W4386554491","doi":"10.1093/bioinformatics/btad552","title":"μ- PBWT: a lightweight r-indexing of the PBWT for storing and querying UK Biobank data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; European Commission; Natural Sciences and Engineering Research Council of Canada; Japan Society for the Promotion of Science; National Institutes of Health; National Science Foundation","keywords":"Computer science; Biobank; Search engine indexing; Leverage (statistics); Set (abstract data type); Data structure; Haplotype; Data mining; Index (typography); Computation; Theoretical computer science; Information retrieval; Algorithm; Artificial intelligence; Bioinformatics; Biology; Genotype; Genetics","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":[0.001522754,0.001384109,0.001224048,0.003089017,0.0008639012,0.002653583,0.004342877,0.001152241,0.009690761],"category_scores_gemma":[0.01333822,0.0008574724,0.001305763,0.006743904,0.001151012,0.00687886,0.004042896,0.001538793,0.007338067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129121,"about_ca_system_score_gemma":0.002837756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00681375,"about_ca_topic_score_gemma":0.006203332,"domain_scores_codex":[0.9973851,0.0002856505,0.0003919287,0.000547636,0.001189202,0.0002005793],"domain_scores_gemma":[0.9946842,0.001158425,0.0004915956,0.00268685,0.0007499763,0.0002289791],"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":[0.001439753,0.0003860086,0.005047842,0.001323948,0.000141541,0.0006621128,0.0009057513,0.0227711,0.05135451,0.03525189,0.1266849,0.7540306],"study_design_scores_gemma":[0.0006671652,0.0005528515,0.003874345,0.0002426757,0.00009863857,0.00141911,0.0006673128,0.6908586,0.09367286,0.08824123,0.1194379,0.0002673882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03210007,0.001380699,0.8676173,0.0007611309,0.0003428744,0.0006611947,0.01503849,0.07718548,0.004912816],"genre_scores_gemma":[0.119136,0.0005830718,0.8385093,0.0003260864,0.0001460684,0.0007921009,0.03319285,0.003240736,0.004073748],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009690761,"threshold_uncertainty_score":0.03241885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04623299182789144,"score_gpt":0.2960578176711589,"score_spread":0.2498248258432675,"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."}}