{"id":"W4296458366","doi":"10.1101/2022.09.16.508250","title":"Compressed Data Structures for Population-Scale Positional Burrows–Wheeler Transforms","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Data structure; Haplotype; Memory footprint; Matching (statistics); Computer science; Footprint; Scale (ratio); Algorithm; Bounding overwatch; Population; Data mining; Mathematics; Artificial intelligence; Statistics; Biology; Geography","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":[0.001267061,0.0007745664,0.0007796539,0.001643122,0.0006446587,0.001992165,0.002015658,0.0008524745,0.007876155],"category_scores_gemma":[0.01292397,0.0004726978,0.0008816884,0.00401726,0.0006791552,0.003393376,0.00198745,0.001617091,0.003928792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008887923,"about_ca_system_score_gemma":0.002098317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002176521,"about_ca_topic_score_gemma":0.002828722,"domain_scores_codex":[0.9983107,0.0002539433,0.00027421,0.000265431,0.0007605796,0.0001352206],"domain_scores_gemma":[0.9951107,0.001556621,0.0004194229,0.001908139,0.0008869662,0.000118118],"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":[0.001345923,0.0003319495,0.004390564,0.0005790858,0.0001071049,0.0004670429,0.00064674,0.06549009,0.0318641,0.1224185,0.05457789,0.717781],"study_design_scores_gemma":[0.0005266654,0.0005343791,0.002425002,0.0001962627,0.00006996629,0.0006763752,0.0005232944,0.6561328,0.06375354,0.1855767,0.08945028,0.0001347975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05260805,0.001216632,0.920872,0.001038273,0.0003702845,0.0003382302,0.008083075,0.01095811,0.004515314],"genre_scores_gemma":[0.2060747,0.0007352817,0.768534,0.0003762985,0.0002183965,0.00114912,0.01835296,0.0008917865,0.003667385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007876155,"threshold_uncertainty_score":0.02634835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01997661531210315,"score_gpt":0.2738836032019117,"score_spread":0.2539069878898085,"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."}}