{"id":"W2951332226","doi":"10.1089/cmb.2019.0309","title":"Efficient Construction of a Complete Index for Pan-Genomics Read Alignment","year":2020,"lang":"en","type":"preprint","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"String (physics); Search engine indexing; Computer science; Rank (graph theory); Sample (material); Suffix array; Compressed suffix array; Index (typography); Data structure; Suffix; Database index; Space (punctuation); Data mining; String searching algorithm; Information retrieval; Mathematics; Combinatorics; World Wide Web; Programming language","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":[0.001389083,0.001031622,0.001990104,0.003884669,0.001140877,0.002569426,0.0021325,0.001206693,0.005631907],"category_scores_gemma":[0.008801332,0.0007861272,0.001205965,0.006049891,0.000646768,0.004825516,0.003436036,0.002181449,0.009092192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008727089,"about_ca_system_score_gemma":0.002929444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001659525,"about_ca_topic_score_gemma":0.002976466,"domain_scores_codex":[0.9976588,0.0002562017,0.0003221037,0.0005161748,0.001040636,0.000206077],"domain_scores_gemma":[0.996145,0.0006930748,0.0002225271,0.001449571,0.001288007,0.0002018183],"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":[0.0005948395,0.0003178537,0.004105354,0.0007575984,0.0001212061,0.0004243046,0.0005751784,0.01691737,0.09436843,0.03245481,0.04845808,0.800905],"study_design_scores_gemma":[0.0002503348,0.0006071486,0.005115023,0.0001836957,0.0001766847,0.001777756,0.0004876825,0.5898419,0.148283,0.08765018,0.165388,0.000238536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02215034,0.001120615,0.9487873,0.0002259432,0.0002742611,0.0002527193,0.004660555,0.0177839,0.004744384],"genre_scores_gemma":[0.05398333,0.000415687,0.9229496,0.0001604386,0.0001742204,0.0003295904,0.01671887,0.001591901,0.003676381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005631907,"threshold_uncertainty_score":0.01884055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03835700790850998,"score_gpt":0.2969671167264644,"score_spread":0.2586101088179544,"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."}}