{"id":"W2463091895","doi":"10.1093/bioinformatics/btw397","title":"ntHash: recursive nucleotide hashing","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Hash function; Computer science; Expediting; Software; Data mining; Sequence (biology); Universal hashing; Theoretical computer science; Hash table; Biology; Genetics; 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":[0.00122493,0.0006355576,0.000725003,0.0009525071,0.0006609383,0.001078385,0.002021729,0.0006327538,0.01113661],"category_scores_gemma":[0.005981087,0.0004059972,0.00058967,0.001461723,0.0008782407,0.001725978,0.002400193,0.0009290772,0.009234875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005830812,"about_ca_system_score_gemma":0.001406157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001549355,"about_ca_topic_score_gemma":0.001873056,"domain_scores_codex":[0.9986986,0.0002309792,0.0001271111,0.0002305833,0.0006078254,0.0001049451],"domain_scores_gemma":[0.9981304,0.0005490819,0.000143654,0.000607425,0.000461532,0.0001079325],"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":[0.001615801,0.0001582889,0.00516848,0.0009871981,0.0001120953,0.0002598528,0.000460339,0.04329789,0.04504209,0.04136975,0.07508264,0.7864456],"study_design_scores_gemma":[0.0003688779,0.0009581667,0.003337289,0.0001689574,0.00009384479,0.001579977,0.0002537536,0.5846991,0.1550042,0.09393184,0.1593722,0.0002319022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02733463,0.001514825,0.9328129,0.0003716009,0.0004521915,0.0003314487,0.002642813,0.02562112,0.00891849],"genre_scores_gemma":[0.2566374,0.0006735681,0.7153977,0.0004237905,0.0002433567,0.0005057827,0.009912255,0.002070465,0.01413574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01113661,"threshold_uncertainty_score":0.0372557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01728474627139232,"score_gpt":0.2344576880311056,"score_spread":0.2171729417597133,"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."}}