{"id":"W4292961172","doi":"10.1093/bioinformatics/btac564","title":"ntHash2: recursive spaced seed hashing for nucleotide sequences","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health","keywords":"Hash function; Computer science; Dynamic perfect hashing; Universal hashing; Sequence (biology); Linear hashing; Algorithm; Hash table; Theoretical computer science; Perfect hash function; Double hashing; 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":[0.001173623,0.0007942106,0.0007444144,0.0009913014,0.0006988385,0.0010551,0.001982277,0.0007864682,0.00946551],"category_scores_gemma":[0.006201632,0.0005283648,0.000631374,0.001472176,0.0008162647,0.002025246,0.002382777,0.0009241839,0.007543378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006495165,"about_ca_system_score_gemma":0.001408194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001481752,"about_ca_topic_score_gemma":0.002399085,"domain_scores_codex":[0.9988795,0.0001788646,0.0001083207,0.0002428077,0.0005035585,0.00008686992],"domain_scores_gemma":[0.9982431,0.0004753008,0.0001388886,0.0006269772,0.0003962083,0.0001196456],"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":[0.002676787,0.0001844988,0.007167232,0.001184761,0.0001509634,0.0004215768,0.0007402276,0.03865575,0.1367875,0.04158469,0.07070463,0.6997413],"study_design_scores_gemma":[0.0004004187,0.0006469808,0.00293572,0.0001461352,0.00006917206,0.001391608,0.000263074,0.6131971,0.2379471,0.05439419,0.08838964,0.0002188779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0304084,0.0008547435,0.9366002,0.0002186667,0.0003020146,0.0002650924,0.002947528,0.02462843,0.003775089],"genre_scores_gemma":[0.2127456,0.0003502661,0.7678595,0.0002157811,0.0001077333,0.0004405181,0.008409044,0.00210546,0.007766085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00946551,"threshold_uncertainty_score":0.03166533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02258197213046361,"score_gpt":0.2519532532620437,"score_spread":0.22937128113158,"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."}}