{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003839225,0.0001176658,0.0001404773,0.00009249529,0.0006488346,0.0002344497,0.001038539,0.0000271843,0.0000230148],"category_scores_gemma":[0.00006475785,0.0001052329,0.00006779752,0.0002608696,0.00002802134,0.00110653,0.0007805681,0.0001338337,0.00002428138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007678084,"about_ca_system_score_gemma":0.0001031396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001982601,"about_ca_topic_score_gemma":0.000001948895,"domain_scores_codex":[0.9989079,0.00002748116,0.0002829361,0.0001556654,0.0003477478,0.0002782747],"domain_scores_gemma":[0.9990721,0.0001262521,0.0002051929,0.0004551023,0.0000601553,0.00008114479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001225011,0.0003751252,0.0007900332,0.0004752686,0.0001702032,0.00004903406,0.04686917,0.01499298,0.001662485,0.3858577,0.2231279,0.3255076],"study_design_scores_gemma":[0.0004379879,0.0002069586,0.0001714663,0.00002037497,0.000006488808,0.00002365227,0.001515147,0.8758789,0.0004886129,0.004412684,0.1165968,0.000240893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004236537,0.00005997381,0.991018,0.001112228,0.0009393115,0.0004056,0.0001144094,0.0002010275,0.001912889],"genre_scores_gemma":[0.02900137,0.00001260501,0.9693454,0.001033801,0.00009112994,0.00008905225,0.00008956702,0.00001216736,0.0003248992],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8608859,"threshold_uncertainty_score":0.4990377,"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."}}