{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001657572,0.0000985333,0.00009833964,0.00006251744,0.0001187475,0.0001519373,0.0007825424,0.00004360337,0.00002733063],"category_scores_gemma":[0.00007774457,0.00005742053,0.00003933795,0.000133244,0.00003327103,0.001940914,0.0004176498,0.00005166758,0.0006562853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003346915,"about_ca_system_score_gemma":0.00003951156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000432046,"about_ca_topic_score_gemma":7.269779e-7,"domain_scores_codex":[0.999171,0.00001297667,0.0002418323,0.0001148177,0.0002288338,0.0002305761],"domain_scores_gemma":[0.9990648,0.00009126456,0.0001184121,0.0005725132,0.0000544781,0.00009853514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003444077,0.00002836842,0.0001473324,0.00002059234,0.00001159192,0.00000807387,0.001309272,0.000005465907,0.0003509413,0.09019294,0.04403867,0.8638833],"study_design_scores_gemma":[0.00198663,0.0003019052,0.002878503,0.0007247524,0.00001483466,0.0000920765,0.0003451595,0.3108798,0.009551945,0.02554555,0.6465446,0.00113415],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00159263,0.00002609951,0.9890481,0.0009836768,0.0004597984,0.00007877625,0.000012463,0.0001798755,0.007618563],"genre_scores_gemma":[0.03550022,0.00007414471,0.962895,0.0007517672,0.0001347601,0.00000601741,0.000005565042,0.00001031497,0.0006221724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8627492,"threshold_uncertainty_score":0.8435439,"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."}}