{"id":"W2191136822","doi":"10.1093/bioinformatics/btv662","title":"rHAT: fast alignment of noisy long reads with regional hashing","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National High-tech Research and Development Program; University of Toronto; National Natural Science Foundation of China","keywords":"Computer science; Hash function; Bottleneck; Hash table; Source code; Theoretical computer science; Data mining; Computational biology; Algorithm; Biology; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001368534,0.0001132934,0.0001271591,0.00002506483,0.00003620521,0.00001389667,0.0001293079,0.00005995109,0.000001573518],"category_scores_gemma":[0.00001777305,0.00008817019,0.00003846472,0.00004709591,0.0000831902,0.00000169333,0.00009921657,0.00003146753,0.000005654448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001207049,"about_ca_system_score_gemma":0.00008873171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001251658,"about_ca_topic_score_gemma":0.00002048386,"domain_scores_codex":[0.9993469,0.000008849406,0.0002309304,0.00009008797,0.0001693971,0.0001538204],"domain_scores_gemma":[0.9994196,0.000005461882,0.000134324,0.0002406895,0.0001197851,0.00008014875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002351165,0.001241894,0.310497,0.001476594,0.003463596,0.00003635236,0.03889167,0.0166543,0.3902632,0.007261899,0.1423039,0.0855585],"study_design_scores_gemma":[0.01011259,0.007659688,0.0613416,0.000387478,0.000373784,0.0004206191,0.0215337,0.006706549,0.4611396,0.000625865,0.4270233,0.002675242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9850854,0.0006150489,0.006725177,0.0001574549,0.0001056535,0.0001629682,0.00002424879,0.000004113606,0.007119928],"genre_scores_gemma":[0.9826417,0.0001160599,0.01665289,0.0001825021,0.00008720318,0.000007000122,0.00004826498,0.00001110288,0.0002532832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2847194,"threshold_uncertainty_score":0.3595476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02446974064005683,"score_gpt":0.2337236409569146,"score_spread":0.2092539003168578,"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."}}