{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002193313,0.001536344,0.00140017,0.001359311,0.0009766876,0.001284984,0.002662681,0.001233787,0.008229319],"category_scores_gemma":[0.008443383,0.0009256256,0.00134059,0.002130758,0.0006945361,0.001986827,0.002175667,0.001818459,0.009619068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004504182,"about_ca_system_score_gemma":0.001461413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001278831,"about_ca_topic_score_gemma":0.001727354,"domain_scores_codex":[0.9974198,0.0004751911,0.0002457379,0.0009512286,0.0007658353,0.0001421462],"domain_scores_gemma":[0.997215,0.001014719,0.0004403402,0.0006385836,0.0005261218,0.0001651843],"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":[0.002583034,0.0003105251,0.008054066,0.003369258,0.0006428519,0.00122594,0.000898547,0.04728563,0.2190374,0.01254617,0.08980556,0.6142412],"study_design_scores_gemma":[0.0006318201,0.001184471,0.006710199,0.0002873965,0.0002835766,0.002298838,0.0003026142,0.6440665,0.2307183,0.02561114,0.08742611,0.0004791159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02529995,0.001886121,0.8757123,0.0002979205,0.0003959067,0.000372714,0.007244174,0.08652196,0.002268941],"genre_scores_gemma":[0.1116112,0.0004721152,0.8611929,0.0003112728,0.0001823635,0.0005980585,0.01826228,0.004733128,0.002636764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008229319,"threshold_uncertainty_score":0.02752978,"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."}}