{"id":"W2944510853","doi":"10.1093/bioinformatics/btz308","title":"gpart: human genome partitioning and visualization of high-density SNP data by identifying haplotype blocks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Hospital for Sick Children; Sinai Health System; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Statistical Sciences Institute; Canadian Institutes of Health Research; National Research Foundation of Korea; Neurosciences Research Foundation","keywords":"Bioconductor; Visualization; Computer science; Cluster analysis; Genome; Tag SNP; dbSNP; Linkage disequilibrium; Data mining; Single-nucleotide polymorphism; R package; Haplotype; Computational biology; SNP genotyping; Reference genome; DNA sequencing; Biology; Genetics; Gene; Artificial intelligence; Computational science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003347179,0.00008648261,0.000159429,0.00002943048,0.00008530118,0.00001943847,0.0001524332,0.0001200159,0.00002572292],"category_scores_gemma":[0.00008539698,0.00008705653,0.00002018975,0.00005337523,0.00004490755,0.00001320212,0.0002500711,0.00003781183,0.0000145912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007467918,"about_ca_system_score_gemma":0.00002102554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006725144,"about_ca_topic_score_gemma":0.00003378292,"domain_scores_codex":[0.9992451,0.00003061415,0.0003484798,0.0001464945,0.00008345029,0.0001458336],"domain_scores_gemma":[0.99924,0.00001329374,0.00024154,0.000395552,0.00006985798,0.00003979238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003317435,0.000135319,0.3177656,0.0003743942,0.0002955226,4.144428e-7,0.0007409086,0.0004866602,0.6561183,0.00167825,0.02025319,0.002118277],"study_design_scores_gemma":[0.003392134,0.001231481,0.8152285,0.0001337281,0.0003028644,0.0000367615,0.001622386,0.0444967,0.09287287,0.001626145,0.03766374,0.0013927],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981245,0.0001915793,0.01787546,0.00003370261,0.0000786425,0.0001300665,0.0000844123,0.000009146962,0.0003519396],"genre_scores_gemma":[0.993218,0.0001471435,0.003710183,0.0001111142,0.0000392006,0.000002037113,0.002476154,0.000008711644,0.0002874807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5632454,"threshold_uncertainty_score":0.3550062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03210594169097992,"score_gpt":0.3011335103091326,"score_spread":0.2690275686181527,"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."}}