{"id":"W3045260398","doi":"10.1101/2020.07.24.212712","title":"Benchmarking challenging small variants with linked and long reads","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Standards and Technology; National Institutes of Health; German Network for Bioinformatics Infrastructure; Bundesministerium für Bildung und Forschung; U.S. National Library of Medicine; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Benchmark (surveying); False positive paradox; Indel; False positives and false negatives; Computer science; Computational biology; Set (abstract data type); Data mining; Biology; Artificial intelligence; Genetics; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01245324,0.002227034,0.001462282,0.002969032,0.001352717,0.003342828,0.002566681,0.002031677,0.003032202],"category_scores_gemma":[0.03686899,0.0006904096,0.001677332,0.003642328,0.001033706,0.001499375,0.002979881,0.001958696,0.002339427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348922,"about_ca_system_score_gemma":0.002028615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008789808,"about_ca_topic_score_gemma":0.009718682,"domain_scores_codex":[0.9822806,0.005740163,0.001528451,0.004137127,0.005461638,0.000852031],"domain_scores_gemma":[0.9783014,0.01025839,0.0008895064,0.005061869,0.004648108,0.0008407373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005220988,0.001056013,0.1200393,0.003301074,0.003381152,0.001684833,0.001184837,0.3440847,0.134392,0.02332241,0.1206606,0.2416723],"study_design_scores_gemma":[0.0005509331,0.001199598,0.04534792,0.0002648882,0.0005139925,0.001490986,0.000555045,0.622997,0.1933247,0.03080632,0.1024891,0.000459506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5992827,0.004090808,0.2832077,0.001447577,0.001222539,0.0008940988,0.05117259,0.04204069,0.01664123],"genre_scores_gemma":[0.5322094,0.0005568581,0.2861817,0.001519016,0.0002100928,0.0009236913,0.1666507,0.007486868,0.004261678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01245324,"threshold_uncertainty_score":0.06585985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01625443660525582,"score_gpt":0.2021607567112065,"score_spread":0.1859063201059507,"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."}}