{"id":"W4410922688","doi":"10.1101/2025.05.30.656631","title":"Finding an optimal sequencing strategy to detect short and long genetic variants in a human genome","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Ontario Genomics","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Genome Canada","keywords":"Human genome; Computational biology; Genetics; Genome; Biology; DNA sequencing; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002790845,0.0007132242,0.001008915,0.001252225,0.0005276524,0.001449182,0.0008046984,0.0009224095,0.001531556],"category_scores_gemma":[0.006355186,0.0004195393,0.0007240253,0.000821782,0.0004270904,0.0009347195,0.0008289571,0.000938958,0.00119445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005087422,"about_ca_system_score_gemma":0.001407719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002431611,"about_ca_topic_score_gemma":0.005134379,"domain_scores_codex":[0.9986475,0.0004098255,0.0001001274,0.0004847352,0.0002462627,0.0001115719],"domain_scores_gemma":[0.998367,0.0009180364,0.0001378831,0.0001140384,0.0003540757,0.0001088853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009949321,0.0002764619,0.04012954,0.001474386,0.0005600292,0.0005544173,0.0003280541,0.05603509,0.6622741,0.00739436,0.004941381,0.2250372],"study_design_scores_gemma":[0.0001315324,0.0007311483,0.01825123,0.0003364987,0.000656162,0.0008767323,0.0004499786,0.4985788,0.4476324,0.01516914,0.01698004,0.0002063521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4648721,0.008848858,0.5135756,0.001289935,0.0002220877,0.0003794926,0.00312893,0.003315684,0.00436733],"genre_scores_gemma":[0.5131805,0.001407988,0.4803864,0.0005661274,0.00004057176,0.0001869811,0.002719905,0.0005339368,0.0009775687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002790845,"threshold_uncertainty_score":0.01475954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167095729215845,"score_gpt":0.2498482526228387,"score_spread":0.2331386797012542,"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."}}