{"id":"W2993248623","doi":"10.1101/863035","title":"ExpansionHunter Denovo: A computational method for locating known and novel repeat expansions in short-read sequencing data","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of New Brunswick; BC Children's Hospital; University of Toronto; SickKids Foundation; Hospital for Sick Children; University of British Columbia","funders":"","keywords":"Computer science; Tandem repeat; Computational biology; Genome; Genetics; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007956699,0.0004335875,0.0004845112,0.0001347538,0.0001399023,0.00009495855,0.0005492586,0.0004045704,0.000002490332],"category_scores_gemma":[0.0003088735,0.0004657396,0.00008467211,0.0001213932,0.00007875262,0.000004946703,0.001808597,0.000281303,0.000001694336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008062753,"about_ca_system_score_gemma":0.0006106191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001122958,"about_ca_topic_score_gemma":0.000037712,"domain_scores_codex":[0.9973772,0.00007618453,0.0005331145,0.001434693,0.0001634154,0.0004153862],"domain_scores_gemma":[0.9978577,0.0001156837,0.0001582698,0.001410729,0.0003395136,0.0001181052],"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":[0.00003547219,0.00005505159,0.005445585,0.0002312998,0.0001620618,0.000003059586,0.00003119219,0.005938818,0.9878074,0.00009204919,0.000181977,0.0000160638],"study_design_scores_gemma":[0.005693963,0.0006497075,0.2012178,0.002357637,0.0007654027,0.000001272389,0.0003461583,0.2370512,0.5270577,0.00005599565,0.01943798,0.005365167],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8260442,0.003065943,0.1684102,0.0001038892,0.0004418919,0.0008867438,0.001026207,0.00001581361,0.000005078006],"genre_scores_gemma":[0.8455995,0.0002180913,0.1534443,0.0001997729,0.0002830488,0.0001516358,0.00001626696,0.00008265796,0.000004725086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4607497,"threshold_uncertainty_score":0.9997794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04433690203876772,"score_gpt":0.2892075723009666,"score_spread":0.2448706702621988,"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."}}