{"id":"W3208677998","doi":"10.1101/2021.10.28.21265577","title":"A fast and robust strategy to remove variant level artifacts in Alzheimer’s Disease Sequencing Project data","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Alzheimer's Coordinating Center; National Institutes of Health; Rush University; European Commission; Johns Hopkins University; Northwestern University; Emory University; York University; University of Pennsylvania; Massachusetts General Hospital; National Institute on Aging; Alzheimer's Association","keywords":"Exome sequencing; Exome; Whole genome sequencing; Computational biology; DNA sequencing; Missing heritability problem; Spurious relationship; Genome-wide association study; Genetic association; Biology; 1000 Genomes Project; Genetics; Genome; Computer science; Genetic variants; Mutation; Gene; Machine learning; Genotype; Single-nucleotide polymorphism","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":[0.02266735,0.001835782,0.001335622,0.003839869,0.001357898,0.00272224,0.002573957,0.001676841,0.002749823],"category_scores_gemma":[0.05372186,0.0009202053,0.002712463,0.003223941,0.0009703457,0.001226964,0.002514076,0.003030529,0.003008352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000568864,"about_ca_system_score_gemma":0.002500683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004596734,"about_ca_topic_score_gemma":0.007261829,"domain_scores_codex":[0.9871513,0.003615935,0.001619804,0.003197514,0.003838159,0.0005773251],"domain_scores_gemma":[0.9705838,0.0133727,0.002794313,0.006781177,0.005799999,0.0006679556],"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":[0.001386485,0.000649741,0.09393628,0.0009551613,0.002879374,0.001999704,0.001415263,0.05292837,0.1268899,0.01274531,0.03230032,0.6719141],"study_design_scores_gemma":[0.0003898582,0.0004933048,0.08074456,0.0002071934,0.0007991884,0.002064554,0.0004745736,0.7185807,0.115036,0.02512694,0.05574062,0.0003424686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02672688,0.0002380924,0.9652548,0.0002131649,0.0001722322,0.0003195989,0.001652858,0.005103996,0.0003183805],"genre_scores_gemma":[0.09501232,0.00009607998,0.8953019,0.0002562221,0.0001429726,0.000624886,0.006466731,0.001020541,0.001078341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02266735,"threshold_uncertainty_score":0.1198778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1562693656243512,"score_gpt":0.3201157581620475,"score_spread":0.1638463925376962,"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."}}