{"id":"W4294844481","doi":"10.1101/2022.09.03.506492","title":"Statistical learning of large-scale genetic data: How to run a genome-wide association study of gene-expression data using the 1000 Genomes Project data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Université de Genève","keywords":"Genome-wide association study; Data science; Computer science; Scripting language; Visualization; Data visualization; Association (psychology); Scale (ratio); Psychology; Data mining; Biology; Genetics; Gene; Cartography","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":[0.009915967,0.002067045,0.001486864,0.001953105,0.001018995,0.004231549,0.00359411,0.001634005,0.07058443],"category_scores_gemma":[0.05329674,0.001408551,0.002162684,0.001443403,0.001237762,0.003592428,0.002943673,0.005013494,0.05144394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007435346,"about_ca_system_score_gemma":0.001909145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001947332,"about_ca_topic_score_gemma":0.002526995,"domain_scores_codex":[0.9965525,0.001524702,0.0002644967,0.0006275922,0.0008859573,0.0001447734],"domain_scores_gemma":[0.9709569,0.02128553,0.0006747415,0.003042768,0.002630598,0.0014096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007585185,0.0004173648,0.005527538,0.001354646,0.0003441917,0.001182542,0.001265106,0.01612892,0.01375621,0.01856324,0.4937524,0.4469493],"study_design_scores_gemma":[0.001229793,0.0003202539,0.01436515,0.0009235683,0.0002098626,0.00142695,0.001223915,0.2351822,0.04224895,0.2814582,0.4206687,0.0007424966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003291148,0.0001486283,0.90669,0.002531078,0.0006531748,0.0004211305,0.004392817,0.07676435,0.005107634],"genre_scores_gemma":[0.0253233,0.0002840356,0.9422146,0.001290701,0.000370637,0.001294808,0.004899616,0.01749876,0.006823436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07058443,"threshold_uncertainty_score":0.2361284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04119319801331665,"score_gpt":0.3013962343870436,"score_spread":0.2602030363737269,"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."}}