{"id":"W3037430960","doi":"10.1101/2020.06.29.177121","title":"kTWAS: Integrating kernel-machine with transcriptome-wide association studies improves statistical power and reveals novel genes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Ontario Brain Institute; Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Health Solutions; Universities Space Research Association","keywords":"Kernel (algebra); Computer science; Feature selection; Kernel method; Feature (linguistics); Genetic association; Pruning; Linear model; Artificial intelligence; Data mining; Computational biology; Machine learning; Biology; Genotype; Support vector machine; Gene; Genetics; Mathematics; Single-nucleotide polymorphism","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":[0.005190932,0.0006933831,0.001169099,0.0009358636,0.0005922613,0.001188496,0.001832845,0.0009065053,0.002030621],"category_scores_gemma":[0.01386135,0.0004792634,0.001254497,0.001191232,0.0007672006,0.001181251,0.001904683,0.001460156,0.0005870702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005502926,"about_ca_system_score_gemma":0.001420587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003160746,"about_ca_topic_score_gemma":0.00493197,"domain_scores_codex":[0.9981934,0.0009347689,0.0000948288,0.0003240018,0.0003320486,0.0001209428],"domain_scores_gemma":[0.995188,0.002963265,0.0002817283,0.0008840488,0.0004889972,0.0001938951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009482069,0.0003347739,0.02854895,0.0004265757,0.001462785,0.0004944655,0.00026115,0.4914469,0.02485229,0.02320638,0.01290119,0.4151163],"study_design_scores_gemma":[0.00007419635,0.00006672735,0.001676502,0.00001171987,0.00005517992,0.00007870423,0.00001566293,0.9812545,0.003451615,0.01131269,0.001979517,0.00002299559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03187206,0.0002336043,0.9632128,0.0003374262,0.0001039571,0.00008071594,0.0002571621,0.003357263,0.0005449607],"genre_scores_gemma":[0.4012857,0.000178534,0.5943627,0.0003593093,0.00008942074,0.0003526453,0.0009998487,0.0006162146,0.001755677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005190932,"threshold_uncertainty_score":0.02745265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01475468706228798,"score_gpt":0.2512506150530373,"score_spread":0.2364959279907493,"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."}}