Medical data and machine learning improve power of stroke genome-wide association studies.
Thangaraj, P. M.; Tatonetti, N.
Show abstract
Genome-wide association studies (GWAS) may require enrollment of up to millions of participants to power variant discovery. This requires manual curation of cases and controls with large-scale collaborations. Biobanks connected to electronic health records (EHR) can facilitate these studies by using data from clinical care systems, like billing diagnosis codes, as phenotypes. These systems, however, do not define adjudicated cases and controls. We developed QTPhenProxy, a machine learning model that adds nuance to cohort classification by assigning everyone in a cohort a probability of having the study disease. We then ran a GWAS using the probabilities as a quantitative trait. With an order of magnitude fewer cases than the largest stroke GWAS, our method outperformed previous methods at replicating known variants in stroke and discovered a novel variant in ABCG8 associated with intracerebral hemorrhage in the UK Biobank that replicated in the MEGASTROKE GWA meta-analysis. QTPhenProxy expands traditional phenotyping to improve the power of GWAS.
Matching journals
The top 13 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Admixture Mapping of Peripheral Artery Disease in a Dominican Population Reveals a Novel Risk Locus on 2q35 93%
- Multi-trait GWAS of atherosclerosis detects novel pleiotropic loci 92%
- Genes and pathways implicated in tetralogy of Fallot revealed by ultra-rare variant burden analysis in 231 genome sequences 92%
Similar papers in this journal
- Impact of loss-of-function in angiopoietin-like 4 on the human phenome 94%
- The association between lymphocyte mitochondrial DNA abundance and Stroke: a combination of multivariable-adjusted survival and mendelian randomization analyses 93%
- Polygenic Hyperlipidemias and Coronary Artery Disease Risk 90%
Similar papers in this journal
- Leveraging genetic data to elucidate the relationship between Covid-19 and ischemic stroke 93%
- Chromosome 10q24.32 Variants Associate with Brain Arterial Diameters in Diverse Populations: A Genome-Wide Association Study 93%
- Genetic downregulation of interleukin-6 signaling and arteriolosclerotic cerebral small vessel disease: a drug target Mendelian randomization analysis 92%
Similar papers in this journal
- Phenome-wide Mendelian randomization study of plasma triglycerides and 2,600 disease traits 93%
- Shared and distinct pathways and networks genetically linked to coronary artery disease between human and mouse 93%
- Ethnic and region-specific genetic risk variants of stroke and its comorbid conditions can define the variations in the burden of stroke and its phenotypic traits 92%
Similar papers in this journal
- Using human genetics to understand the causes and consequences of circulating cardiac troponin I in the general population 93%
- The impact of fatty acids biosynthesis on the risk of cardiovascular diseases in Europeans and East Asians: A Mendelian randomization study 93%
- Multi-ancestry polygenic risk scores for venous thromboembolism 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.