Medical data and machine learning improve power of stroke genome-wide association studies

Pm, Thangaraj; Gisladottir, U; Tatonetti, Nicholas P.

doi:10.1101/2020.01.22.915397

Cited by 4 publications

(3 citation statements)

References 57 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work that uses indGWAS should attempt to maintain the cohort as much as possible. An applicable method for this challenge is QTPhenProxy, in which the phenotype definition is replaced by an estimated phenotype probability using regression on other variables [14]. For the phecode case/control example, a regression could be fit on case/control definitions before being evaluated on the whole cohort.…”

Section: Discussionmentioning

confidence: 99%

Phenotype projections accelerate biobank-scale GWAS

Zietz,

Gisladottir,

Brown

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding the genetic basis of complex disease is a critical research goal due to the immense, worldwide burden of these diseases. Pan-biobank genome-wide association studies (GWAS) provide a powerful resource in complex disease genetics, generating shareable summary statistics on thousands of phenotypes. Biobank-scale GWAS have two notable limitations: they are resource-intensive to compute and do not inform about hand-crafted phenotype definitions, which are often more relevant to study. Here we present Indirect GWAS (indGWAS), a summary-statistic-based method that addresses these limitations. IndGWAS computes GWAS statistics for any phenotype defined as a linear combination of other phenotypes. Our method can reduce runtime by an order of magnitude for large pan-biobank GWAS, and it enables ultra-rapid (less than one minute) GWAS on hand-crafted phenotype definitions using only summary statistics. Overall, this method advances complex disease research by facilitating more accessible and cost-effective genetic studies using large observational data.

show abstract

Section: Discussionmentioning

confidence: 99%

Phenotype projections accelerate biobank-scale GWAS

Zietz,

Gisladottir,

Brown

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although previous studies have identified thousands of disease-associated loci, researchers have yet to deeply explore the joint contribution of family history, clinical measures, and lifestyle factors to model disease liabilities. Machine learning techniques have advanced in recent years, allowing to reveal patterns in massive, high-dimensional datasets and capturing non-linear relationships 18,19 . Our study seeks to improve genetic prediction with deep learning-based estimates of disease liability probabilities that leverage joint semantic and structure-based embeddings of phenotypes in the UKBB.…”

Section: Introductionmentioning

confidence: 99%

Genetic association studies using disease liabilities from deep neural networks

Yang

Sadler

Altman

2023

Preprint

View full text Add to dashboard Cite

The case-control study is a widely used method for investigating the genetic landscape of binary traits. However, the health-related outcome or disease status of participants in long-term, prospective cohort studies such as the UK Biobank are subject to change. Here, we develop an approach for the genetic association study leveraging disease liabilities computed from a deep patient phenotyping framework (AI-based liability). Analyzing 44 common traits in 261,807 participants from the UK Biobank, we identified novel loci compared to the conventional case-control (CC) association studies. Our results showed that combining liability scores with CC status was more powerful than the CC-GWAS in detecting independent genetic loci across different diseases. This boost in statistical power was further reflected in increased SNP-based heritability estimates. Moreover, polygenic risk scores calculated from AI-based liabilities better identified newly diagnosed cases in the 2022 release of the UK Biobank that served as controls in the 2019 version (6.2% percentile rank increase on average). These findings demonstrate the utility of deep neural networks that are able to model disease liabilities from high-dimensional phenotypic data in large-scale population cohorts. Our pipeline of genome-wide association studies with disease liabilities can be applied to other biobanks with rich phenotype and genotype data.

show abstract

“…'& ), consistent with the known pathophysiology of disorder. Interestingly, there was a significant interaction effect between the cryptic phenotype PGS and P/LP carrier status (bPGSxP/LP=0 50.…”

mentioning

confidence: 99%

Common genetic variation associated with Mendelian disease severity revealed through cryptic phenotype analysis

Blair

Hoffmann

Shieh

2021

Preprint

View full text Add to dashboard Cite

Clinical heterogeneity is common in Mendelian disease, but small sample sizes make it difficult to identify specific contributing factors. However, if a rare disease represents the severely affected extreme of a spectrum of phenotypic variation, then modifier effects may be apparent within a larger subset of the population. Analyses that take advantage of this full spectrum could have substantially increased power. To test this, we developed cryptic phenotype analysis (CPA), a model-based approach that uses symptom data to infer latent quantitative traits that capture disease-related phenotypic variability. By applying this approach to 50 Mendelian diseases in two large cohorts of patients, we found that these quantitative traits reliably captured disease severity. We then conducted genome-wide association analyses for five of the inferred cryptic phenotypes, uncovering common variation that was predictive of Mendelian disease-related diagnoses and outcomes. Overall, this study highlights the utility of computationally derived phenotypes and biobank-scale cohorts for investigating the complex genetic architecture of Mendelian diseases.

show abstract

Medical data and machine learning improve power of stroke genome-wide association studies

Cited by 4 publications

References 57 publications

Phenotype projections accelerate biobank-scale GWAS

Phenotype projections accelerate biobank-scale GWAS

Genetic association studies using disease liabilities from deep neural networks

Common genetic variation associated with Mendelian disease severity revealed through cryptic phenotype analysis

Contact Info

Product

Resources

About