Bradley Webb

Virginia Commonwealth University

2 active projects

Predicting psychiatric disorder risk for genetic discovery analyses V6.1

Large sample sizes are required for genetic studies of psychiatric disorders such as major depression and alcohol use disorder. While All of Us is powerful resource, not all variables are measured on all participants which reduces power for genetic analyses.…

Scientific Questions Being Studied

Large sample sizes are required for genetic studies of psychiatric disorders such as major depression and alcohol use disorder. While All of Us is powerful resource, not all variables are measured on all participants which reduces power for genetic analyses. Methods exists to estimate unmeasured variables if correlated variables are measured, thereby offering the opportunity to increase power. However, non-random missingness can diminish prediction accuracy. We’ve developed an approach to address correlated patterns of missingness when predicting unmeasured phenotypes. This research seeks to apply and develop this approach and perform integrated genetic association analyses using both measured and predicted variables related to psychiatric and substance use disorders. These disorders have significant negative impacts on individuals, families, and society. Understanding the influence of genetics on these disorders is important for improved diagnostics and treatment.

Project Purpose(s)

  • Disease Focused Research (Psychiatric and substance use disorders)
  • Methods Development
  • Ancestry

Scientific Approaches

We plan to apply machine learning approaches such as LASSO and GBMs to predict disorder risk, symptoms, and/or diagnoses that are not directly measured using other measured and correlated variables that are available. These predictions will be used in applied genetic association analyses to search for genetic variants associated with risk.

Anticipated Findings

We anticipated being able to predict risk in subjects without direct clinical assessments. These predictions will increase the effective sample size and statistical power for applied genetic association studies. This is expected to increase the ability to discover novel genetic loci influencing risk to psychiatric and substance used disorders as well as increase confidence in and refine effect sizes for loci previously implicated.

Demographic Categories of Interest

  • Race / Ethnicity

Data Set Used

Registered Tier

Research Team

Owner:

Collaborators:

  • Amanda Gentry - Research Fellow, Virginia Commonwealth University
  • Brien Riley - Late Career Tenured Researcher, Virginia Commonwealth University
  • Mohammad Ahangari - Graduate Trainee, Virginia Commonwealth University
  • Amy Moore - Research Associate, Research Triangle Institute

Predicting psychiatric disorder risk for genetic discovery analyses V5

Large sample sizes are required for genetic studies of psychiatric disorders such as major depression and alcohol use disorder. While All of Us is powerful resource, not all variables are measured on all participants which reduces power for genetic analyses.…

Scientific Questions Being Studied

Large sample sizes are required for genetic studies of psychiatric disorders such as major depression and alcohol use disorder. While All of Us is powerful resource, not all variables are measured on all participants which reduces power for genetic analyses. Methods exists to estimate unmeasured variables if correlated variables are measured, thereby offering the opportunity to increase power. However, non-random missingness can diminish prediction accuracy. We’ve developed an approach to address correlated patterns of missingness when predicting unmeasured phenotypes. This research seeks to apply and develop this approach and perform integrated genetic association analyses using both measured and predicted variables related to psychiatric and substance use disorders. These disorders have significant negative impacts on individuals, families, and society. Understanding the influence of genetics on these disorders is important for improved diagnostics and treatment.

Project Purpose(s)

  • Disease Focused Research (Psychiatric and substance use disorders)
  • Methods Development
  • Ancestry

Scientific Approaches

We plan to apply machine learning approaches such as LASSO and GBMs to predict disorder risk, symptoms, and/or diagnoses that are not directly measured using other measured and correlated variables that are available. These predictions will be used in applied genetic association analyses to search for genetic variants associated with risk.

Anticipated Findings

We anticipated being able to predict risk in subjects without direct clinical assessments. These predictions will increase the effective sample size and statistical power for applied genetic association studies. This is expected to increase the ability to discover novel genetic loci influencing risk to psychiatric and substance used disorders as well as increase confidence in and refine effect sizes for loci previously implicated.

Demographic Categories of Interest

  • Race / Ethnicity

Data Set Used

Registered Tier

Research Team

Owner:

Collaborators:

  • Amanda Gentry - Research Fellow, Virginia Commonwealth University
  • Brien Riley - Late Career Tenured Researcher, Virginia Commonwealth University
  • Mohammad Ahangari - Graduate Trainee, Virginia Commonwealth University
  • Amy Moore - Research Associate, Research Triangle Institute
1 - 2 of 2
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.