Postdoctoral Fellow in Pharmacogenetics, Bioinformatics, and Machine Learning

Institution/Company:
University of Toronto, Centre for Addiction and Mental Health
Location:
Toronto, ON, Canada
Job Type:
  • Postdoctoral
Degree Level Required:
PhD
Apply Now

Postdoctoral Fellow in Pharmacogenetics, Bioinformatics, and Machine Learning

Applications are invited for a Postdoctoral Fellow position at the Pharmacogenetics Research Clinic at the Centre for Addiction and Mental Health and the University of Toronto, under the supervision of Dr. Daniel Mueller (MD, Ph.D.). The postdoctoral fellow will integrate psychiatric pharmacogenetics with various methods in computational biology and bioinformatics. Our major goal is to understand and optimize the methodological opportunities and challenges for machine learning associated with the integration of genome-wide data from large-scale, epidemiological datasets and smaller, clinical-treatment cohorts. The postdoctoral fellow will engage in projects which aim to understand the genetic contributions to antidepressant non-remission in older adults with late-life depression as a function of underlying pathophysiology associated with ageing, such as cerebrovascular and neurodegenerative changes.

Responsibilities:

  • Developing and refining an in-development, open-source, computational pipeline for analyzing large-scale genomic data and predictive modelling for complex outcomes
  • Developing and evaluating predictive models for psychiatric treatment outcomes (e.g., antidepressant response)
  • Analyzing in-house cohorts of individuals with psychiatric diagnoses (e.g., depression, schizophrenia) and integrating findings with publicly-available cohorts with genomic and clinical data
  • Using in silicon methods to characterize and explore genetic variants, genes and their associated pathways
  • Staying abreast with cutting-edge methods and techniques as research opportunities develop
  • Training and mentorship of young trainees in understanding genomics and applying computational methods

Qualifications:

REQUIRED QUALIFICATIONS

  • Ph.D. (or similar qualification) in Bioinformatics, Biostatistics, Computer Science, computational sciences or relevant field or a combination of relevant experience and education.
  • Must have an understanding of and experience in statistical genetics or genetic epidemiology for working with genome-wide genetic data (genotype and other variation) for complex trait analyses
  • Must have proficient computer programming skills, including familiarity with UNIX-like OS, high-performance computing (cluster), R or at least one programming language
  • Experience with computational methods development and application (e.g., developing R packages)
  • Experience with machine learning techniques, such as random forest models, support vector machines and deep learning.
  • Excellent data visualization skills, as well as experience in using tools for reproducible research including git
  • Ability to work independently and collaboratively as a member of an interdisciplinary team
  • Ability to multitask and track projects
  • Strong written and oral communication skills as demonstrated by peer-reviewed publications and conference presentations
  • English language proficiency is required

PREFERRED QUALIFICATIONS

  • Experience managing large and complex datasets
  • Experience with supervising students, mentoring, or teaching
  • How to Apply

    Interested applicants should email (1) their CV; (2) a cover letter (detailing interest in the lab, fellowship applications, and future plans); (3) a one-page summary of the most relevant publication, and (4) contact information for three references to Dr. Daniel Mueller. The position will remain open until filled.