Data Scientist - 26006222

Data Scientist Nurs-Health Promotion & Development - Pennsylvania-Pittsburgh - (26006222) The University of Pittsburgh School of Nursing (PI: Lacey W. Heinsberg, PhD, RN) is seeking a highly motivated Data Scientist to help lead analyses across an active, interdisciplinary research program. Our work examines the genomic, epigenomic, environmental, and behavioral factors contributing to complex health outcomes. Current projects include community-partnered studies of pregnancy outcomes, child growth, and cardiometabolic health in Samoa and American Samoa, alongside collaborative genomic research on neurological injury, cancer, and more. Much of this work involves array-based DNA methylation data, and prior experience with DNA methylation analysis in R is very valuable. Equally important is strong analytic judgment, productivity, adaptability across concurrent projects, and genuine eagerness to learn new data types and methods. Job Summary Performs research, analysis, and modeling on organizational data and data sets utilizing advanced statistical methods to mine and analyze complex and unstructured data sets. Offers complex analysis and utilizes advanced algorithms and statistical software. Adheres to all protocols. Essential Functions Lead and support statistical analyses across a portfolio of genetic and genomic projects, both large and small Conduct epigenome-wide and genome-wide association study data cleaning and analyses, carrying data from raw files through analysis and interpretation Perform data quality diagnostics, including quality control of array-based data, handling of missing data, outlier detection, imputation, and sensitivity analyses Execute regression analyses, mixed-effects modeling, mediation analyses, and related statistical approaches across diverse study designs Create clear, transparent, and reproducible R Markdown reports and analysis pipelines maintained under version control Help maintain and improve data infrastructure to support advanced analysis Support data management activities as needed, including: REDCap database development and maintenance for phenotype and clinical data (prior REDCap experience helpful but not required; training provided) Preparation and management of dbGaP submissions for large-scale genomic datasets (prior experience helpful but not required; training provided) Contribute to manuscript preparation, scientific presentations, grant proposals, and collaborative projects May assist with training members of View the full job description on the employer's website. Equal employment opportunity, including veterans and individuals with disabilities. PI287409359 / 15-2051.00 Data Scientists