Nathan Sheffield, PhD, an associate professor in the Departments of Public Health Sciences, Biomedical Engineering, and Biochemistry and Molecular Genetics, and in the School of Data Science, was recently awarded a $1.5 million R01 grant from the NIH for a study to support biomedical analysis of genome and epigenome data by developing faster and more accurate approaches to compare genomic locations.
Dr. Sheffield’s research team includes Co-Investigators Don Brown, PhD, the Quantitative Foundation Distinguished Professor of Data Science, senior associate dean for research, School of Data Science, and co-director of iTHRIV and Aidong Zhang, PhD, the William Wulf Faculty Fellow and Professor of Computer Science, Biomedical Engineering, and Data Science.
The team’s approach uses more scalable algorithms and machine learning to improve both the efﬁciency and accuracy of methods for analyzing genomic locations. These advances could lead to new ways of exploring the vast and growing corpus of genome interval data. The data holds tremendous promise to understand gene regulation in diseases like cancer because many health outcomes are affected by genetic variation or epigenetic perturbation in regulatory DNA.
Dr. Sheffield’s research is centered in the Center for Public Health Genomics (CPHG), which broadly aims to address questions in biology, public health, and medicine by developing and applying state-of-the-art genetic, genomic, and computational approaches to complex human diseases.
Read more about the Sheffield Lab and UVA’s School of Medicine Center for Public Health Genomics.
Abstract: Epigenomic assays help us measure the molecular behavior of regions of the genome, helping us better understand what the genome encodes. This knowledge has driven biomedical discovery in analysis of genetic variation and gene regulation. As the amount of available epigenome data increases, we need novel methods to extract useful biological knowledge from the data. Our proposal develops novel machine learning approaches to learn relationships among genomic regions, improving our ability to interpret the human genome. These advances will improve both the efficiency and accuracy of research approaches that analyze genomic regions, and open the door to new ways of exploring the vast and growing corpus of genomic data.