Newswise — Seven projects from across the University of Utah have been awarded One Utah Data Science Hub seed grants, kickstarting collaborative projects that find creative ways to harness big data and answer tough questions.
The proposed projects range in focus from an investigation of the potential benefits of virtual reality-based “nature” experiences for hospital patients to tools that allow scientists to make full use of huge databases of dietary compounds. The breadth of awarded research is representative of the scope of the One Utah Data Science Hub. The hub aims to promote interdisciplinary research across the U on the technology, applications, and ethics related to the unprecedented amount of data that scientists can now access.
Penny Atkins, PhD, former associate director of the One Utah Data Science Hub, says, “We were excited to witness the development of so many new collaborations and appreciated the diversity of projects submitted to this funding opportunity. The leadership of the One Utah Data Science Hub looks forward to the progression of these projects over the next year.”
This year’s awarded projects:
“Explaining Data Evolution”
Anna Fariha, PhD (School of Computing)
Nina de Lacy, MD (Department of Psychiatry)
- Most existing tools to understand and summarize large datasets are used for static, unchanging data and don’t adequately capture how data can change dynamically. The researchers will develop a technique to better understand how large datasets change over time.
“Scalable and Information-Rich Sequence Search Over SRA for Advanced Biological Analyses”
Prashant Pandey, PhD (School of Computing)
Aaron Quinlan, PhD (Departments of Human Genetics and Biomedical Informatics)
- This project will improve the usefulness of a search tool for the Sequence Read Archive, a massive, public database of when and where genes are expressed in the body, helping researchers learn more from this wealth of information.
“Connecting the Metabolite-Protein Interactome: Precision Diet and Drug Synergy for Enhanced Cancer Care”
Mary Playdon, PhD (Departments of Nutrition & Integrative Physiology and Population Health Sciences)
Kevin Hicks, PhD (Department of Biochemistry)
Aik Choon Tan, PhD (Departments of Oncology and Biomedical Informatics)
- Diet plays an important role in cancer progression and the efficacy of treatment. The research team will build a tool that cross-references databases of food-derived compounds, cancer drugs, and cancer gene expression to help scientists design precision diets that improve outcomes for cancer patients.
“Information Theoretic Approaches to Causal Inference”
Ellis Scharfenaker, PhD (Department of Economics)
Braxton Osting, PhD (Department of Mathematics)
- Randomized controlled trials are the gold standard in social sciences and economics research, but they can miss underlying factors, making it difficult to know the true causes of outcomes. The scientists are finding better ways to infer causality, basing their work in statistics and an understanding of randomness and uncertainty.
“Automated Live Meta-Analysis of Clinical Outcomes Using Generative AI”
Fatemeh Shah-Mohammadi, PhD (Department of Biomedical Informatics)
Joseph Finkelstein, MD, PhD (Department of Biomedical Informatics)
- Clinical research outcomes are essential for informing medical care, but this data is often scattered and difficult to interpret. This project will build an AI-based tool that collects relevant clinical research and synthesizes it into a comprehensive, interactive dashboard in real time.
“Modeling the Effect of Artificial Nature Exposure on Brain Health in Bed-bound Populations Using Variational Autoencoders”
Elliot Smith, PhD (Department of Neurosurgery)
Jeanine Stefanucci, PhD (Department of Psychology)
- Exposure to nature reduces stress and improves mental well-being, and simulations of nature could potentially do the same for people without access to the outside. The research team will use a combination of mood and stress measurements and recordings of electrical activity to learn how virtual reality-based “nature” exposures affect hospital patients.
“Using Controlled Animal ECG Recordings for Machine Learning-Based Prediction of Myocardial Ischemia Outcomes”
Tolga Tasdizen, PhD (Department of Electrical & Computer Engineering and School of Computing)
Ben Steinberg, MD (Division of Cardiovascular Medicine)
Rob MacLeod, PhD (Departments of Biomedical Engineering and Internal Medicine)
- Myocardial ischemia, or reduced blood flow to the heart, can lead to deadly complications, including heart attack. But it’s hard to estimate the risks of ischemia-related complications before they occur. This project will use recordings from animal models to train a machine learning tool to predict the severity of ischemia based on the electrical activity of the heart.