Computational Characterization of Environmental Enteropathy

项目总结/文摘

PROJECT SUMMARY/ABSTRACT Undernutrition afflicts 20% of children < 5 years of age in low- and middle-income countries (LMICs) and is a major risk factor for mortality. Linear growth failure (or stunting) in children is tightly linked to irreversible physical and cognitive deficits, with profound implications for development. A common cause of stunting in LMICs is Environmental Enteropathy (EE) which has also been linked to decreased oral vaccine immunogenicity. To date, there are no universally accepted, clear diagnostic algorithms or non-invasive biomarkers for EE making this a critical priority. In this K23 Mentored Career Development Award application, Dr. Sana Syed, a Pediatric Gastroenterologist with advanced training in Nutrition at the University of Virginia, proposes to 1) Develop and validate a Deep Learning Net to identify morphological features of EE versus celiac and healthy small intestinal tissue, 2) correlate the Deep Learning Net identified distinguishing EE intestinal tissue findings with clinical phenotype, measures of gut barrier and absorption, and bile acid deconjugation, and 3) Use a Deep Learning Net computational approach to identify distinguishing multiomic patterns of EE versus celiac disease. This work will be carried out in the context of an ongoing birth cohort study of environmental enteropathy in Pakistan (SEEM). Dr. Syed proposes a career development plan which includes mentorship, fieldwork, coursework, publications, and clinical time that will situate her as an independent physician-scientist with expertise in translational research employing computational `omics and image approaches to elucidate biologic mechanisms of stunting pathways and in identification of novel and effective therapies for EE.