Postdoctoral Fellowship: PRFB: Using Deep Learning to Assess the Impacts of Genome Duplication on Gene Networks Important for Crop Domestication and Resilience

Dunn, Tamsen Jane, San Diego CA

Investigators

Abstract

This action funds an NSF Plant Genome Postdoctoral Research Fellowship in Biology for FY 2025. The fellowship supports a research and training plan in a host laboratory for the Fellow who also presents a plan to broaden participation in biology. The title of the research and training plan for this fellowship to Tamsen Dunn is "Using deep learning to assess the impacts of genome duplication on gene networks important for crop domestication and resilience" The host institution for the fellowship is the University of Arizona and the sponsoring scientist is Dr. Michael Barker. This project seeks to decode the role of whole genome duplication in shaping crop resilience and productivity, as a framework for deriving novel methods for targeted crop improvement. Whole genome duplication or polyploidy is a situation where the number of sets of chromosomes of an organism increase. Polyploidy has occurred frequently in plant evolution and is common among crop plants. Despite the prevalence of polyploidy, it is unclear whether it is favored or disfavored by evolution. Polyploid plants often exhibit increased vigor and larger fruit, often outcompeting their diploid counterparts. However, over generations, polyploid species gradually shed genes and return to the original, two sets of chromosomes. This project seeks to integrate data from plants across the tree of life where their ancestors experienced polyploidy at different time periods in the past to untangle the advantages and disadvantages of polyploidy. Improvements in our understanding in this area will empower plant scientists to make new improvements to crops. Additionally, this fellowship will prepare the Fellow for a lead role in the scientific community by serving as a mentor to graduate and undergraduate students. The Fellow will receive additional training in teaching at the university level in preparation for the next stage of the Fellow’s career. This project uses a big-data approach, combining genomic simulations, large-scale data analytics, and machine learning, to examine how whole genome duplication impacts genome structure, gene networks, adaptive traits, and crop domestication potential across 1,500 sequenced plant species. The main goal is to pinpoint genetic patterns that promote resilience and productivity in crop species. This goal is advanced by three aims: (1) use lessons learned from evolution during past environmental change events to determine if and at what stage polyploidy and diploidization have conferred resilience to plant lineages, (2) use machine learning and big data approaches to investigate the relationship between the stage of diploidization and genome structure in domesticated crops, (3) leverage the relationship between inferred resilience and genome structure to model and test how changes to genomic features might increase or decrease resilience to environmental changes in Brassicaceae. This research aims to produce a foundational model for harnessing the advantages of whole genome duplication to inform crop improvement in an era of increasing agricultural demand. Additionally, the Fellow will serve as a mentor-in-training to students in the NSF Research Traineeship Program, CAMBIUM. This program provides training for college students in the integration of biology, health, social, and policy data. The Fellow will participate in the Postdoctoral Teaching Certificate program, which focuses on evidence-based teaching. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.