Liang, Yu; Wu, Dalei; Yang, Li
College of Engineering and Computer Science
University of Tennessee at Chattanooga
Place of Publication
Biological analytics and more advanced data analysis techniques have made remarkable advancements as the area of machine learning continues to grow. More specifically, genetic modeling and neural network building are gaining interest as it becomes a fundamental piece of most model building we see today. We propose a Knowledge-Based Artificial Neural Network (KBANN) to predict phenotype while providing insight to effected subsystems. Within KBANN, the input layers are a single or group of Gene Ontology (GO) terms while each layer’s input is a single number between 0 and 1, explaining how expressed the given term is. The expression number provides an average of the number of copies that a gene is producing at its current age compared to that over the average of its entire lifespan. Preliminary results show that KBANN model can potentially be used to predict lifespan phenotype using the Genotype-Tissue Expression data.
It has been an honor to conduct this research at the University of Tennessee at Chattanooga. I would like to begin by thanking my committee chair, Dr. Hong Qin, for providing a home for me in his lab and his continuous support and guidance throughout this process. His mentoring style is one I have always admired, even prior to our research together. His openness to ideas and gentle ways of guiding you to the way of success is unmatched. Under his mentorship, I have learned the ways of proposal writing, which aided in our granted access of protected data sets, and methods of genetic data modeling. I will forever be appreciative of his time and efforts to make sure we have the assistance and support we need to succeed. I appreciate the NSF Career award 1720215, BD Spoke 1761839 that support the Dr. Qin’s research projects in data science and computational biology. I would also like to thank Trevor Peyton, my research partner for this project. Without Trevor’s background and coding expertise the success of this project would not have been possible. Trevor has worked tirelessly on model building and training and was a great support and partner. It has been an absolute honor to work alongside him. Finally, I would like to thank my thesis committee members, Dr. Yu Liang, Dr. Dalei Wu, and Dr. Li Yang. I have had the pleasure of working with Dr. Liang on many occasions during my time at the University of Tennessee at Chattanooga. His teaching style is one I always admired, always creating an open door for discussion and questions. I am incredibly grateful for my time in his classes and the many areas of computer science in which he expanded my knowledge on. Dr. Wu was one of the first professors I met when starting this program, and I will never forget the fundamentals he taught me early on. His expertise and guidance were a crucial piece of the start of my career. It is an honor to have him here with me as I end this chapter. Finally, Dr. Li Yang has been a fundamental piece of this thesis project. Her grant aided in my ability to perform this work and carry out this project during my time in Dr. Qin’s lab. Thank you for your support and for believing in our work. My deepest gratitude goes out to my incredible support system of friends and family, without whom I could not have done this. Their constant support and encouragement constantly kept me going even when things got tough. The individuals I have met during my time here at UTC have truly aided in creating such an amazing space for me to learn and fuel my future career. Specifically, Victoria Sinnott and Viji Kumarasamy who have stuck through the entirety of my master’s career with me and have continued to be a fundamental support for me during this time. I will forever cherish the friendship we created over the years. Mom, Dad, Peden, Yasmine, Madysen, and Jake you have all provided support, and encouragement as I took on this endeavor. Thank you for the countless days and nights of listening to any and all problems and providing sincere perspective. Finally, I would like to thank my fiance, Jared. You have continued to push me throughout the years even when I wanted to give up. You have taught me to always aim for the stars and go after what I want, to never let anyone other than myself determine my success. Thank you for your patience and encouragement with me when I have been frustrated. Not to mention, all the many nights trying to help me understand organic chemistry.
M. A.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Arts.
Genetics--Mathematical models; Neural networks (Computer science)
xii, 35 leaves
Day, Taylor, "Knowledge-based artificial neural network modeling assessment: integrating heterogeneous genomics data to uncover lifespan regulation" (2022). Masters Theses and Doctoral Dissertations.