2020 Virtual undergraduate Research symposium
Machine Learning to Investigate the Relationship Between Nutrition, Disease, and the Human Gut Microbiome
PROJECT NUMBER: 40
AUTHOR: Lauren Zoe Baker, Computer Science | MENTOR: Hua Wang, Computer Science
ABSTRACT
—
The human gut microbiome is a population of microorganisms that inhabit the human gastrointestinal tract. The host bacteria that comprise the human gut microbiome are interconnected with nutrition and human health outcomes, such as obesity, type 2 diabetes, inflammatory bowel disease, and cardiovascular disease. We want to investigate and model a relationship between three interconnected entities. Due to the nature of this relationship, we propose the use of multi-task learning. For example, we might have the following two tasks: (1) regression, where we use nutrients to predict bacteria and (2) classification, where we use nutrients and bacteria to classify a certain disease. Solving these two tasks simultaneously could better characterize this multidirectional relationship. We consider a joint regression classification method as well as various neural network architectures.
VISUAL PRESENTATION
—
AUTHOR BIOGRAPHY
—
Lauren “Zoe” Baker is a sophomore pursuing a B.S. in Computer Science and a B.S. in Computational and Applied Mathematics. Zoe conducts research with the Machine Learning, Informatics, and Data Science (MInDS@Mines) lab, under the mentorship of Dr. Hua Wang and PhD students Saad Elbeleidy and Lodewijk Brand. Her research is primarily focused on the development and application of machine learning algorithms to analyze and interpret biological data. This past year, Zoe has concentrated those efforts onto better understanding the human gut microbiome, in an attempt to uncover the potential hidden relationships between microorganisms in the gut and human health and nutrition. In the future, Zoe hopes to pursue a doctorate in Computer Science and a career in research.
The poster is successful in getting the audience excited about the use of Machine Learning to tackle human health.
In this reviewer’s opinion, the poster is overly dense in content, and can perhaps overwhelm the reader. The language in the poster also does not sound like that of an undergraduate student researcher. Finally, this reviewer failed to identify key results that bring the research back home to the topic of human health.
I hope that the research can continue, and the student can sink teeth into the field.