My lab's research projects lie at the intersection of mathematical modeling, machine learning, and computer programming and focus on understanding biological systems and human diseases better. This summer, we will tackle four exciting projects.
Project 1. Prediction of Human Mood Disorders using Machine Learning
A significant portion of the population today are affected by mood disorders such as anxiety and depression. Multiple studies have found an association between mood disorders and misalignments in human circadian rhythms caused by variations in circadian clock genes. This study will use machine learning to predict mood disorders using specific genetic variations and clinical factors.
Project 2. Prediction of Soil-transmitted Helminth Infection using Machine Learning
A number of parasitic worms cause soil-transmitted helminth (STH) infections. Approximately 1.5 billion people are infected with STHs worldwide. The morbidity and reduced fitness associated with this disease makes it a significant concern for global health and agriculture in endemic areas. This project will use a detailed Ethiopian school children survey to identify the potential risk factors for STH infections. Using these risk factors, we will develop machine learning approaches to predict the infection status of patients.
Project 3. Network Discovery using Mathematical Modeling and Machine Learning
The precursors of spatially repetitive vertebrae segments are periodically generated by a biological regulatory network (a set of genes and proteins that interact with each other to control a specific cell function.) This yet-to-be-discovered biological network controls the vertebrate segmentation during embryonic development. In this project, we will identify this network through mathematical modeling and machine learning.
Project 4. Developing a High-Performance Parallel Simulation Software for Large Scale Biological Systems
There is no stochastic simulation software for large scale biological systems with delays. This project will create a high-performance parallel version of an existing stochastic simulation software. The new software should create highly compact and efficient data structures and should also potentially support GPU acceleration.
Students must have taken COSC 102, MATH 260 and/or MATH 376, at minimum. Experience with C programming language and statistical/machine learning would be helpful, as would experience with mathematical modeling.
Number of Student Researchers
Applications open on 01/03/2021 and close on 03/22/2021