Lindsay attends Emory University.
This year, I used Python, a computer programming language, to study mutations in the two genes PTEN and PI3K. The proteins made by expressing these genes are involved in cell growth and metabolism, so mutations in these two genes commonly cause cancer. I created a database of protein sequences that included information such as the pathogenicity of the mutation, the database from which it was taken, and the species of the organism. Comparing mutations among different species can lead to other insights as well, so I gathered sequences from many organisms.
After creating the database, I began to learn the technique of machine learning, which is teaching the computer how to classify something based on a training set of data. Thus, the goal of my project was to predict mutations in these two genes, based on data I had gathered and information from my computer.
The main reason I wanted to complete this project was to delve deeper into the field of biocomputation. I am interested in biology and computer science, so this project exposed me to the intersection of these two areas, through research. I also wanted to learn more about computer science. Learning Python gave me a head start on programming.
The first step in my project was to teach myself Python, so that was an entire learning experience in itself! Overall, this project acquainted me to the world of independent research; I had to do a lot of decision-making and problem solving, as I turned down many different paths to find the right one. In general, I learned much more about genomics and programming. This project has allowed me to see the bigger picture that is the interconnection of biology and computer science, exposing me to the importance of applying advanced technologies to biological concepts. Therefore, with the knowledge of possible solutions to seemingly inexorable health issues, I hope to continue research like this in college, and beyond!