Senior Capstone Project
The project is focused on developing optimal neural network models through Python to predict cancerous tissue type based on the gene expression levels found in tissue samples. The majority of data sets used exceed 500 million entries and required large amounts of data manipulation and transformation before model fitting.
The goal application of the model is to correctly classify tissue samples based on gene expression levels as tissue samples used in bioinformatics can often be mislabeled and incorrectly associated with a body part. The aim of the model is to be used to cross-reference the original tissue label and validate the classification for quality assurance in a research setting.