The dataset I am using includes 83 features, 77 numerical and 5 categorical. The 77 numerical features are protein levels that were measured in different test groups of mice. The mice were either control and had no mutation, or had Down Syndrome. The goal of this project is to be able to produce a model that can connect protein levels to whether or not a mouse has Down Syndrome. If the model can accurately predict whether or not the mouse had Down Syndrome solely from the proteins, it will provide greater insight into our understanding of which proteins are involved in the mutation, as well as interactions of proteins once the mutation is present.