Biologists work with a multitude of protein sequences represented by strings of letters. The amino acid sequence of these proteins allows us to leverage various machine learning Natural Language Processing algorithms aimed to predict enzyme classifications which are indicative of both protein structure and functionality. Our goal is to propose a multi level classification solution that is designed to predict the respective class of a given enzyme. Our approach consists of predicting the classification of an enzyme by applying NLP to a protein sequence. Our method utilizes BERT (Bidirectional Encoder Representations from Transformers) models to create embeddings, or feature vectors, and a variety of machine learning models to predict the respective class and subclass of an enzyme.