Yuhan Zhang
Pronouns: she/her/hers
Research Mentor(s): Yongqun He
Research Mentor School/College/Department: Lab Animal Medicine, Microbiology and Immunology, & Bioinformatics / Medicine
Program: UROP
Session: Session 7 (4:40pm – 5:30pm)
Authors: Yuhan Zhang, Anthony Huffman, Oliver He
Abstract
Vaccines are a vital tool in preventing infectious diseases by stimulating the immune system. However, developing an effective vaccine is a complex process that involves multiple stages. In recent years, machine learning and deep learning techniques have been used to improve the vaccine development process. This project aims to develop a neural network-based algorithm for predicting vaccine candidates using biological and physiochemical features from previous training data. The algorithm uses Fully Connected Layers (FCLs) with the ReLU activation function and Batch Normalization to construct models. The output layer contains two classes, representing protective and non-protective candidates. During training, the Adam Optimizer updates the weights and biases of the neural network, while the cross-entropy loss function is used to evaluate the performance of the model. By utilizing machine learning and deep learning techniques, this project seeks to improve the accuracy of vaccine candidate prediction, which could lead to the development of more effective vaccines in the future.
