Serena Chen
Pronouns: she/ her
Research Mentor(s): Yongqun He
Research Mentor School/College/Department: / 0
Program:
Authors: Serena Chen, Anthony Huffman, Yongqun He
Session: Session 4: 1:40 pm – 2:30 pm
Poster: 76
Abstract
Our initiative is at the vanguard of enhancing antigen discovery for vaccine development, utilizing a revised UNIFAN (Unsupervised Single-cell Functional Annotation) neural network machine learning model to analyze complex genomic datasets. This effort seeks to isolate pivotal antigens that target specific pathogens more effectively, optimizing the vaccine development process. We undertake a systematic approach, initiating with the adaptation and refinement of the UNIFAN model across multiple datasets to establish its robustness. The next phase evaluates the model’s refined clustering and annotation capabilities, examining its proficiency in distinguishing between diverse bacterial datasets through modified gene set activity scoring. In adapting and fine-tuning UNIFAN, we are poised to deepen our understanding of antigen expression in varying conditions, thereby improving the precision of vaccine targeting. The anticipated outcomes from this study are set to broaden the utility of the UNIFAN model in infectious disease research, paving the way for more nuanced and impactful vaccine strategies.
