Online Archive of University of Virginia Scholarship
AI-Powered Prediction of Off-Target Effects in Genetic Engineering: A Bioinformatics and Machine Learning Approach; Navigating Ethical and Regulatory Frameworks in Genetic Engineering154 views
Author
Nieves, Natalie, School of Engineering and Applied Science, University of Virginia
Advisors
Morrison, Briana, Computer Science, University of Virginia
Wayland, Kent, Engineering, University of Virginia
Foley, Rider, Computer Science, University of Virginia
Vrugtman, Rosanna, Computer Science, University of Virginia
Abstract
The increasing concern over unintentional consequences in genetic engineering prompts the need for computational tools to predict and mitigate off-target effects. To lessen the possibility of unforeseen outcomes, I propose an Artificial Intelligence (AI) model designed to predict potential off-target effects of genetic modifications. The model would utilize advanced machine learning algorithms and use large and diverse genomic datasets to enhance accuracy. The design and implementation would involve the integration of deep learning algorithms and bioinformatics tools, requiring knowledge and skill in both computer science and genetics. Initial results indicate promising capabilities in identifying and understanding unintended consequences. However, further testing and evaluation are necessary to validate the model's accuracy across diverse genetic contexts.
Nieves, Natalie. AI-Powered Prediction of Off-Target Effects in Genetic Engineering: A Bioinformatics and Machine Learning Approach; Navigating Ethical and Regulatory Frameworks in Genetic Engineering. University of Virginia, School of Engineering and Applied Science, BS (Bachelor of Science), 2024-05-10, https://doi.org/10.18130/1gyn-df39.
