Title
HIV Resistance Prediction using Feed Forward Neural Networks and Sequence Expansion Methodologies
Date of Award
5-2019
Document Type
Thesis open access
Department
Computer Science
First Advisor
Matthew A. Hibbs
Second Advisor
Mark Lewis
Third Advisor
Kevin Livingstone
Abstract
HIV is a chronic and debilitating disease affecting the lives of millions of people globally. While therapies to treat HIV are available, drug resistance is a consistent problem. For this reason, an effective means of determining drug resistance for a given isolate is needed. In this experiment, we use a simple Artificial Neural Network (ANN) model trained on phenotypically labeled sequences from HIVdb for resistance classifications. We also observe an interesting data processing method, and determine train and test set division before such data processing is optimal for network performance.
Recommended Citation
Luikart, Christopher S., "HIV Resistance Prediction using Feed Forward Neural Networks and Sequence Expansion Methodologies" (2019). Computer Science Honors Theses. 51.
https://digitalcommons.trinity.edu/compsci_honors/51