Masters Applied Projects

Project 11

Using Machine Learning to Identify Epigenetic Features that Predict Cell Lines Responsiveness to Polycomb-Based Transcription Factor

Student:
Rachel Fisher

Mentors:
Dr. Benjamin Bartelle, PhD – Arizona State University, SBHSE
Dr. Christopher Plaisier, PhD – Arizona State University, SBHSE
Dr. Melissa Wilson, PhD - Arizona State University, SOLS

YouTube Link:
View the video link below before joining the zoom meeting

Zoom Link:
https://asu.zoom.us/j/87027033201


Abstract

Polycomb-based Transcription Factor (PcTF) has been shown to reactivate silenced interferon genes in the MCF7 breast cancer cell line, making it a promising potential cancer treatment. This study aims to use epigenetic features to predict which genes are responsive to PcTF with the ultimate goal of predicting which cancer cell lines may be responsive to PcTF. A feature matrix containing commonly seen epigenetic features extracted from MCF7 cells, previously identified in another study, will be used as an input for a variety of classification models. ChIP-seq and RNA-seq data from MCF7 cells will also be used to train and validate the accuracy of the classifiers. The accuracy of each model will be measured by its classification error, the receiver operating characteristic area under the curve, and the area under the precision-recall curve. The classifier determined to be the best based on these metrics will then be deconstructed to identify which epigenetic features are best able to predict PcTF sensitivity.