Deep Learning Approach to Predict Lung Adenocarcinoma Recurrence

Poster Number: P162
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Deep Learning, Machine Learning, Cancer Genetics, Cancer Prevention, Bioinformatics, Omics (genomics, metabolomics, proteomics, transcriptomics, etc.) and Integrative Analyses
Primary Track: Applications
Programmatic Theme: Translational Bioinformatics

Our project examines the ability of Deep Learning (DL) models to predict Lung Adenocarcinoma (LUAD) recurrence (data from the LUAD TCGA PanCancer Atlas dataset). Our dataset included clinical features (age, sex, tumor type, clinical (TNM) and pathologic AJCC tumor staging), mrna expression Z-scores, non-synonymous mutation counts per gene, and gene methylation data. When compared to machine learning, DL model achieved high AUROC and AUPRC, and gave insights into the features most involved in LUAD recurrence.

Speaker(s):
Karma Hayek, BS
Brown University

Author(s):
Karma Hayek, BS - Brown University; Jessica Patricoski, PhD student, Computational Biology - Brown University Center for Computational Molecular Biology; Jeremy Warner, MD, MS - Brown University; Ece Uzun, PhD - Lifespan/Brown University;