Lana Garmire, PhD
Assistant Professor, Cancer Epidemiology Program, University of Hawaii Cancer Center
Title: Machine-Learning and Deep-Learning Based Genomics Data Integration on Cancer Biomarker Discoveries
Abstract: With the rapid applications of high throughput technologies such as next generation sequencing, it is particularly urgent to detecting biomarkers arising from different high-throughput platforms. In this talk, I will elaborate recent research effort in my research group that aim to integrate the omics profiles for cancer diagnosis and prognosis prediction. We have constructed a versatile individual- oriented pathway-based modeling framework from multiple omics data types to predict patient prognosis and/or diagnosis. The pathway-level predictors perform better than the gene-based predictors, and achieve even better results when combined with clinical features. Additionally, we have initiated deep-learning based mutli-omics prognosis biomarker investigation, and demonstrated the robust predictive power in multiple liver cancer cohorts of various omics data types. I will end my talk with recent improvement on heterogeneity detection among single-cell cancer genomics data.