Presenter: Silu Huang, Graduate Research Assistant

Advisor: Prof. Aditya Parameswaran

Title: Genvisage: rapid identification of discriminative features for genomic data analysis

Abstract: Given two different classes of samples and a feature-sample matrix, our goal is to find the TOP-K feature pairs separating these two classes. Many biological applications fit in this framework, e.g., characterizing differentially expressed genes (DEGs). Our design principle is to prioritize running time over accuracy, serving as a data exploration tool before investing in more time-consuming methods. We propose to use the light-weighted rocchio classifier to separate different classes, and have been developing different optimization strategies to reduce the running time in finding best feature pairs.