Convex Biclustering

• Activity Number: 588
• Type: Topic Contributed
• Date/Time: Thursday, August 7, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Eric Chi*+ and Genevera Allen and Richard G. Baraniuk
• Companies: Rice University and Rice University/Baylor College of Medicine and Rice University
• Keywords: Convex Optimization ; Biclustering ; mRNA-sequencing ; Fused Lasso ; Clustering ; Penalization

Abstract

In the biclustering problem, we seek to simultaneously group observations and features. While biclustering has applications in a wide array of domains, ranging from text mining to collaborative filtering, identifying structure in high dimensional genomic data motivates this work. In this context, biclustering enables us to identify subsets of genes that are co-expressed only within a subset of experimental conditions. We present a convex formulation of the biclustering problem that possesses a unique global minimizer and an iterative algorithm that is guaranteed to identify it. Our approach generates an entire solution path of possible biclusters as a single tuning regularization parameter is varied. The key contributions of our work are its simplicity, interpretability, and algorithmic guarantees - features that arguably are lacking in the current alternative algorithms. We demonstrate our method on some real mRNA-seq data.