Stochastic Block Coordinate Frank-Wolfe Algorithm for Large-Scale Biological Network Alignment

TL;DR

This paper introduces a scalable stochastic block coordinate Frank-Wolfe algorithm tailored for large-scale biological network alignment, significantly reducing computational costs while maintaining accuracy in identifying conserved protein interactions.

Contribution

It presents a novel randomized block coordinate Frank-Wolfe algorithm with convergence guarantees, optimized for large biomedical data analysis tasks.

Findings

Effective in aligning protein-protein interaction networks

Reduces computational time and space per iteration

Successfully identifies conserved functional pathways in yeast networks

Abstract

With increasingly "big" data available in biomedical research, deriving accurate and reproducible biology knowledge from such big data imposes enormous computational challenges. In this paper, motivated by recently developed stochastic block coordinate algorithms, we propose a highly scalable randomized block coordinate Frank-Wolfe algorithm for convex optimization with general compact convex constraints, which has diverse applications in analyzing biomedical data for better understanding cellular and disease mechanisms. We focus on implementing the derived stochastic block coordinate algorithm to align protein-protein interaction networks for identifying conserved functional pathways based on the IsoRank framework. Our derived stochastic block coordinate Frank-Wolfe (SBCFW) algorithm has the convergence guarantee and naturally leads to the decreased computational cost (time and space) for each iteration. Our experiments for querying conserved functional protein complexes in yeast networks confirm the effectiveness of this technique for analyzing large-scale biological networks.