The joint graphical lasso for inverse covariance estimation across multiple classes

TL;DR

This paper introduces the joint graphical lasso, a method for estimating multiple related graphical models simultaneously, improving accuracy by borrowing strength across classes, especially useful in high-dimensional gene expression data analysis.

Contribution

The paper proposes a novel joint graphical lasso approach that estimates multiple related graphical models together, utilizing fused or group lasso penalties for improved accuracy in high-dimensional settings.

Findings

Outperforms competing methods in simulation studies

Provides more accurate network and covariance estimation

Successfully applied to lung cancer gene expression data

Abstract

We consider the problem of estimating multiple related but distinct graphical models on the basis of a high-dimensional data set with observations that belong to distinct classes. A motivating example occurs in the analysis of gene expression data for tissue samples with and without cancer. In this case, we might wish to estimate a gene expression network for the normal tissue and a gene expression network for the tumor tissue. We expect the two gene expression networks to be similar but not identical to each other, and so more accurate estimation of these two networks may be possible using a joint approach. We propose the joint graphical lasso for this purpose. Rather than estimating a graphical model for each class separately, or a single graphical model across all classes, we borrow strength across the classes in order to estimate multiple graphical models that share certain characteristics, such as the locations or weights of nonzero edges. Our approach is based upon maximizing a penalized log likelihood. We employ fused lasso or group lasso penalties, and implement a very fast computational approach that solves the joint graphical lasso problem. In a simulation study we demonstrate that our proposed approach leads to more accurate estimation of networks and covariance structure than competing approaches. We further illustrate our proposal on a publicly-available lung cancer gene expression data set.