GNisi: A graph network for reconstructing Ising models from multivariate binarized data

TL;DR

This paper introduces GNisi, a graph neural network-based method for accurately inferring Ising model parameters from multivariate binary data, outperforming existing approaches and demonstrated on gene expression datasets.

Contribution

The paper presents a novel GNN-based approach, GNisi, for reconstructing Ising models from data, improving accuracy over current methods.

Findings

GNisi outperforms existing software in accuracy

Successfully applied to gene expression data

Provides a new tool for biological data analysis

Abstract

Ising models are a simple generative approach to describing interacting binary variables. They have proven useful in a number of biological settings because they enable one to represent observed many-body correlations as the separable consequence of many direct, pairwise statistical interactions. The inference of Ising models from data can be computationally very challenging and often one must be satisfied with numerical approximations or limited precision. In this paper we present a novel method for the determination of Ising parameters from data, called GNisi, which uses a Graph Neural network trained on known Ising models in order to construct the parameters for unseen data. We show that GNisi is more accurate than the existing state of the art software, and we illustrate our method by applying GNisi to gene expression data.