GNisi: A graph network for reconstructing Ising models from multivariate binarized data
This provides a more accurate tool for researchers in fields like biology who need to reconstruct Ising models from data, though it is an incremental improvement over existing methods.
The paper tackles the computationally challenging problem of inferring Ising model parameters from multivariate binarized data by introducing GNisi, a graph neural network method trained on known models, and shows it is more accurate than existing state-of-the-art software, as applied to gene expression data.
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.