Paper detail

Inference of Mixed Graphical Models for Dichotomous Phenotypes using Markov Random Field Model

In this article, we propose a new method named fused mixed graphical model (FMGM), which can infer network structures for dichotomous phenotypes. We assumed that the interplay of different omics markers is associated with disease status and proposed an FMGM-based method to detect the associated omics marker network difference. The statistical models of the networks were based on a pairwise Markov random field model, and penalty functions were added to minimize the effect of sparseness in the networks. The fast proximal gradient method (PGM) was used to optimize the target function. Method validity was measured using synthetic datasets that simulate power-law network structures, and it was found that FMGM showed superior performance, especially in terms of F1 scores, compared with the previous method inferring the networks sequentially (0.392 and 0.546). FMGM performed better not only in identifying the differences (0.217 and 0.410) but also in identifying the networks (0.492 and 0.572). The proposed method was applied to multi-omics profiles of 6-month-old infants with and without atopic dermatitis (AD), and different correlations were found between the abundance of microbial genes related to carotenoid biosynthesis and RNA degradation according to disease status, suggesting the importance of metabolism related to oxidative stress and microbial RNA balance.