Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method

Abstract

Alzheimer’s disease (AD) is a severe neurodegenerative disease for which there is currently no effective treatment. Mild cognitive impairment (MCI) is an early disease that may progress to AD. The effective diagnosis of AD and MCI in the early stage has important clinical significance.MethodsTo this end, this paper proposed a hypergraph-based netNMF (HG-netNMF) algorithm for integrating structural magnetic resonance imaging (sMRI) of AD and MCI with corresponding gene expression profiles.ResultsHypergraph regularization assumes that regions of interest (ROIs) and genes were located on a non-linear low-dimensional manifold and can capture the inherent prevalence of two modalities of data and mined high-order correlation features of the two data. Further, this paper used the HG-netNMF algorithm to construct a brain structure connection network and a protein interaction network (PPI) with potential role relationships, mine the risk (ROI) and key genes of both, and conduct a series of bioinformatics analyses.ConclusionFinally, this paper used the risk ROI and key genes of the AD and MCI groups to construct diagnostic models. The AUC of the AD group and MCI group were 0.8 and 0.797, respectively.

Identification of the methotrexate resistance-related diagnostic markers in osteosarcoma via adaptive total variation netNMF and multi-omics datasets

“…Three co-expression networks were created from these data: ME network , ME-GE network , and GE network . Based on the previous study ( Zhuang et al, 2023 ), the value of dimensionality reduction k generally is at most one-tenth of the minimum number of samples or features of the network modules. Therefore, in this study, k is set to 8, and the number of iterations is set to 200.…”

“…NetNMF uses the decomposed submatrices to construct co-expression networks, which may weaken the connectivity of the nodes in the network. Therefore, Zhuang et al proposed a hypergraph regularization constraint-based netNMF method (HG-netNMF) ( Zhuang et al, 2023 ), and Ding et al proposed a graph regularization-based netNMF method (NMFNA), both of which can better mine higher-order features between two genetic data compared to netNMF ( Ding et al, 2021 ). The above NMF-based network analysis method provides an effective way to understand the interactions of different genetic data to understand the pathogenic mechanisms of cancer.…”