Prior knowledge-guided multilevel graph neural network for tumor risk prediction and interpretation via multi-omics data integration.

The interrelation and complementary nature of multi-omics data can provide valuable insights into the intricate molecular mechanisms underlying diseases. However, challenges such as limited sample size, high data dimensionality and differences in omics modalities pose significant obstacles to fully harnessing the potential of these data. The prior knowledge such as gene regulatory network and pathway information harbors useful gene-gene interaction and gene functional module information. To effectively integrate multi-omics data and make full use of the prior knowledge, here, we propose a Multilevel-graph neural network (GNN): a hierarchically designed deep learning algorithm that sequentially leverages multi-omics data, gene regulatory networks and pathway information to extract features and enhance accuracy in predicting survival risk. Our method achieved better accuracy compared with existing methods. Furthermore, key factors nonlinearly associated with the tumor pathogenesis are prioritized by employing two interpretation algorithms (i.e. GNN-Explainer and IGscore) for neural networks, at gene and pathway level, respectively. The top genes and pathways exhibit strong associations with disease in survival analyses, many of which such as SEC61G and CYP27B1 are previously reported in the literature.

Characterization of NAC Gene Family in Ammopiptanthus mongolicus and Functional Analysis of AmNAC24, an Osmotic and Cold-Stress-Induced NAC Gene.

The NAC family of transcription factors (TFs) is recognized as a significant group within the plant kingdom, contributing crucially to managing growth and development processes in plants, as well as to their response and adaptation to various environmental stressors. Ammopiptanthus mongolicus, a temperate evergreen shrub renowned for its remarkable resilience to low temperatures and drought stress, presents an ideal subject for investigating the potential involvement of NAC TFs in stress response mechanisms. Here, the structure, evolution, and expression profiles of NAC family TFs were analyzed systematically, and a cold and osmotic stress-induced member, AmNAC24, was selected and functionally characterized. A total of 86 NAC genes were identified in A. mongolicus, and these were divided into 15 groups. Up to 48 and 8 NAC genes were generated by segmental duplication and tandem duplication, respectively, indicating that segmental duplication is a predominant mechanism in the expansion of the NAC gene family in A. mongolicus. A considerable amount of NAC genes, including AmNAC24, exhibited upregulation in response to cold and osmotic stress. This observation is in line with the detection of numerous cis-acting elements linked to abiotic stress response in the promoters of A. mongolicus NAC genes. Subcellular localization revealed the nuclear residence of the AmNAC24 protein, coupled with demonstrable transcriptional activation activity. AmNAC24 overexpression enhanced the tolerance of cold and osmotic stresses in Arabidopsis thaliana, possibly by maintaining ROS homeostasis. The present study provided essential data for understanding the biological functions of NAC TFs in plants.