Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2024 Sep 3:2024.08.01.606219.
doi: 10.1101/2024.08.01.606219.

mosGraphFlow: a novel integrative graph AI model mining disease targets from multi-omic data

Heming Zhang  1 , Dekang Cao  1   2 , Tim Xu  1   2 , Emily Chen  1   3 , Guangfu Li  4 , Yixin Chen  2 , Philip Payne  1 , Michael Province  5 , Fuhai Li  1   6
Affiliations

mosGraphFlow: a novel integrative graph AI model mining disease targets from multi-omic data

Heming Zhang et al. bioRxiv. .

Abstract

Multi-omic data can better characterize complex cellular signaling pathways from multiple views compared to individual omic data. However, integrative multi-omic data analysis to rank key disease biomarkers and infer core signaling pathways remains an open problem. In this study, our novel contributions are that we developed a novel graph AI model, mosGraphFlow, for analyzing multi-omic signaling graphs (mosGraphs), 2) analyzed multi-omic mosGraph datasets of AD, and 3) identified, visualized and evaluated a set of AD associated signaling biomarkers and network. The comparison results show that the proposed model not only achieves the best classification accuracy but also identifies important AD disease biomarkers and signaling interactions. Moreover, the signaling sources are highlighted at specific omic levels to facilitate the understanding of the pathogenesis of AD. The proposed model can also be applied and expanded for other studies using multi-omic data. Model code is accessible via GitHub: https://github.com/FuhaiLiAiLab/mosGraphFlow.

PubMed Disclaimer

Conflict of interest statement

Declarations Competing interests The authors declare no competing interests.

Figures

Figure 1.
Figure 1.
Architecture of mosGraphFlow
Figure 2.
Figure 2.
Top 70 important nodes signaling network interaction in AD samples
Figure 3.
Figure 3.
Top 70 important nodes signaling network interaction in non-AD samples
Figure 4.
Figure 4.
Bar chart displaying the weight of important genes in AD and non-AD samples, ranking by their p-values. (The red dashed line indicates a p-value threshold of 0.05)
Figure 5.
Figure 5.
Top 70 important nodes signaling network interaction in females
Figure 6.
Figure 6.
Top 70 important nodes signaling network interaction in males
Figure 7.
Figure 7.
Bar chart displaying the weight of important genes in female and male, ranking by their p-values. (The red dashed line indicates a p-value threshold of 0.05)
Figure 8.
Figure 8.
Lollipop plot showing the negative base-10 logarithm of the False Discovery Rate (FDR) and number of genes of the top 20 signaling pathways based on the top 70 gene features found to be associated with AD. Generated by ShinyGo 0.80 after performing pathway enrichment analysis with FDR cutoff at 0.05.
Figure 9.
Figure 9.
Sankey diagram illustrating the relationship between the identified signaling pathways and corresponding genes using the top 70 genes features found to be associated with AD
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Zeliger H. Oxidative Stress: Its Mechanisms and Impacts on Human Health and Disease Onset. (Academic Press, 2022).
    1. MAPPING A BETTER FUTURE FOR DEMENTIA CARE NAVIGATION.
    1. Kipf T. N. & Welling M. Semi-supervised classification with graph convolutional networks. 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings 1–14 (2017).
    1. Hamilton W. L., Ying R. & Leskovec J. Inductive representation learning on large graphs. Adv Neural Inf Process Syst 2017-Decem, 1025–1035 (2017).
    1. Veličković P. et al. Graph attention networks. 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings 1–12 (2018).

Publication types

LinkOut - more resources