mosGraphGen: a novel tool to generate multi-omics signaling graphs to facilitate integrative and interpretable graph AI model development

Heming Zhang; Dekang Cao; Zirui Chen; Xiuyuan Zhang; Yixin Chen; Cole Sessions; Carlos Cruchaga; Philip Payne; Guangfu Li; Michael Province; Fuhai Li

doi:10.1093/bioadv/vbae151

mosGraphGen: a novel tool to generate multi-omics signaling graphs to facilitate integrative and interpretable graph AI model development

Bioinform Adv. 2024 Oct 8;4(1):vbae151. doi: 10.1093/bioadv/vbae151. eCollection 2024.

Authors

Heming Zhang¹, Dekang Cao¹, Zirui Chen¹, Xiuyuan Zhang¹, Yixin Chen², Cole Sessions³, Carlos Cruchaga^{4

5

6}, Philip Payne¹, Guangfu Li⁷, Michael Province⁸, Fuhai Li^{1

3

6}

Affiliations

¹ Institute for Informatics, Data Science and Biostatistics (I2DB), Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.
² Department of Computer Science and Engineering, Washington University in St. Louis, Saint Louis, MO 63130, United States.
³ Department of Pediatrics, Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.
⁴ Department of Psychiatry, Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.
⁵ Hope Center for Neurological Disorders, Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.
⁶ NeuroGenomics and Informatics Center, Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.
⁷ Department of Surgery, School of Medicine, University of Connecticut, Farmington, CT 06030, United States.
⁸ Division of Statistical Genomics, Department of Genetics, Washington University School of Medicine, Saint Louis, MO 63110-1010, United States.

Abstract

Motivation: Multi-omics data, i.e. genomics, epigenomics, transcriptomics, proteomics, characterize cellular complex signaling systems from multi-level and multi-view and provide a holistic view of complex cellular signaling pathways. However, it remains challenging to integrate and interpret multi-omics data for mining critical biomarkers. Graph AI models have been widely used to analyze graph-structure datasets, and are ideal for integrative multi-omics data analysis because they can naturally integrate and represent multi-omics data as a biologically meaningful multi-level signaling graph and interpret multi-omics data via graph node and edge ranking analysis. Nevertheless, it is nontrivial for graph-AI model developers to pre-analyze multi-omics data and convert the data into biologically meaningful graphs, which can be directly fed into graph-AI models.

Results: To resolve this challenge, we developed mosGraphGen (multi-omics signaling graph generator), generating Multi-omics Signaling graphs (mos-graph) of individual samples by mapping multi-omics data onto a biologically meaningful multi-level background signaling network with data normalization by aggregating measurements and aligning to the reference genome. With mosGraphGen, AI model developers can directly apply and evaluate their models using these mos-graphs. In the results, mosGraphGen was used and illustrated using two widely used multi-omics datasets of The Cancer Genome Atlas (TCGA) and Alzheimer's disease (AD) samples.

Availability and implementation: The code of mosGraphGen is open-source and publicly available via GitHub: https://github.com/FuhaiLiAiLab/mosGraphGen.