MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification

By Tongxin Wang, Wei Shao, Zhi Huang, Haixu Tang, J. Zhang, Zhengming Ding, Kun Huang. Nature Communications, 2021

575 citations recorded by the source corpus.

To fully utilize the advances in omics technologies and achieve a more comprehensive understanding of human diseases, novel computational methods are required for integrative analysis of multiple types of omics data. Here, we present a novel multi-omics integrative method named Multi-Omics Graph cOnvolutional NETworks (MOGONET) for biomedical classification. MOGONET jointly explores omics-specific learning and cross-omics correlation learning for effective multi-omics data classification. We demonstrate that MOGONET outperforms other state-of-the-art supervised multi-omics integrative analysis approaches from different biomedical classification applications using mRNA expression data, DNA methylation data, and microRNA expression data. Furthermore, MOGONET can identify important biomarkers from different omics data types related to the investigated biomedical problems. Our understanding of human disease can be improved by integrating the abundance of high throughput biomedical data. Here, the authors use deep learning methods successfully used on images to integrate various types of omics data to improve patient classification and identify disease biomarkers.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/e53678ce8beacb74a3952d7ff8dea7d0cdea2281

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Artificial intelligence in cancer target identification and drug discovery (2022, background): “Second, Wang et al. sequentially select such proteins as seed connectors that maximally increase the size of the largest connected component of the subnetwork until there is no additional protein that can be selected as a seed connector.”
Deep Multimodal Data Fusion (2024, methodology): “For instance, Wang et al. [185] propose multi-omics GCNs for a biomedical classification task, in which the model utilizes GCN to extract independent features from three modalities, i.e., mRNA expression data, DNA methylation data, and microRNA expression data, separately.”
Trusted Multi-View Classification With Dynamic Evidential Fusion (2022, background): “Besides, there are studies that integrate decisions from different sources through learnable models [59], [60], [61],”
Multimodal biomedical AI (2022, background): “Graph neural networks are one example; 18,19 these are deep learning model”