DeepMoIC: Multi-omics Data Integration Via Deep Graph Convolutional Networks for Cancer Subtype Classification

Overview

Journal BMC Genomics

Publisher Biomed Central

Specialty Genetics

Date 2024 Dec 18

PMID 39695368

Authors

Jiecheng Wu

Zhaoliang Chen

Shunxin Xiao

Genggeng Liu

Wenjie Wu

Shiping Wang

Affiliations

Soon will be listed here.

Abstract

Background: Achieving precise cancer subtype classification is imperative for effective prognosis and treatment. Multi-omics studies, encompassing diverse data modalities, have emerged as powerful tools for unraveling the complexities of cancer. However, owing to the intricacies of biological data, multi-omics datasets generally show variations in data types, scales, and distributions. These intractable problems lead to challenges in exploring intact representations from heterogeneous data, which often result in inaccuracies in multi-omics information analysis.

Results: To address the challenges of multi-omics research, our approach DeepMoIC presents a novel framework derived from deep Graph Convolutional Network (GCN). Leveraging autoencoder modules, DeepMoIC extracts compact representations from omics data and incorporates a patient similarity network through the similarity network fusion algorithm. To handle non-Euclidean data and explore high-order omics information effectively, we design a Deep GCN module with two strategies: residual connection and identity mapping. With extracted higher-order representations, our approach consistently outperforms state-of-the-art models on a pan-cancer dataset and 3 cancer subtype datasets.

Conclusion: The introduction of Deep GCN shows encouraging performance in terms of supervised multi-omics feature learning, offering promising insights for precision medicine in cancer research. DeepMoIC can potentially be an important tool in the field of cancer subtype classification because of its capacity to handle complex multi-omics data and produce reliable classification findings.

References

Liu C, Duan Y, Zhou Q, Wang Y, Gao Y, Kan H . A classification method of gastric cancer subtype based on residual graph convolution network. Front Genet. 2023; 13:1090394. PMC: 9845413. DOI: 10.3389/fgene.2022.1090394. View

Sherman B, Hao M, Qiu J, Jiao X, Baseler M, Lane H . DAVID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update). Nucleic Acids Res. 2022; 50(W1):W216-W221. PMC: 9252805. DOI: 10.1093/nar/gkac194. View

Sun X, Jia X, Lu Z, Tang J, Li M . Drug repositioning with adaptive graph convolutional networks. Bioinformatics. 2023; 40(1). PMC: 10761094. DOI: 10.1093/bioinformatics/btad748. View

Xiao S, Lin H, Wang C, Wang S, Rajapakse J . Graph Neural Networks With Multiple Prior Knowledge for Multi-Omics Data Analysis. IEEE J Biomed Health Inform. 2023; 27(9):4591-4600. DOI: 10.1109/JBHI.2023.3284794. View

Goldman M, Craft B, Hastie M, Repecka K, McDade F, Kamath A . Visualizing and interpreting cancer genomics data via the Xena platform. Nat Biotechnol. 2020; 38(6):675-678. PMC: 7386072. DOI: 10.1038/s41587-020-0546-8. View

Picard M, Scott-Boyer M, Bodein A, Perin O, Droit A . Integration strategies of multi-omics data for machine learning analysis. Comput Struct Biotechnol J. 2021; 19:3735-3746. PMC: 8258788. DOI: 10.1016/j.csbj.2021.06.030. View

Yang B, Yang Y, Wang M, Su X . MRGCN: cancer subtyping with multi-reconstruction graph convolutional network using full and partial multi-omics dataset. Bioinformatics. 2023; 39(6). PMC: 10279523. DOI: 10.1093/bioinformatics/btad353. View

Zhang X, Liang L, Liu L, Tang M . Graph Neural Networks and Their Current Applications in Bioinformatics. Front Genet. 2021; 12:690049. PMC: 8360394. DOI: 10.3389/fgene.2021.690049. View

Marei H, Althani A, Afifi N, Hasan A, Caceci T, Pozzoli G . p53 signaling in cancer progression and therapy. Cancer Cell Int. 2021; 21(1):703. PMC: 8709944. DOI: 10.1186/s12935-021-02396-8. View

10.

Lu Y, Peng R, Dong L, Xia K, Wu R, Xu S . Multiomics dynamic learning enables personalized diagnosis and prognosis for pancancer and cancer subtypes. Brief Bioinform. 2023; 24(6). PMC: 10605059. DOI: 10.1093/bib/bbad378. View

11.

Tini G, Marchetti L, Priami C, Scott-Boyer M . Multi-omics integration-a comparison of unsupervised clustering methodologies. Brief Bioinform. 2017; 20(4):1269-1279. DOI: 10.1093/bib/bbx167. View

12.

Poirion O, Jing Z, Chaudhary K, Huang S, Garmire L . DeepProg: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data. Genome Med. 2021; 13(1):112. PMC: 8281595. DOI: 10.1186/s13073-021-00930-x. View

13.

Wang T, Shao W, Huang Z, Tang H, Zhang J, Ding Z . MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. Nat Commun. 2021; 12(1):3445. PMC: 8187432. DOI: 10.1038/s41467-021-23774-w. View

14.

Wen G, Li L . FGCNSurv: dually fused graph convolutional network for multi-omics survival prediction. Bioinformatics. 2023; 39(8). PMC: 10412406. DOI: 10.1093/bioinformatics/btad472. View

15.

Hasin Y, Seldin M, Lusis A . Multi-omics approaches to disease. Genome Biol. 2017; 18(1):83. PMC: 5418815. DOI: 10.1186/s13059-017-1215-1. View

16.

Li X, Ma J, Leng L, Han M, Li M, He F . MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis. Front Genet. 2022; 13:806842. PMC: 8847688. DOI: 10.3389/fgene.2022.806842. View

17.

Duchartre Y, Kim Y, Kahn M . The Wnt signaling pathway in cancer. Crit Rev Oncol Hematol. 2016; 99:141-9. PMC: 5853106. DOI: 10.1016/j.critrevonc.2015.12.005. View

18.

Huang A, Wang Z, Zheng Y, Zhao T, Lin C . Embedding Regularizer Learning for Multi-View Semi-Supervised Classification. IEEE Trans Image Process. 2021; 30:6997-7011. DOI: 10.1109/TIP.2021.3101917. View

19.

Huang D, Sherman B, Lempicki R . Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nat Protoc. 2009; 4(1):44-57. DOI: 10.1038/nprot.2008.211. View

20.

Wang W, Sun B, Yu M, Wu S, Liu D, Zhang H . GraphPLBR: Protein-Ligand Binding Residue Prediction With Deep Graph Convolution Network. IEEE/ACM Trans Comput Biol Bioinform. 2023; 20(3):2223-2232. DOI: 10.1109/TCBB.2023.3239983. View