MOMA: a Multi-task Attention Learning Algorithm for Multi-omics Data Interpretation and Classification

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2022 Feb 14

PMID 35157023

Authors

Sehwan Moon

Hyunju Lee

Affiliations

Soon will be listed here.

Abstract

Motivation: Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required.

Results: Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer's disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis.

Availability And Implementation: The source codes are available at https://github.com/dmcb-gist/MOMA.

Supplementary Information: Supplementary materials are available at Bioinformatics online.

Citing Articles

An Attention-Aware Multi-Task Learning Framework Identifies Candidate Targets for Drug Repurposing in Sarcopenia.

Reza M, Qiu C, Lin X, Su K, Liu A, Zhang X J Cachexia Sarcopenia Muscle. 2025; 16(2):e13661.

PMID: 40045692 PMC: 11883102. DOI: 10.1002/jcsm.13661.

Scalable randomized kernel methods for multiview data integration and prediction with application to Coronavirus disease.

Safo S, Lu H Biostatistics. 2025; 26(1).

PMID: 39973130 PMC: 11839864. DOI: 10.1093/biostatistics/kxaf001.

MMnc: multi-modal interpretable representation for non-coding RNA classification and class annotation.

Creux C, Zehraoui F, Radvanyi F, Tahi F Bioinformatics. 2025; 41(3).

PMID: 39891346 PMC: 11890286. DOI: 10.1093/bioinformatics/btaf051.

AI-driven multi-omics integration for multi-scale predictive modeling of genotype-environment-phenotype relationships.

Wu Y, Xie L Comput Struct Biotechnol J. 2025; 27:265-277.

PMID: 39886532 PMC: 11779603. DOI: 10.1016/j.csbj.2024.12.030.

Multiomics of Aging and Aging-Related Diseases.

Kiseleva O, Arzumanian V, Ikhalaynen Y, Kurbatov I, Kryukova P, Poverennaya E Int J Mol Sci. 2025; 25(24.

PMID: 39769433 PMC: 11677528. DOI: 10.3390/ijms252413671.

References

Chen H, Chiu Y, Zhang T, Zhang S, Huang Y, Chen Y . GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization. BMC Syst Biol. 2018; 12(Suppl 8):142. PMC: 6302374. DOI: 10.1186/s12918-018-0642-2. View

Elmarakeby H, Hwang J, Arafeh R, Crowdis J, Gang S, Liu D . Biologically informed deep neural network for prostate cancer discovery. Nature. 2021; 598(7880):348-352. PMC: 8514339. DOI: 10.1038/s41586-021-03922-4. View

Min W, Chang T, Zhang S, Wan X . TSCCA: A tensor sparse CCA method for detecting microRNA-gene patterns from multiple cancers. PLoS Comput Biol. 2021; 17(6):e1009044. PMC: 8195367. DOI: 10.1371/journal.pcbi.1009044. View

Huang L, Brunell D, Stephan C, Mancuso J, Yu X, He B . Driver network as a biomarker: systematic integration and network modeling of multi-omics data to derive driver signaling pathways for drug combination prediction. Bioinformatics. 2019; 35(19):3709-3717. PMC: 6761967. DOI: 10.1093/bioinformatics/btz109. View

Ma B, Meng F, Yan G, Yan H, Chai B, Song F . Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics data. Comput Biol Med. 2020; 121:103761. DOI: 10.1016/j.compbiomed.2020.103761. View

Chen H, Chan D . Mitochondrial dynamics--fusion, fission, movement, and mitophagy--in neurodegenerative diseases. Hum Mol Genet. 2009; 18(R2):R169-76. PMC: 2758711. DOI: 10.1093/hmg/ddp326. View

Zhang S, Liu C, Li W, Shen H, Laird P, Zhou X . Discovery of multi-dimensional modules by integrative analysis of cancer genomic data. Nucleic Acids Res. 2012; 40(19):9379-91. PMC: 3479191. DOI: 10.1093/nar/gks725. View

Li W, Wong W, Jiang R . DeepTACT: predicting 3D chromatin contacts via bootstrapping deep learning. Nucleic Acids Res. 2019; 47(10):e60. PMC: 6547469. DOI: 10.1093/nar/gkz167. View

Dwivedi S, Tjarnberg A, Tegner J, Gustafsson M . Deriving disease modules from the compressed transcriptional space embedded in a deep autoencoder. Nat Commun. 2020; 11(1):856. PMC: 7016183. DOI: 10.1038/s41467-020-14666-6. View

10.

Bennett D, Buchman A, Boyle P, Barnes L, Wilson R, Schneider J . Religious Orders Study and Rush Memory and Aging Project. J Alzheimers Dis. 2018; 64(s1):S161-S189. PMC: 6380522. DOI: 10.3233/JAD-179939. View

11.

Chen S, Liu Q, Cui X, Feng Z, Li C, Wang X . OpenAnnotate: a web server to annotate the chromatin accessibility of genomic regions. Nucleic Acids Res. 2021; 49(W1):W483-W490. PMC: 8262705. DOI: 10.1093/nar/gkab337. View

12.

Kanehisa M, Goto S . KEGG: kyoto encyclopedia of genes and genomes. Nucleic Acids Res. 1999; 28(1):27-30. PMC: 102409. DOI: 10.1093/nar/28.1.27. View

13.

Koh H, Fermin D, Vogel C, Choi K, Ewing R, Choi H . iOmicsPASS: network-based integration of multiomics data for predictive subnetwork discovery. NPJ Syst Biol Appl. 2019; 5:22. PMC: 6616462. DOI: 10.1038/s41540-019-0099-y. View

14.

Chen J, Zhang S . Discovery of two-level modular organization from matched genomic data via joint matrix tri-factorization. Nucleic Acids Res. 2018; 46(12):5967-5976. PMC: 6158745. DOI: 10.1093/nar/gky440. View

15.

Ding Q, Markesbery W, Chen Q, Li F, Keller J . Ribosome dysfunction is an early event in Alzheimer's disease. J Neurosci. 2005; 25(40):9171-5. PMC: 6725754. DOI: 10.1523/JNEUROSCI.3040-05.2005. View

16.

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

17.

Rudy C, Hunsberger H, Weitzner D, Reed M . The role of the tripartite glutamatergic synapse in the pathophysiology of Alzheimer's disease. Aging Dis. 2015; 6(2):131-48. PMC: 4365957. DOI: 10.14336/AD.2014.0423. View

18.

Manczak M, Park B, Jung Y, Reddy P . Differential expression of oxidative phosphorylation genes in patients with Alzheimer's disease: implications for early mitochondrial dysfunction and oxidative damage. Neuromolecular Med. 2004; 5(2):147-62. DOI: 10.1385/NMM:5:2:147. View

19.

Yang Z, Wu N, Liang Y, Zhang H, Ren Y . SMSPL: Robust Multimodal Approach to Integrative Analysis of Multiomics Data. IEEE Trans Cybern. 2020; 52(4):2082-2095. DOI: 10.1109/TCYB.2020.3006240. View

20.

Wu Y, Swaab D . Disturbance and strategies for reactivation of the circadian rhythm system in aging and Alzheimer's disease. Sleep Med. 2007; 8(6):623-36. DOI: 10.1016/j.sleep.2006.11.010. View