An official website of the United States government
Multi-omics data analysis has the potential to discover hidden molecular interactions, revealing potential regulatory and/or signal transduction pathways for cellular processes of interest when studying life and disease systems. One of critical challenges when dealing with real-world multi-omics data is that they may manifest heterogeneous structures and data quality as often existing data may be collected from different subjects under different conditions for each type of omics data. We propose a novel deep Bayesian generative model to efficiently infer a multi-partite graph encoding molecular interactions across such heterogeneous views, using a fused Gromov-Wasserstein (FGW) regularization between latent representations of corresponding views for integrative analysis. With such an optimal transport regularization in the deep Bayesian generative model, it not only allows incorporating view-specific side information, either with graph-structured or unstructured data in different views, but also increases the model flexibility with the distribution-based regularization. This allows efficient alignment of heterogeneous latent variable distributions to derive reliable interaction predictions compared to the existing point-based graph embedding methods. Our experiments on several real-world datasets demonstrate enhanced performance of MoReL in inferring meaningful interactions compared to existing baselines.
more »
« less
BayReL: Bayesian Relational Learning for Multi-omics Data Integration
High-throughput molecular profiling technologies have produced high-dimensional multi-omics data, enabling systematic understanding of living systems at the genome scale. Studying molecular interactions across different data types helps reveal signal transduction mechanisms across different classes of molecules. In this paper, we develop a novel Bayesian representation learning method that infers the relational interactions across multi-omics data types. Our method, Bayesian Relational Learning (BayReL) for multi-omics data integration, takes advantage of a priori known relationships among the same class of molecules, modeled as a graph at each corresponding view, to learn view-specific latent variables as well as a multi-partite graph that encodes the interactions across views. Our experiments on several real-world datasets demonstrate enhanced performance of BayReL in inferring meaningful interactions compared to existing baselines.
more »
« less
- PAR ID:
- 10209353
- Date Published:
- Journal Name:
- Advances in neural information processing systems
- Volume:
- 33
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Multi-omics data analysis has the potential to discover hidden molecular interactions, revealing potential regulatory and/or signal transduction pathways for cellular processes of interest when studying life and disease systems. One of critical challenges when dealing with real-world multi-omics data is that they may manifest heterogeneous structures and data quality as often existing data may be collected from different subjects under different conditions for each type of omics data. We propose a novel deep Bayesian generative model to efficiently infer a multi-partite graph encoding molecular interactions across such heterogeneous views, using a fused Gromov-Wasserstein (FGW) regularization between latent representations of corresponding views for integrative analysis. With such an optimal transport regularization in the deep Bayesian generative model, it not only allows incorporating view-specific side information, either with graph-structured or unstructured data in different views, but also increases the model flexibility with the distribution-based regularization. This allows efficient alignment of heterogeneous latent variable distributions to derive reliable interaction predictions compared to the existing point-based graph embedding methods. Our experiments on several real-world datasets demonstrate enhanced performance of MoReL in inferring meaningful interactions compared to existing baselines.more » « less
-
Elucidation of complex molecular networks requires integrative analysis of molecular features and changes at different levels of information flow and regulation. Accordingly, high throughput functional genomics tools such as transcriptomics, proteomics, metabolomics, and lipidomics have emerged to provide system-wide investigations. Unfortunately, analysis of different types of biomolecules requires specific sample extraction procedures in combination with specific analytical instrumentation. The most efficient extraction protocols often only cover a restricted type of biomolecules due to their different physicochemical properties. Therefore, several sets/aliquots of samples are needed for extracting different molecules. Here we adapted a biphasic fractionation method to extract proteins, metabolites, and lipids from the same sample (3-in-1) for liquid chromatography-tandem mass spectrometry (LC-MS/MS) multi-omics. To demonstrate utility of the improved method, we used bacteria-primed Arabidopsis leaves to generate multi-omics datasets from the same sample. In total, we were able to analyze 1849 proteins, 1967 metabolites, and 424 lipid species in single samples. The molecules cover a wide range of biological and molecular processes, and allow quantitative analyses of different molecules and pathways. Our results have shown the clear advantages of the multi-omics method, including sample conservation, high reproducibility, and tight correlation between different types of biomolecules.more » « less
-
Abstract The integration of multi-omics data is essential for achieving a comprehensive understanding of molecular systems and enhancing the performance of predictive models in biomedical research. However, many existing models have limited capacity to capture cross-omics feature interactions, which hinders the depth of integration. In this study, we introduce SynOmics, a graph convolutional network framework designed to improve multi-omics integration by constructing omics networks in the feature space and modeling both within- and cross-omics dependencies. By incorporating both omics-specific networks and cross-omics bipartite networks, SynOmics enables simultaneous learning of intra-omics and inter-omics relationships. Unlike traditional approaches that rely on early or late integration strategies, SynOmics adopts a parallel learning strategy to process feature-level interactions at each layer of the model. Experimental results demonstrate that SynOmics consistently outperforms state-of-the-art multi-omics integration methods across a range of biomedical classification tasks, highlighting its potential for biomarker discovery and clinical applications.more » « less
-
Accurate cancer subtype prediction is crucial for personalized medicine. Integrating multi-omics data represents a viable approach to comprehending the intricate pathophysiology of complex diseases like cancer. Conventional machine learning techniques are not ideal for analyzing the complex interrelationships among different categories of omics data. Numerous models have been suggested using graph-based learning to uncover veiled representations and network formations unique to distinct types of omics data to heighten predictions regarding cancers and characterize patients’ profiles, amongst other applications aimed at improving disease management in medical research. The existing graph-based state-of-the-art multi-omics integration approaches for cancer subtype prediction, MOGONET, and SUPREME, use a graph convolutional network (GCN), which fails to consider the level of importance of neighboring nodes on a particular node. To address this gap, we hypothesize that paying attention to each neighbor or providing appropriate weights to neighbors based on their importance might improve the cancer subtype prediction. The natural choice to determine the importance of each neighbor of a node in a graph is to explore the graph attention network (GAT). Here, we propose MOGAT, a novel multi-omics integration approach, leveraging GAT models that incorporate graph-based learning with an attention mechanism. MOGAT utilizes a multi-head attention mechanism to extract appropriate information for a specific sample by assigning unique attention coefficients to neighboring samples. Based on our knowledge, our group is the first to explore GAT in multi-omics integration for cancer subtype prediction. To evaluate the performance of MOGAT in predicting cancer subtypes, we explored two sets of breast cancer data from TCGA and METABRIC. Our proposed approach, MOGAT, outperforms MOGONET by 32% to 46% and SUPREME by 2% to 16% in cancer subtype prediction in different scenarios, supporting our hypothesis. Our results also showed that GAT embeddings provide a better prognosis in differentiating the high-risk group from the low-risk group than raw features.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- The DOI is not currently available.
