Unsupervised classification of multi-omics data during cardiac remodeling using deep learning

• Published in: Methods (San Diego, Calif.) Vol. 166; pp. 66 - 73
• Main Authors: Chung, Neo Christopher, Mirza, Bilal, Choi, Howard, Wang, Jie, Wang, Ding, Ping, Peipei, Wang, Wei
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.08.2019
• Subjects: algorithms; analytical methods; Cardiovascular; cardiovascular diseases; Clustering; computational methodology; Integrative analysis; metabolites; mice; Multi-omics; neural networks; proteins; time series analysis; Time-series; Unsupervised deep learning; Unsupervised deep learning; Integrative analysis; Time-series; Clustering; Cardiovascular; Multi-omics
• ISSN: 1046-2023; 1095-9130; 1095-9130
• DOI: 10.1016/j.ymeth.2019.03.004

•Metabolites and proteins respond to cardiac remodeling with coherent patterns.•Unsupervised deep learning (DL) helps uncover the temporal trends in multi-omics.•DL methods generated more biologically meaningful clusters than conventional methods.•DCEC, optimizing featuring learning and clustering jointly, outperformed other methods. Integration of multi-omics in cardiovascular diseases (CVDs) presents high potentials for translational discoveries. By analyzing abundance levels of heterogeneous molecules over time, we may uncover biological interactions and networks that were previously unidentifiable. However, to effectively perform integrative analysis of temporal multi-omics, computational methods must account for the heterogeneity and complexity in the data. To this end, we performed unsupervised classification of proteins and metabolites in mice during cardiac remodeling using two innovative deep learning (DL) approaches. First, long short-term memory (LSTM)-based variational autoencoder (LSTM-VAE) was trained on time-series numeric data. The low-dimensional embeddings extracted from LSTM-VAE were then used for clustering. Second, deep convolutional embedded clustering (DCEC) was applied on images of temporal trends. Instead of a two-step procedure, DCEC performes a joint optimization for image reconstruction and cluster assignment. Additionally, we performed K-means clustering, partitioning around medoids (PAM), and hierarchical clustering. Pathway enrichment analysis using the Reactome knowledgebase demonstrated that DL methods yielded higher numbers of significant biological pathways than conventional clustering algorithms. In particular, DCEC resulted in the highest number of enriched pathways, suggesting the strength of its unified framework based on visual similarities. Overall, unsupervised DL is shown to be a promising analytical approach for integrative analysis of temporal multi-omics.