Format

Send to

Choose Destination
Methods. 2019 Aug 15;166:66-73. doi: 10.1016/j.ymeth.2019.03.004. Epub 2019 Mar 7.

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

Author information

1
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA; Institute of Informatics, Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Banacha 2, 02-097 Warsaw, Poland. Electronic address: nchchung@gmail.com.
2
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA; Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA.
3
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA; Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA; Bioinformatics Interdepartmental Program, University of California Los Angeles, Los Angeles, CA 90095, USA.
4
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA; Department of Physiology, University of California Los Angeles, Los Angeles, CA 90095, USA; Scalable Analytics Institute (ScAi), University of California Los Angeles, Los Angeles, CA 90095, USA; Bioinformatics Interdepartmental Program, University of California Los Angeles, Los Angeles, CA 90095, USA; Department of Medicine (Cardiology), University of California Los Angeles, Los Angeles, CA 90095, USA.
5
NIH BD2K Center of Excellence for Biomedical Computing, University of California Los Angeles, Los Angeles, CA 90095, USA; Department of Computer Science, University of California Los Angeles, Los Angeles, CA 90095, USA; Scalable Analytics Institute (ScAi), University of California Los Angeles, Los Angeles, CA 90095, USA; Bioinformatics Interdepartmental Program, University of California Los Angeles, Los Angeles, CA 90095, USA. Electronic address: weiwang@cs.ucla.edu.

Abstract

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.

KEYWORDS:

Cardiovascular; Clustering; Integrative analysis; Multi-omics; Time-series; Unsupervised deep learning

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center