Estimating gene expression from DNA methylation and copy number variation: A deep learning regression model for multi-omics integration

Seal, Dibyendu Bikash; Das, Vivek; Goswami, Saptarsi; De, Rajat K.

doi:10.1016/j.ygeno.2020.03.021

Cited by 44 publications

(26 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The datasets used in this work are about HGS-OvCa, and the clinical data include these molecular subtypes for most of the samples. Although these molecular subtypes are transcriptional (e.g., mRNA), they can be used for other omics data analysis due to their correlation or association with transcriptional data [55][56][57][58] . For example, authors in 55 have reported that DNA methylation is often negatively associated with gene expression in promoter regions, while DNA methylation is often positively associated with gene expression in gene bodies.…”

Section: Vae/mmd-vae Architecture Standard Vaementioning

confidence: 99%

“…Even these non-transcriptional datasets, especially the DNA methylation dataset, show a good classification performance with an accuracy range 72.3-75.2%. This performance could be due to the association or correlation between the omics datasets [55][56][57][58] . For the same reason, the use of integrated nontranscriptional and transcriptional data helps to maintain a similar performance or improve the performances of the transcriptional subtypes clustering and classification.…”

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Integrated multi-omics analysis of ovarian cancer using variational autoencoders

Hira

Razzaque

Angione

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Cancer is a complex disease that deregulates cellular functions at various molecular levels (e.g., DNA, RNA, and proteins). Integrated multi-omics analysis of data from these levels is necessary to understand the aberrant cellular functions accountable for cancer and its development. In recent years, Deep Learning (DL) approaches have become a useful tool in integrated multi-omics analysis of cancer data. However, high dimensional multi-omics data are generally imbalanced with too many molecular features and relatively few patient samples. This imbalance makes a DL based integrated multi-omics analysis difficult. DL-based dimensionality reduction technique, including variational autoencoder (VAE), is a potential solution to balance high dimensional multi-omics data. However, there are few VAE-based integrated multi-omics analyses, and they are limited to pancancer. In this work, we did an integrated multi-omics analysis of ovarian cancer using the compressed features learned through VAE and an improved version of VAE, namely Maximum Mean Discrepancy VAE (MMD-VAE). First, we designed and developed a DL architecture for VAE and MMD-VAE. Then we used the architecture for mono-omics, integrated di-omics and tri-omics data analysis of ovarian cancer through cancer samples identification, molecular subtypes clustering and classification, and survival analysis. The results show that MMD-VAE and VAE-based compressed features can respectively classify the transcriptional subtypes of the TCGA datasets with an accuracy in the range of 93.2-95.5% and 87.1-95.7%. Also, survival analysis results show that VAE and MMD-VAE based compressed representation of omics data can be used in cancer prognosis. Based on the results, we can conclude that (i) VAE and MMD-VAE outperform existing dimensionality reduction techniques, (ii) integrated multi-omics analyses perform better or similar compared to their mono-omics counterparts, and (iii) MMD-VAE performs better than VAE in most omics dataset.

show abstract

Section: Vae/mmd-vae Architecture Standard Vaementioning

confidence: 99%

Section: Classificationmentioning

confidence: 99%

Integrated multi-omics analysis of ovarian cancer using variational autoencoders

Hira

Razzaque

Angione

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Deep learning has already been applied to predict alternative poly-adenylation [ 101 , 102 ], noncoding variants that interfere with splicing [ 103 , 104 ], gene regulatory networks [ 105 , 106 , 107 , 108 ], the expression of copy number variants [ 109 ], and in single-cells [ 110 , 111 ] or the targets of non-coding RNAs.…”

Section: The Virtual Gene Concept Can Define a Practical Research Pro...mentioning

confidence: 99%

Virtual Gene Concept and a Corresponding Pragmatic Research Program in Genetical Data Science

Huminiecki

2021

Entropy

View full text Add to dashboard Cite

Mendel proposed an experimentally verifiable paradigm of particle-based heredity that has been influential for over 150 years. The historical arguments have been reflected in the near past as Mendel’s concept has been diversified by new types of omics data. As an effect of the accumulation of omics data, a virtual gene concept forms, giving rise to genetical data science. The concept integrates genetical, functional, and molecular features of the Mendelian paradigm. I argue that the virtual gene concept should be deployed pragmatically. Indeed, the concept has already inspired a practical research program related to systems genetics. The program includes questions about functionality of structural and categorical gene variants, about regulation of gene expression, and about roles of epigenetic modifications. The methodology of the program includes bioinformatics, machine learning, and deep learning. Education, funding, careers, standards, benchmarks, and tools to monitor research progress should be provided to support the research program.

show abstract

“…Multi-omics analysis combining transcriptome and methylome could systematically detect the variation of different pathways, discover biomarkers, and help identify therapeutic targets and inform the medication management. This could more accurately summarise the occurrence and development of the disease than single analysis [ 25 ]. However, multi-omics analysis has not previously been applied in osteosarcoma model research.…”

Section: Introductionmentioning

confidence: 99%

Multi-omics analysis based on 3D-bioprinted models innovates therapeutic target discovery of osteosarcoma

Lin

Yang

Yuan

et al. 2022

Bioactive Materials

View full text Add to dashboard Cite

Estimating gene expression from DNA methylation and copy number variation: A deep learning regression model for multi-omics integration

Cited by 44 publications

References 41 publications

Integrated multi-omics analysis of ovarian cancer using variational autoencoders

Integrated multi-omics analysis of ovarian cancer using variational autoencoders

Virtual Gene Concept and a Corresponding Pragmatic Research Program in Genetical Data Science

Multi-omics analysis based on 3D-bioprinted models innovates therapeutic target discovery of osteosarcoma

Contact Info

Product

Resources

About