Skip to Main content Skip to Navigation
Conference papers

Multiomics Data Integration for Gene Regulatory Network Inference with Exponential Family Embeddings

Abstract : The advent of omics technologies has enabled the generation of huge, complex, heterogeneous, and high-dimensional omics data. Imposing numerous challenges in data integration, these data could lead to a better understanding of the organism's cellular system. Omics data are typically represented as networks to study relations between biological entities, such as protein-protein interaction, gene regulation, and signal transduction. To this end, network embedding approaches allow us to learn latent feature representations for nodes of a graph structure. In this study, we propose a new methodology to learn embeddings by modeling the underlying interactions among biological entities (nodes) with exponential family distributions from a well-chosen set of omics modalities. We evaluate our proposed method based on the gene regulatory network (GRN) inference problem. As the ground truth for evaluation, we use GRN available in public databases and demonstrate its effectiveness by comparing to other network integration approaches.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03336884
Contributor : Fragkiskos Malliaros <>
Submitted on : Tuesday, September 7, 2021 - 1:53:46 PM
Last modification on : Friday, September 10, 2021 - 3:33:20 AM

File

Multiomics_GRN_EUSIPCO_2021.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03336884, version 1

Citation

Surabhi Jagtap, Abdulkadir Çelikkanat, Aurélie Pirayre, Frederique Bidard, Laurent Duval, et al.. Multiomics Data Integration for Gene Regulatory Network Inference with Exponential Family Embeddings. 29th European Signal Processing Conference (EUSIPCO), Aug 2021, Dublin (Online), Ireland. ⟨hal-03336884⟩

Share

Metrics

Record views

35

Files downloads

3