Prediction of Time Series Gene Expression and Structural Analysis of Gene Regulatory Networks Using Recurrent Neural Networks.

Michele Monti,Edoardo Milanetti,Giorgio Gosti,Jonathan Fiorentino,Gian Gaetano Tartaglia

doi:10.3390/e24020141

Abstract

Methods for time series prediction and classification of gene regulatory networks (GRNs) from gene expression data have been treated separately so far. The recent emergence of attention-based recurrent neural network (RNN) models boosted the interpretability of RNN parameters, making them appealing for the understanding of gene interactions. In this work, we generated synthetic time series gene expression data from a range of archetypal GRNs and we relied on a dual attention RNN to predict the gene temporal dynamics. We show that the prediction is extremely accurate for GRNs with different architectures. Next, we focused on the attention mechanism of the RNN and, using tools from graph theory, we found that its graph properties allow one to hierarchically distinguish different architectures of the GRN. We show that the GRN responded differently to the addition of noise in the prediction by the RNN and we related the noise response to the analysis of the attention mechanism. In conclusion, this work provides a way to understand and exploit the attention mechanism of RNNs and it paves the way to RNN-based methods for time series prediction and inference of GRNs from gene expression data.

Highlights

Recent technological innovations, such as chromatin immunoprecipitation sequencing (ChIP-seq) and RNA sequencing (RNA-seq), allow complex networks formed by interactions among proteins, DNA and RNA to be systematic studied [1]
The recent emergence of high-throughput experimental techniques for gene expression measurement led to the development of a wide range of computational methods to obtain an accurate picture of the interactions among transcription factors (TFs) and their target genes, which is known as the gene regulatory networks (GRNs) inference problem [12,13,14,15]
We implemented a deep neural network model that relies on the dual-stage attentionbased recurrent neural network (DA-RNN) for time series prediction [45], which has been developed in order to predict the behavior of a target quantity in a stochastic ensemble of time traces

Summary

Introduction

Recent technological innovations, such as chromatin immunoprecipitation sequencing (ChIP-seq) and RNA sequencing (RNA-seq), allow complex networks formed by interactions among proteins, DNA and RNA to be systematic studied [1]. These approaches are strongly advancing system biology and open up new opportunities in medicine, allowing us to study complex diseases that affect several genes [2,3]. Deep learning models have been recently employed to understand gene regulation [16,17] or to infer GRNs from imaging [18] and RNA-seq gene expression data [19,20] For this reason, we investigated how deep neural networks (DNN) can be exploited to classify GRNs considering different network topologies

Objectives

Methods

Results

Conclusion