Gene Regulatory Network Inference using 3D Convolutional Neural Network

Citations Over TimeTop 10% of 2021 papers

Abstract

Gene regulatory networks (GRNs) consist of gene regulations between transcription factors (TFs) and their target genes. Single-cell RNA sequencing (scRNA-seq) brings both opportunities and challenges to the inference of GRNs. On the one hand, scRNA-seq data reveals statistic information of gene expressions at the single-cell resolution, which is conducive to the construction of GRNs; on the other hand, noises and dropouts pose great difficulties on the analysis of scRNA-seq data, causing low prediction accuracy by traditional methods. In this paper, we propose 3D Co-Expression Matrix Analysis (3DCEMA), which predicts regulatory relationships by classifying 3D co-expression matrices of gene triples using a 3D convolutional neural network. We found that by introducing a third gene as a comparison factor, our method can avoid the disturbance of noises and dropouts, and significantly increase the prediction accuracy of regulations between gene pairs. Compared with other existing GRN inference algorithms on both in-silico datasets and scRNA-Seq datasets, our algorithm based on deep learning shows higher stability and accuracy in the task of GRN inference.

Related Papers

• → Simultaneous classification of several features of a person’s appearance using a deep convolutional neural network(2015)10 cited
• → Feature extraction with convolutional neural networks for aerial image retrieval(2017)8 cited
• → Unconstrained Face Verification Based on Monogenic Binary Pattern and Convolutional Neural Network(2020)7 cited
• Approaching Bio Cellular Classification for Malaria Infected Cells Using Machine Learning and then Deep Learning to compare & analyze K-Nearest Neighbours and Deep CNNs.(2020)
• → Approaching Bio Cellular Classification for Malaria Infected Cells Using Machine Learning and then Deep Learning to compare & analyze K-Nearest Neighbours and Deep CNNs(2020)