Deep learning of gene relationships from single cell time-course expression data

Abstract

Motivation: Time-course gene expression data has been widely used to infer regulatory and signaling relationships between genes. Most of the widely used methods for such analysis were developed for bulk expression data. Single cell RNA-Seq (scRNA-Seq) data offers several advantages including the large number of expression profiles available and the ability to focus on individual cells rather than averages. However, this data also raises new computational challenges. Results: Using a novel encoding for scRNA-Seq expression data we develop deep learning methods for interaction prediction from time-course data. Our methods use a supervised framework which represents the data as a 3D tensor and train convolutional and recurrent neural networks (CNN and RNN) for predicting interactions. We tested our Time-course Deep Learning (TDL) models on five different time series scRNA-Seq datasets. As we show, TDL can accurately identify causal and regulatory gene-gene interactions and can also be used to assign new function to genes. TDL improves on prior methods for the above tasks and can be generally applied to new time series scRNA-Seq data.

DeepDRIM: a deep neural network to reconstruct cell-type-specific gene regulatory network using single-cell RNA-seq data

“…As same as CNNC, DeepDRIM can also make use of the sequence knowledge and be extended to work on the timecourse data [27,59]. Supplementary Figure S8 demonstrates the network structure of DeepDRIM to tackle with the motif position weight matrix.…”