Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.

  title={Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis.},
  author={Mario Flores and Zhentao Liu and Ting-He Zhang and Md. Hasib and Yu-Chiao Chiu and Zhenqing Ye and Karla Paniagua and Sumin Jo and Jianqiu Zhang and Shou-Jiang Gao and Yu-Fang Jin and Yidong Chen and Yufei Huang},
  journal={Briefings in bioinformatics},
Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell… 

Figures and Tables from this paper


Supervised Adversarial Alignment of Single-Cell RNA-seq Data
By overcoming batch effects this method was able to correctly separate cell types, improving on several prior methods suggested for this task and analysis of the top features used by the network indicates that by taking the batch impact into account, the reduced representation is much better able to focus on key genes for each cell type.
Digitaldlsorter: Deep-Learning on scRNA-Seq to Deconvolute Gene Expression Data
A DL based method to enumerate and quantify the immune infiltration in colorectal and breast cancer bulk RNA-Seq samples starting from scRNA-Sequ, using a Deep Neural Network model that allows quantification not only of lymphocytes as a general population but also of specific CD8+, CD4Tmem, CD4Th and CD3regs subpopulations, as well as B-cells and Stromal content.
A comparison of deep learning-based pre-processing and clustering approaches for single-cell RNA sequencing data.
A systematic review for most popular single-cell RNA-seq analysis methods and tools based on deep learning models, involving the procedures of data preprocessing (quality control, normalization, data correction, dimensionality reduction and data visualization) and clustering task for downstream analysis.
Using neural networks for reducing the dimensions of single-cell RNA-Seq data
This work develops and test a method based on neural networks (NN) for the analysis and retrieval of single cell RNA-Seq data and shows that the NN method improves upon prior methods in both, the ability to correctly group cells in experiments not used in the training and the able to correctly infer cell type or state by querying a database of tens of thousands of singlecell profiles.
DEEPsc: A Deep Learning-Based Map Connecting Single-Cell Transcriptomics and Spatial Imaging Data
DEEPsc provides a data-adaptive tool to connect scRNA-seq datasets and spatial imaging datasets to analyze cell fate decisions and is compared with four existing methods on four biological systems to find that while DEEPsc has comparable accuracy to other methods, an improved balance between precision and robustness is achieved.
Imputation of single-cell gene expression with an autoencoder neural network
LATE and TRANSLATE outperform existing scRNA-seq imputation methods, achieving lower mean squared error in most cases, recovering nonlinear gene-gene relationships, and better separating cell types.
scIGANs: single-cell RNA-seq imputation using generative adversarial networks
This work demonstrated in many ways with compelling evidence that scIGANs is not only an application of GANs in omics data but also represents a competing imputation method for the scRNA-seq data.
A Hybrid Deep Clustering Approach for Robust Cell Type Profiling Using Single-cell RNA-seq Data
A new hybrid approach, Deep Unsupervised Single-cell Clustering (DUSC), is developed that integrates feature generation based on a deep learning architecture with a model-based clustering algorithm, to find a compact and informative representation of the single-cell transcriptomic data generating robust clusters.
Deep Generative Modeling for Single-cell Transcriptomics
Single-cell variational inference (scVI) is a ready-to-use generative deep learning tool for large-scale single-cell RNA-seq data that enables raw data processing and a wide range of rapid and accurate downstream analyses.
scGMAI: a Gaussian mixture model for clustering single-cell RNA-Seq data based on deep autoencoder.
The scGMAI is a new single-cell Gaussian mixture clustering method based on autoencoder networks and the fast independent component analysis (FastICA) that leads to outperforming results compared to existing tools, including Seurat, in clustering cells from 17 public scRNA-Seq datasets.