An official website of the United States government
Abstract Numerous single‐cell transcriptomic datasets from identical tissues or cell lines are generated from different laboratories or single‐cell RNA sequencing (scRNA‐seq) protocols. The denoising of these datasets to eliminate batch effects is crucial for data integration, ensuring accurate interpretation and comprehensive analysis of biological questions. Although many scRNA‐seq data integration methods exist, most are inefficient and/or not conducive to downstream analysis. Here, DeepBID, a novel deep learning‐based method for batch effect correction, non‐linear dimensionality reduction, embedding, and cell clustering concurrently, is introduced. DeepBID utilizes a negative binomial‐based autoencoder with dual Kullback–Leibler divergence loss functions, aligning cell points from different batches within a consistent low‐dimensional latent space and progressively mitigating batch effects through iterative clustering. Extensive validation on multiple‐batch scRNA‐seq datasets demonstrates that DeepBID surpasses existing tools in removing batch effects and achieving superior clustering accuracy. When integrating multiple scRNA‐seq datasets from patients with Alzheimer's disease, DeepBID significantly improves cell clustering, effectively annotating unidentified cells, and detecting cell‐specific differentially expressed genes.
more »
« less
Application of Deep Learning on Single-Cell RNA Sequencing Data Analysis: A Review
Abstract Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.
more »
« less
- Award ID(s):
- 1750326
- PAR ID:
- 10506766
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Genomics, Proteomics & Bioinformatics
- Volume:
- 20
- Issue:
- 5
- ISSN:
- 1672-0229
- Format(s):
- Medium: X Size: p. 814-835
- Size(s):
- p. 814-835
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
BackgroundUnderstanding genetic underpinnings of immune-mediated inflammatory diseases is crucial to improve treatments. Single-cell RNA sequencing (scRNA-seq) identifies cell states expanded in disease, but often overlooks genetic causality due to cost and small genotyping cohorts. Conversely, large genome-wide association studies (GWAS) are commonly accessible. MethodsWe present a 3-step robust benchmarking analysis of integrating GWAS and scRNA-seq to identify genetically relevant cell states and genes in inflammatory diseases. First, we applied and compared the results of three recent algorithms, based on pathways (scGWAS), single-cell disease scores (scDRS), or both (scPagwas), according to accuracy/sensitivity and interpretability. While previous studies focused on coarse cell types, we used disease-specific, fine-grained single-cell atlases (183,742 and 228,211 cells) and GWAS data (Ns of 97,173 and 45,975) for rheumatoid arthritis (RA) and ulcerative colitis (UC). Second, given the lack of scRNA-seq for many diseases with GWAS, we further tested the tools’ resolution limits by differentiating between similar diseases with only one fine-grained scRNA-seq atlas. Lastly, we provide a novel evaluation of noncoding SNP incorporation methods by testing which enabled the highest sensitivity/accuracy of known cell-state calls. ResultsWe first found that single-cell based tools scDRS and scPagwas called superior numbers of supported cell states that were overlooked by scGWAS. While scGWAS and scPagwas were advantageous for gene exploration, scDRS effectively accounted for batch effect and captured cellular heterogeneity of disease-relevance without single-cell genotyping. For noncoding SNP integration, we found a key trade-off between statistical power and confidence with positional (e.g. MAGMA) and non-positional approaches (e.g. chromatin-interaction, eQTL). Even when directly incorporating noncoding SNPs through 5’ scRNA-seq measures of regulatory elements, non disease-specific atlases gave misleading results by not containing disease-tissue specific transcriptomic patterns. Despite this criticality of tissue-specific scRNA-seq, we showed that scDRS enabled deconvolution of two similar diseases with a single fine-grained scRNA-seq atlas and separate GWAS. Indeed, we identified supported and novel genetic-phenotype linkages separating RA and ankylosing spondylitis, and UC and crohn’s disease. Overall, while noting evolving single-cell technologies, our study provides key findings for integrating expanding fine-grained scRNA-seq, GWAS, and noncoding SNP resources to unravel the complexities of inflammatory diseases.more » « less
-
Abstract Single-cell RNA sequencing (scRNA-seq) is a widely used technique for characterizing individual cells and studying gene expression at the single-cell level. Clustering plays a vital role in grouping similar cells together for various downstream analyses. However, the high sparsity and dimensionality of large scRNA-seq data pose challenges to clustering performance. Although several deep learning-based clustering algorithms have been proposed, most existing clustering methods have limitations in capturing the precise distribution types of the data or fully utilizing the relationships between cells, leaving a considerable scope for improving the clustering performance, particularly in detecting rare cell populations from large scRNA-seq data. We introduce DeepScena, a novel single-cell hierarchical clustering tool that fully incorporates nonlinear dimension reduction, negative binomial-based convolutional autoencoder for data fitting, and a self-supervision model for cell similarity enhancement. In comprehensive evaluation using multiple large-scale scRNA-seq datasets, DeepScena consistently outperformed seven popular clustering tools in terms of accuracy. Notably, DeepScena exhibits high proficiency in identifying rare cell populations within large datasets that contain large numbers of clusters. When applied to scRNA-seq data of multiple myeloma cells, DeepScena successfully identified not only previously labeled large cell types but also subpopulations in CD14 monocytes, T cells and natural killer cells, respectively.more » « less
-
Abstract Single-cell RNA-sequencing (scRNA-seq) has been widely used for disease studies, where sample batches are collected from donors under different conditions including demographic groups, disease stages, and drug treatments. It is worth noting that the differences among sample batches in such a study are a mixture of technical confounders caused by batch effect and biological variations caused by condition effect. However, current batch effect removal methods often eliminate both technical batch effect and meaningful condition effect, while perturbation prediction methods solely focus on condition effect, resulting in inaccurate gene expression predictions due to unaccounted batch effect. Here we introduce scDisInFact, a deep learning framework that models both batch effect and condition effect in scRNA-seq data. scDisInFact learns latent factors that disentangle condition effect from batch effect, enabling it to simultaneously perform three tasks: batch effect removal, condition-associated key gene detection, and perturbation prediction. We evaluate scDisInFact on both simulated and real datasets, and compare its performance with baseline methods for each task. Our results demonstrate that scDisInFact outperforms existing methods that focus on individual tasks, providing a more comprehensive and accurate approach for integrating and predicting multi-batch multi-condition single-cell RNA-sequencing data.more » « less
-
Abstract The advancement of single cell RNA-sequencing (scRNA-seq) technology has enabled the direct inference of co-expressions in specific cell types, facilitating our understanding of cell-type-specific biological functions. For this task, the high sequencing depth variations and measurement errors in scRNA-seq data present two significant challenges, and they have not been adequately addressed by existing methods. We propose a statistical approach, CS-CORE, for estimating and testing cell-type-specific co-expressions, that explicitly models sequencing depth variations and measurement errors in scRNA-seq data. Systematic evaluations show that most existing methods suffered from inflated false positives as well as biased co-expression estimates and clustering analysis, whereas CS-CORE gave accurate estimates in these experiments. When applied to scRNA-seq data from postmortem brain samples from Alzheimer’s disease patients/controls and blood samples from COVID-19 patients/controls, CS-CORE identified cell-type-specific co-expressions and differential co-expressions that were more reproducible and/or more enriched for relevant biological pathways than those inferred from existing methods.more » « less
