Comparison of Scanpy-based algorithms to remove the batch effect from single-cell RNA-seq data

AbstractWith the development of single-cell RNA sequencing (scRNA-seq) technology, analysts need to integrate hundreds of thousands of cells with multiple experimental batches. It is becoming increasingly difficult for users to select the best integration methods to remove batch effects. Here, we compared the advantages and limitations of four commonly used Scanpy-based batch-correction methods using two representative and large-scale scRNA-seq datasets. We quantitatively evaluated batch-correction performance and efficiency. Furthermore, we discussed the performance differences among the evaluated methods at the algorithm level.

Download Full-text

deepMNN: Deep Learning-Based Single-Cell RNA Sequencing Data Batch Correction Using Mutual Nearest Neighbors

Frontiers in Genetics ◽

10.3389/fgene.2021.708981 ◽

2021 ◽

Vol 12 ◽

Author(s):

Bin Zou ◽

Tongda Zhang ◽

Ruilong Zhou ◽

Xiaosen Jiang ◽

Huanming Yang ◽

...

Keyword(s):

Deep Learning ◽

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Cell Types ◽

Batch Effect ◽

Batch Effects ◽

Batch Correction ◽

Single Cell Rna Sequencing ◽

Identical Cell

It is well recognized that batch effect in single-cell RNA sequencing (scRNA-seq) data remains a big challenge when integrating different datasets. Here, we proposed deepMNN, a novel deep learning-based method to correct batch effect in scRNA-seq data. We first searched mutual nearest neighbor (MNN) pairs across different batches in a principal component analysis (PCA) subspace. Subsequently, a batch correction network was constructed by stacking two residual blocks and further applied for the removal of batch effects. The loss function of deepMNN was defined as the sum of a batch loss and a weighted regularization loss. The batch loss was used to compute the distance between cells in MNN pairs in the PCA subspace, while the regularization loss was to make the output of the network similar to the input. The experiment results showed that deepMNN can successfully remove batch effects across datasets with identical cell types, datasets with non-identical cell types, datasets with multiple batches, and large-scale datasets as well. We compared the performance of deepMNN with state-of-the-art batch correction methods, including the widely used methods of Harmony, Scanorama, and Seurat V4 as well as the recently developed deep learning-based methods of MMD-ResNet and scGen. The results demonstrated that deepMNN achieved a better or comparable performance in terms of both qualitative analysis using uniform manifold approximation and projection (UMAP) plots and quantitative metrics such as batch and cell entropies, ARI F1 score, and ASW F1 score under various scenarios. Additionally, deepMNN allowed for integrating scRNA-seq datasets with multiple batches in one step. Furthermore, deepMNN ran much faster than the other methods for large-scale datasets. These characteristics of deepMNN made it have the potential to be a new choice for large-scale single-cell gene expression data analysis.

Download Full-text

A Comprehensive Multi-Center Cross-platform Benchmarking Study of Single-cell RNA Sequencing Using Reference Samples

10.1101/2020.03.27.010249 ◽

2020 ◽

Author(s):

Wanqiu Chen ◽

Yongmei Zhao ◽

Xin Chen ◽

Xiaojiang Xu ◽

Zhaowei Yang ◽

...

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Cell Types ◽

Batch Effect ◽

Batch Effects ◽

Data Set ◽

Batch Correction ◽

Single Cell Rna Sequencing ◽

Cross Platform ◽

Reference Samples

AbstractSingle-cell RNA sequencing (scRNA-seq) has become a very powerful technology for biomedical research and is becoming much more affordable as methods continue to evolve, but it is unknown how reproducible different platforms are using different bioinformatics pipelines, particularly the recently developed scRNA-seq batch correction algorithms. We carried out a comprehensive multi-center cross-platform comparison on different scRNA-seq platforms using standard reference samples. We compared six pre-processing pipelines, seven bioinformatics normalization procedures, and seven batch effect correction methods including CCA, MNN, Scanorama, BBKNN, Harmony, limma and ComBat to evaluate the performance and reproducibility of 20 scRNA-seq data sets derived from four different platforms and centers. We benchmarked scRNA-seq performance across different platforms and testing sites using global gene expression profiles as well as some cell-type specific marker genes. We showed that there were large batch effects; and the reproducibility of scRNA-seq across platforms was dictated both by the expression level of genes selected and the batch correction methods used. We found that CCA, MNN, and BBKNN all corrected the batch variations fairly well for the scRNA-seq data derived from biologically similar samples across platforms/sites. However, for the scRNA-seq data derived from or consisting of biologically distinct samples, limma and ComBat failed to correct batch effects, whereas CCA over-corrected the batch effect and misclassified the cell types and samples. In contrast, MNN, Harmony and BBKNN separated biologically different samples/cell types into correspondingly distinct dimensional subspaces; however, consistent with this algorithm’s logic, MNN required that the samples evaluated each contain a shared portion of highly similar cells. In summary, we found a great cross-platform consistency in separating two distinct samples when an appropriate batch correction method was used. We hope this large cross-platform/site scRNA-seq data set will provide a valuable resource, and that our findings will offer useful advice for the single-cell sequencing community.

Download Full-text

Correcting batch effects in single-cell RNA sequencing data by matching mutual nearest neighbours

10.1101/165118 ◽

2017 ◽

Cited By ~ 15

Author(s):

Laleh Haghverdi ◽

Aaron T. L. Lun ◽

Michael D. Morgan ◽

John C. Marioni

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Data Sets ◽

Batch Effects ◽

Sequencing Data ◽

Batch Correction ◽

Nearest Neighbours ◽

Single Cell Rna Sequencing ◽

New Strategy

AbstractThe presence of batch effects is a well-known problem in experimental data analysis, and single- cell RNA sequencing (scRNA-seq) is no exception. Large-scale scRNA-seq projects that generate data from different laboratories and at different times are rife with batch effects that can fatally compromise integration and interpretation of the data. In such cases, computational batch correction is critical for eliminating uninteresting technical factors and obtaining valid biological conclusions. However, existing methods assume that the composition of cell populations are either known or the same across batches. Here, we present a new strategy for batch correction based on the detection of mutual nearest neighbours in the high-dimensional expression space. Our approach does not rely on pre-defined or equal population compositions across batches, only requiring that a subset of the population be shared between batches. We demonstrate the superiority of our approach over existing methods on a range of simulated and real scRNA-seq data sets. We also show how our method can be applied to integrate scRNA-seq data from two separate studies of early embryonic development.

Download Full-text

BERMUDA: A novel deep transfer learning method for single-cell RNA sequencing batch correction reveals hidden high-resolution cellular subtypes

10.1101/641191 ◽

2019 ◽

Cited By ~ 1

Author(s):

Tongxin Wang ◽

Travis S Johnson ◽

Wei Shao ◽

Zixiao Lu ◽

Bryan R Helm ◽

...

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Transfer Learning ◽

Cell Types ◽

Batch Effect ◽

Batch Effects ◽

Combine Data ◽

Batch Correction ◽

Single Cell Rna Sequencing ◽

Bona Fide

AbstractTo fully utilize the power of single-cell RNA sequencing (scRNA-seq) technologies for cell lineation and identifyingbona fidetranscriptional signals, it is necessary to combine data from multiple experiments. We presentBERMUDA(Batch-Effect ReMoval Using Deep Autoencoders) — a novel transfer-learning-based method for batch-effect correction in scRNA-seq data.BERMUDAeffectively combines different batches of scRNA-seq data with vastly different cell population compositions and amplifies biological signals by transferring information among batches. We demonstrate thatBERMUDAoutperforms existing methods for removing batch effects and distinguishing cell types in multiple simulated and real scRNA-seq datasets.

Download Full-text

SSCC: a novel computational framework for rapid and accurate clustering large single cell RNA-seq data

10.1101/344242 ◽

2018 ◽

Cited By ~ 2

Author(s):

Xianwen Ren ◽

Liangtao Zheng ◽

Zemin Zhang

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Random Projection ◽

Rna Seq ◽

Sequencing Data ◽

Computational Framework ◽

Human Blood Cells ◽

Single Cell Rna Sequencing ◽

Data Volume

ABSTRACTClustering is a prevalent analytical means to analyze single cell RNA sequencing data but the rapidly expanding data volume can make this process computational challenging. New methods for both accurate and efficient clustering are of pressing needs. Here we proposed a new clustering framework based on random projection and feature construction for large scale single-cell RNA sequencing data, which greatly improves clustering accuracy, robustness and computational efficacy for various state-of-the-art algorithms benchmarked on multiple real datasets. On a dataset with 68,578 human blood cells, our method reached 20% improvements for clustering accuracy and 50-fold acceleration but only consumed 66% memory usage compared to the widely-used software package SC3. Compared to k-means, the accuracy improvement can reach 3-fold depending on the concrete dataset. An R implementation of the framework is available from https://github.com/Japrin/sscClust.

Download Full-text

SHARP: Single-cell RNA-seq Hyper-fast and Accurate Processing via Ensemble Random Projection

10.1101/461640 ◽

2018 ◽

Cited By ~ 2

Author(s):

Shibiao Wan ◽

Junil Kim ◽

Kyoung Jae Won

Keyword(s):

Dimension Reduction ◽

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Random Projection ◽

Rna Seq ◽

Running Speed ◽

Large Size ◽

Single Cell Rna Sequencing ◽

Speed And Accuracy

ABSTRACTTo process large-scale single-cell RNA-sequencing (scRNA-seq) data effectively without excessive distortion during dimension reduction, we present SHARP, an ensemble random projection-based algorithm which is scalable to clustering 10 million cells. Comprehensive benchmarking tests on 17 public scRNA-seq datasets demonstrate that SHARP outperforms existing methods in terms of speed and accuracy. Particularly, for large-size datasets (>40,000 cells), SHARP’s running speed far excels other competitors while maintaining high clustering accuracy and robustness. To the best of our knowledge, SHARP is the only R-based tool that is scalable to clustering scRNA-seq data with 10 million cells.

Download Full-text

Vacuum-Driven Micropump with Support Columns: Toward Large Scale Single-Cell RNA-Sequencing

2018 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) ◽

10.1109/marss.2018.8481157 ◽

2018 ◽

Author(s):

Kento Hisa ◽

Musashi Kakugawa ◽

Takayuki Shibata ◽

Moeto Nagai

Keyword(s):

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Single Cell Rna Sequencing

Download Full-text

Assessing the measurement transfer function of single-cell RNA sequencing

10.1101/045450 ◽

2016 ◽

Author(s):

Hannah R. Dueck ◽

Rizi Ai ◽

Adrian Camarena ◽

Bo Ding ◽

Reymundo Dominguez ◽

...

Keyword(s):

Transfer Function ◽

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Transfer Functions ◽

Single Cells ◽

Biological Information ◽

Gene Detection ◽

Single Cell Rna Sequencing ◽

Scale Control

AbstractRecently, measurement of RNA at single cell resolution has yielded surprising insights. Methods for single-cell RNA sequencing (scRNA-seq) have received considerable attention, but the broad reliability of single cell methods and the factors governing their performance are still poorly known. Here, we conducted a large-scale control experiment to assess the transfer function of three scRNA-seq methods and factors modulating the function. All three methods detected greater than 70% of the expected number of genes and had a 50% probability of detecting genes with abundance greater than 2 to 4 molecules. Despite the small number of molecules, sequencing depth significantly affected gene detection. While biases in detection and quantification were qualitatively similar across methods, the degree of bias differed, consistent with differences in molecular protocol. Measurement reliability increased with expression level for all methods and we conservatively estimate the measurement transfer functions to be linear above ~5-10 molecules. Based on these extensive control studies, we propose that RNA-seq of single cells has come of age, yielding quantitative biological information.

Download Full-text

Flexible comparison of batch correction methods for single-cell RNA-seq using BatchBench

10.1101/2020.05.22.111211 ◽

2020 ◽

Author(s):

Ruben Chazarra-Gil ◽

Stijn van Dongen ◽

Vladimir Yu Kiselev ◽

Martin Hemberg

Keyword(s):

Single Cell ◽

Computational Methods ◽

Rna Seq ◽

Batch Effects ◽

Systematic Comparison ◽

Batch Correction ◽

Link Type ◽

Biological Signals ◽

The Cost

AbstractAs the cost of single-cell RNA-seq experiments has decreased, an increasing number of datasets are now available. Combining newly generated and publicly accessible datasets is challenging due to non-biological signals, commonly known as batch effects. Although there are several computational methods available that can remove batch effects, evaluating which method performs best is not straightforward. Here we present BatchBench (https://github.com/cellgeni/batchbench), a modular and flexible pipeline for comparing batch correction methods for single-cell RNA-seq data. We apply BatchBench to eight methods, highlighting their methodological differences and assess their performance and computational requirements through a compendium of well-studied datasets. This systematic comparison guides users in the choice of batch correction tool, and the pipeline makes it easy to evaluate other datasets.

Download Full-text