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

Chazarra-Gil, Ruben; Dongen, Stijn van; Kiselev, Vladimir Yu; Hemberg, Martin

doi:10.1101/2020.05.22.111211

Cited by 12 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…however, these methods typically rank outside the top three when used for complex real data scenarios, which is in agreement with recent benchmarks on simpler batch structures 10,24 . In contrast, on more complex integration tasks, BBKNN, Scanorama (embeddings), and scVI performed well.…”

Section: Discussionsupporting

confidence: 87%

See 1 more Smart Citation

Benchmarking atlas-level data integration in single-cell genomics

Luecken

Büttner

Chaichoompu

et al. 2020

Preprint

117

142

View full text Add to dashboard Cite

Cell atlases often include samples that span locations, labs, and conditions, leading to complex, nested batch effects in data. Thus, joint analysis of atlas datasets requires reliable data integration .Choosing a data integration method is a challenge due to the difficulty of defining integration success. Here, we benchmark 38 method and preprocessing combinations on 77 batches of gene expression, chromatin accessibility, and simulation data from 23 publications, altogether representing >1.2 million cells distributed in nine atlas-level integration tasks. Our integration tasks span several common sources of variation such as individuals, species, and experimental labs. We evaluate methods according to scalability, usability, and their ability to remove batch effects while retaining biological variation.Using 14 evaluation metrics, we find that highly variable gene selection improves the performance of data integration methods, whereas scaling pushes methods to prioritize batch removal over conservation of biological variation. Overall, BBKNN, Scanorama, and scVI perform well, particularly on complex integration tasks; Seurat v3 performs well on simpler tasks with distinct biological signals; and methods that prioritize batch removal perform best for ATAC-seq data integration. Our freely available reproducible python module can be used to identify optimal data integration methods for new data, benchmark new methods, and improve method development.2

show abstract

Section: Discussionsupporting

confidence: 87%

“…The diversity in output formats from data integration methods poses a challenge to fair benchmarking 24 . Although input data are consistently preprocessed, requirements on scaling and HVG selection also differ between methods.…”

Section: Single-cell Integration Benchmarking (Scib)mentioning

confidence: 99%

Benchmarking atlas-level data integration in single-cell genomics

Luecken

Büttner

Chaichoompu

et al. 2020

Preprint

117

142

View full text Add to dashboard Cite

show abstract

“…For both the combined human kidney and Tabula Muris datasets, many cell types from the individual datasets did not overlap. Moreover, it has been shown that merging datasets can distort expression profiles 74 . For these reasons, batch-correction methods were not used on the concatenated datasets, as this might remove biological signal in addition to batch effects.…”

Section: Datasets Usedmentioning

confidence: 99%

Predicting the impact of sequence motifs on gene regulation using single-cell data

Hepkema

Stewart

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Binding of transcription factors (TFs) at proximal promoters and distal enhancers is central to gene regulation. Yet, identification of TF binding sites, also known as regulatory motifs, and quantification of their impact remains challenging. Here we present scover, a convolutional neural network model that can discover putative regulatory motifs along with their cell type-specific importance from single-cell data. Analysis of scRNA-seq data from human kidney shows that ETS, YY1 and NRF1 are the most important motif families for proximal promoters. Using multiple mouse tissues we obtain for the first time a model with cell type resolution which explains 34% of the variance in gene expression. Finally, by applying scover to distal enhancers identified using scATAC-seq from the mouse cerebral cortex we highlight the emergence of layer specific regulatory patterns during development.

show abstract

“…A benchmarking study showed that LIGER, Seurat V3, and Harmony perform better than other existing methods through comprehensive comparisons among 14 state-of-the-art methods [17]. However, recent large-scale benchmarking studies [18,19] suggested that method performance is dependent on the complexity of the integration task and multiple batches introduce additional difficulties for those methods that perform well for two batches. Moreover, these methods did not explicitly distinguish technical variation from biological variation when aligning multiple single-cell datasets, which might mitigate biological variation as well when removing technical variation.…”

Section: Introductionmentioning

confidence: 99%

scMC learns biological variation through the alignment of multiple single-cell genomics datasets

2021

View full text Add to dashboard Cite

Distinguishing biological from technical variation is crucial when integrating and comparing single-cell genomics datasets across different experiments. Existing methods lack the capability in explicitly distinguishing these two variations, often leading to the removal of both variations. Here, we present an integration method scMC to remove the technical variation while preserving the intrinsic biological variation. scMC learns biological variation via variance analysis to subtract technical variation inferred in an unsupervised manner. Application of scMC to both simulated and real datasets from single-cell RNA-seq and ATAC-seq experiments demonstrates its capability of detecting context-shared and context-specific biological signals via accurate alignment.

show abstract

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

Cited by 12 publications

References 41 publications

Benchmarking atlas-level data integration in single-cell genomics

Benchmarking atlas-level data integration in single-cell genomics

Predicting the impact of sequence motifs on gene regulation using single-cell data

scMC learns biological variation through the alignment of multiple single-cell genomics datasets

Contact Info

Product

Resources

About