scMRA: A robust deep learning method to annotate scRNA-seq data with multiple reference datasets

2021 ◽  
Author(s):  
Musu Yuan ◽  
Liang Chen ◽  
Minghua Deng
Keyword(s):  
Deep Learning ◽  
Single Cell ◽  
Reference Data ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Supplementary Information ◽  
Batch Effects ◽  
Cell Type ◽  
Convolutional Network ◽  
Multiple Reference

Abstract Motivation Single-cell RNA-seq (scRNA-seq) has been widely used to resolve cellular heterogeneity. After collecting scRNA-seq data, the natural next step is to integrate the accumulated data to achieve a common ontology of cell types and states. Thus, an effective and efficient cell-type identification method is urgently needed. Meanwhile, high quality reference data remain a necessity for precise annotation. However, such tailored reference data are always lacking in practice. To address this, we aggregated multiple datasets into a meta-dataset on which annotation is conducted. Existing supervised or semi-supervised annotation methods suffer from batch effects caused by different sequencing platforms, the effect of which increases in severity with multiple reference datasets. Results Herein, a robust deep learning based single-cell Multiple Reference Annotator (scMRA) is introduced. In scMRA, a knowledge graph is constructed to represent the characteristics of cell types in different datasets, and a graphic convolutional network (GCN) serves as a discriminator based on this graph. scMRA keeps intra-cell-type closeness and the relative position of cell types across datasets. scMRA is remarkably powerful at transferring knowledge from multiple reference datasets, to the unlabeled target domain, thereby gaining an advantage over other state-of-the-art annotation methods in multi-reference data experiments. Furthermore, scMRA can remove batch effects. To the best of our knowledge, this is the first attempt to use multiple insufficient reference datasets to annotate target data, and it is, comparatively, the best annotation method for multiple scRNA-seq datasets. Availability An implementation of scMRA is available from https://github.com/ddb-qiwang/scMRA-torch Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals JIND: Joint Integration and Discrimination for Automated Single-Cell Annotation

2020 ◽  
Author(s):  
Mohit Goyal ◽  
Guillermo Serrano ◽  
Ilan Shomorony ◽  
Mikel Hernaez ◽  
Idoia Ochoa
Keyword(s):  
Single Cell ◽  
Cell Types ◽  
Marker Genes ◽  
Specific Marker ◽  
Rna Seq ◽  
Batch Effects ◽  
Cell Type ◽  
Latent Space ◽  
Cell Type Specific ◽  
Low Dimensional

AbstractSingle-cell RNA-seq is a powerful tool in the study of the cellular composition of different tissues and organisms. A key step in the analysis pipeline is the annotation of cell-types based on the expression of specific marker genes. Since manual annotation is labor-intensive and does not scale to large datasets, several methods for automated cell-type annotation have been proposed based on supervised learning. However, these methods generally require feature extraction and batch alignment prior to classification, and their performance may become unreliable in the presence of cell-types with very similar transcriptomic profiles, such as differentiating cells. We propose JIND, a framework for automated cell-type identification based on neural networks that directly learns a low-dimensional representation (latent code) in which cell-types can be reliably determined. To account for batch effects, JIND performs a novel asymmetric alignment in which the transcriptomic profile of unseen cells is mapped onto the previously learned latent space, hence avoiding the need of retraining the model whenever a new dataset becomes available. JIND also learns cell-type-specific confidence thresholds to identify and reject cells that cannot be reliably classified. We show on datasets with and without batch effects that JIND classifies cells more accurately than previously proposed methods while rejecting only a small proportion of cells. Moreover, JIND batch alignment is parallelizable, being more than five or six times faster than Seurat integration. Availability: https://github.com/mohit1997/JIND.

scholarly journals CHETAH: a selective, hierarchical cell type identification method for single-cell RNA sequencing

2019 ◽  
Vol 47 (16) ◽  
pp. e95-e95 ◽  
Author(s):  
Jurrian K de Kanter ◽  
Philip Lijnzaad ◽  
Tito Candelli ◽  
Thanasis Margaritis ◽  
Frank C P Holstege
Keyword(s):  
Single Cell ◽  
Rna Sequencing ◽  
Reference Data ◽  
Classification Tree ◽  
Cell Types ◽  
Biological Information ◽  
Identification Algorithm ◽  
Intermediate Cell ◽  
Cell Type ◽  
Single Cell Rna Sequencing

Abstract Cell type identification is essential for single-cell RNA sequencing (scRNA-seq) studies, currently transforming the life sciences. CHETAH (CHaracterization of cEll Types Aided by Hierarchical classification) is an accurate cell type identification algorithm that is rapid and selective, including the possibility of intermediate or unassigned categories. Evidence for assignment is based on a classification tree of previously available scRNA-seq reference data and includes a confidence score based on the variance in gene expression per cell type. For cell types represented in the reference data, CHETAH’s accuracy is as good as existing methods. Its specificity is superior when cells of an unknown type are encountered, such as malignant cells in tumor samples which it pinpoints as intermediate or unassigned. Although designed for tumor samples in particular, the use of unassigned and intermediate types is also valuable in other exploratory studies. This is exemplified in pancreas datasets where CHETAH highlights cell populations not well represented in the reference dataset, including cells with profiles that lie on a continuum between that of acinar and ductal cell types. Having the possibility of unassigned and intermediate cell types is pivotal for preventing misclassification and can yield important biological information for previously unexplored tissues.

scholarly journals Ensemble learning for classifying single-cell data and projection across reference atlases

2020 ◽  
Vol 36 (11) ◽  
pp. 3585-3587
Author(s):  
Lin Wang ◽  
Francisca Catalan ◽  
Karin Shamardani ◽  
Husam Babikir ◽  
Aaron Diaz
Keyword(s):  
Single Cell ◽  
Cell Types ◽  
Status Quo ◽  
Supplementary Information ◽  
Published Data ◽  
Supplementary Data ◽  
Cell Type ◽  
Low Sensitivity ◽  
Project Data ◽  
Cell Data

Abstract Summary Single-cell data are being generated at an accelerating pace. How best to project data across single-cell atlases is an open problem. We developed a boosted learner that overcomes the greatest challenge with status quo classifiers: low sensitivity, especially when dealing with rare cell types. By comparing novel and published data from distinct scRNA-seq modalities that were acquired from the same tissues, we show that this approach preserves cell-type labels when mapping across diverse platforms. Availability and implementation https://github.com/diazlab/ELSA Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Bulk Tissue Cell Type Deconvolution with Multi-Subject Single-Cell Expression Reference

2018 ◽  
Author(s):  
Xuran Wang ◽  
Jihwan Park ◽  
Katalin Susztak ◽  
Nancy R. Zhang ◽  
Mingyao Li
Keyword(s):  
Single Cell ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Tissue Cell ◽  
Specific Gene ◽  
Rna Seq ◽  
Cell Type ◽  
Cell Type Specific ◽  
Cell Expression

AbstractWe present MuSiC, a method that utilizes cell-type specific gene expression from single-cell RNA sequencing (RNA-seq) data to characterize cell type compositions from bulk RNA-seq data in complex tissues. When applied to pancreatic islet and whole kidney expression data in human, mouse, and rats, MuSiC outperformed existing methods, especially for tissues with closely related cell types. MuSiC enables characterization of cellular heterogeneity of complex tissues for identification of disease mechanisms.

scholarly journals The single-cell epigenetic regulatory landscape in mammalian perinatal testis development

2021 ◽  
Author(s):  
Jinyue Liao ◽  
Hoi Ching Suen ◽  
Shitao Rao ◽  
Alfred Chun Shui Luk ◽  
Ruoyu Zhang ◽  
...  
Keyword(s):  
Gene Expression ◽  
Single Cell ◽  
Cell Fate ◽  
Germ Cells ◽  
Somatic Cells ◽  
Cell Types ◽  
Regulatory Elements ◽  
Cellular Heterogeneity ◽  
Cell Populations ◽  
Cell Type

AbstractSpermatogenesis depends on an orchestrated series of developing events in germ cells and full maturation of the somatic microenvironment. To date, the majority of efforts to study cellular heterogeneity in testis has been focused on single-cell gene expression rather than the chromatin landscape shaping gene expression. To advance our understanding of the regulatory programs underlying testicular cell types, we analyzed single-cell chromatin accessibility profiles in more than 25,000 cells from mouse developing testis. We showed that scATAC-Seq allowed us to deconvolve distinct cell populations and identify cis-regulatory elements (CREs) underlying cell type specification. We identified sets of transcription factors associated with cell type-specific accessibility, revealing novel regulators of cell fate specification and maintenance. Pseudotime reconstruction revealed detailed regulatory dynamics coordinating the sequential developmental progressions of germ cells and somatic cells. This high-resolution data also revealed putative stem cells within the Sertoli and Leydig cell populations. Further, we defined candidate target cell types and genes of several GWAS signals, including those associated with testosterone levels and coronary artery disease. Collectively, our data provide a blueprint of the ‘regulon’ of the mouse male germline and supporting somatic cells.

scholarly journals SMNN: Batch Effect Correction for Single-cell RNA-seq data via Supervised Mutual Nearest Neighbor Detection

2019 ◽  
Author(s):  
Yuchen Yang ◽  
Gang Li ◽  
Huijun Qian ◽  
Kirk C. Wilhelmsen ◽  
Yin Shen ◽  
...  
Keyword(s):  
Single Cell ◽  
Nearest Neighbor ◽  
State Of The Art ◽  
Nearest Neighbors ◽  
Cell Types ◽  
Batch Effect ◽  
Batch Effects ◽  
Cell Type ◽  
Label Information ◽  
Cell Type Specific

AbstractBatch effect correction has been recognized to be indispensable when integrating single-cell RNA sequencing (scRNA-seq) data from multiple batches. State-of-the-art methods ignore single-cell cluster label information, but such information can improve effectiveness of batch effect correction, particularly under realistic scenarios where biological differences are not orthogonal to batch effects. To address this issue, we propose SMNN for batch effect correction of scRNA-seq data via supervised mutual nearest neighbor detection. Our extensive evaluations in simulated and real datasets show that SMNN provides improved merging within the corresponding cell types across batches, leading to reduced differentiation across batches over MNN, Seurat v3, and LIGER. Furthermore, SMNN retains more cell type-specific features, partially manifested by differentially expressed genes identified between cell types after SMNN correction being biologically more relevant, with precision improving by up to 841%.Key PointsBatch effect correction has been recognized to be critical when integrating scRNA-seq data from multiple batches due to systematic differences in time points, generating laboratory and/or handling technician(s), experimental protocol, and/or sequencing platform.Existing batch effect correction methods that leverages information from mutual nearest neighbors across batches (for example, implemented in SC3 or Seurat) ignore cell type information and suffer from potentially mismatching single cells from different cell types across batches, which would lead to undesired correction results, especially under the scenario where variation from batch effects is non-negligible compared with biological effects.To address this critical issue, here we present SMNN, a supervised machine learning method that first takes cluster/cell-type label information from users or inferred from scRNA-seq clustering, and then searches mutual nearest neighbors within each cell type instead of global searching.Our SMNN method shows clear advantages over three state-of-the-art batch effect correction methods and can better mix cells of the same cell type across batches and more effectively recover cell-type specific features, in both simulations and real datasets.

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

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.

scholarly journals RNA-seq library preparation from single pancreatic acinar cells

2016 ◽  
Author(s):  
Damian Wollny ◽  
Sheng Zhao ◽  
Ana Martin-Villalba
Keyword(s):  
Single Cell ◽  
Rna Sequencing ◽  
Acinar Cells ◽  
Cell Types ◽  
Cellular Heterogeneity ◽  
Pancreatic Acinar Cells ◽  
Library Preparation ◽  
Cell Type ◽  
Promising Tool ◽  
Single Cell Rna Sequencing

Single cell RNA sequencing technology has emerged as a promising tool to uncover previously neglected cellular heterogeneity. Multiple methods and protocols have been developed to apply single cell sequencing to different cell types from various organs. However, library preparation for RNA sequencing remains challenging for cell types with high RNAse content due to rapid degradation of endogenous RNA molecules upon cell lysis. To this end, we developed a protocol based on the SMART-seq2 technology for single cell RNA sequencing of pancreatic acinar cells, the cell type with one of the highest ribonuclease concentration measured to date. This protocol reliably produces high quality libraries from single acinar cells reaching a total of 5x106 reads / cell and ∼ 80% transcript mapping rate with no detectable 3´end bias. Thus, our protocol makes single cell transcriptomics accessible to cell type with very high RNAse content.

scholarly journals A cis-regulatory atlas in maize at single-cell resolution

2020 ◽  
Author(s):  
Alexandre P. Marand ◽  
Zongliang Chen ◽  
Andrea Gallavotti ◽  
Robert J. Schmitz
Keyword(s):  
Single Cell ◽  
Cell Types ◽  
Regulatory Elements ◽  
Cellular Heterogeneity ◽  
Cell Type ◽  
Crop Species ◽  
Cell Functions ◽  
Cell Type Specific ◽  
Type Specification ◽  
Accessible Chromatin

ABSTRACTCis-regulatory elements (CREs) encode the genomic blueprints for coordinating spatiotemporal gene expression programs underlying highly specialized cell functions. To identify CREs underlying cell-type specification and developmental transitions, we implemented single-cell sequencing of Assay for Transposase Accessible Chromatin in an atlas of Zea mays organs. We describe 92 distinct states of chromatin accessibility across more than 165,913 putative CREs, 56,575 cells, and 52 known cell-types in maize using a novel implementation of regularized quasibinomial logistic regression. Cell states were largely determined by combinatorial accessibility of transcription factors (TFs) and their binding sites. A neural network revealed that cell identity could be accurately predicted (>0.94) solely based on TF binding site accessibility. Co-accessible chromatin recapitulated higher-order chromatin interactions, with distinct sets of TFs coordinating cell type-specific regulatory dynamics. Pseudotime reconstruction and alignment with Arabidopsis thaliana trajectories identified conserved TFs, associated motifs, and cis-regulatory regions specifying sequential developmental progressions. Cell-type specific accessible chromatin regions were enriched with phenotype-associated genetic variants and signatures of selection, revealing the major cell-types and putative CREs targeted by modern maize breeding. Collectively, our analysis affords a comprehensive framework for understanding cellular heterogeneity, evolution, and cis-regulatory grammar of cell-type specification in a major crop species.

scholarly journals ACTINN: automated identification of cell types in single cell RNA sequencing

2019 ◽  
Author(s):  
Feiyang Ma ◽  
Matteo Pellegrini
Keyword(s):  
Neural Network ◽  
Single Cell ◽  
Rna Sequencing ◽  
Immune Cell ◽  
Cell Types ◽  
Mouse Cell ◽  
Supplementary Information ◽  
Cell Type ◽  
Human T Cell ◽  
Single Cell Rna Sequencing

Abstract Motivation Cell type identification is one of the major goals in single cell RNA sequencing (scRNA-seq). Current methods for assigning cell types typically involve the use of unsupervised clustering, the identification of signature genes in each cluster, followed by a manual lookup of these genes in the literature and databases to assign cell types. However, there are several limitations associated with these approaches, such as unwanted sources of variation that influence clustering and a lack of canonical markers for certain cell types. Here, we present ACTINN (Automated Cell Type Identification using Neural Networks), which employs a neural network with three hidden layers, trains on datasets with predefined cell types and predicts cell types for other datasets based on the trained parameters. Results We trained the neural network on a mouse cell type atlas (Tabula Muris Atlas) and a human immune cell dataset, and used it to predict cell types for mouse leukocytes, human PBMCs and human T cell sub types. The results showed that our neural network is fast and accurate, and should therefore be a useful tool to complement existing scRNA-seq pipelines. Availability and implementation The codes and datasets are available at https://figshare.com/articles/ACTINN/8967116. Tutorial is available at https://github.com/mafeiyang/ACTINN. All codes are implemented in python. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document