scholarly journals LAmbDA: Label Ambiguous Domain Adaption Dataset Integration Reduces Batch Effects and Improves Subtype Detection

2019 ◽  
Author(s):  
Travis S Johnson ◽  
Zhi Huang ◽  
Christina Y Yu ◽  
Tongxin Wang ◽  
Yi Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Cell Types ◽  
High Accuracy ◽  
Batch Effects ◽  
Data Types ◽  
Learning Framework ◽  
Multiple Datasets ◽  
Single Cell Rna Sequencing ◽  
Systematic Biases ◽  
Diverse Data

AbstractMotivationRapid advances in single cell RNA sequencing have produced more granular subtypes of cells in multiple tissues from different species. There exists a need to develop rigorous methods that can i) model multiple datasets with ambiguous labels across species and studies and ii) remove systematic biases across datasets and species.ResultsWe developed a species- and dataset-independent transfer learning framework (LAmbDA) to train models on multiple datasets and applied our framework on scRNA-seq experiments. These models mapped corresponding cell types between datasets with inconsistent labels while simultaneously reducing batch effects. We achieved high accuracy in labeling cellular subtypes (weighted accuracy pancreas: 91%, brain: 78%) using LAmbDA Random Forest. LAmbDA Feedforward 1 Layer Neural Network achieved higher weighted accuracy in labeling cellular subtypes than CaSTLe or MetaNeighbor in brain (48%, 32%, 20% respectively). Furthermore, LAmbDA Feedforward 1 Layer Neural Network was the only method to correctly predict ambiguous cellular subtype labels in both pancreas and brain compared to CaSTLe and MetaNeighbor. LAmbDA is model- and dataset-independent and generalizable to diverse data types representing an advance in biocomputing.Availability: github.com/tsteelejohnson91/LAmbDAContact:[email protected], [email protected]

scholarly journals LAmbDA: label ambiguous domain adaptation dataset integration reduces batch effects and improves subtype detection

2019 ◽  
Vol 35 (22) ◽  
pp. 4696-4706 ◽  
Author(s):  
Travis S Johnson ◽  
Tongxin Wang ◽  
Zhi Huang ◽  
Christina Y Yu ◽  
Yi Wu ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Simulated Data ◽  
Cell Types ◽  
Supplementary Information ◽  
Batch Effects ◽  
Data Types ◽  
Single Model ◽  
Model Type ◽  
Multiple Datasets ◽  
Systematic Biases

Abstract Motivation Rapid advances in single cell RNA sequencing (scRNA-seq) have produced higher-resolution cellular subtypes in multiple tissues and species. Methods are increasingly needed across datasets and species to (i) remove systematic biases, (ii) model multiple datasets with ambiguous labels and (iii) classify cells and map cell type labels. However, most methods only address one of these problems on broad cell types or simulated data using a single model type. It is also important to address higher-resolution cellular subtypes, subtype labels from multiple datasets, models trained on multiple datasets simultaneously and generalizability beyond a single model type. Results We developed a species- and dataset-independent transfer learning framework (LAmbDA) to train models on multiple datasets (even from different species) and applied our framework on simulated, pancreas and brain scRNA-seq experiments. These models mapped corresponding cell types between datasets with inconsistent cell subtype labels while simultaneously reducing batch effects. We achieved high accuracy in labeling cellular subtypes (weighted accuracy simulated 1 datasets: 90%; simulated 2 datasets: 94%; pancreas datasets: 88% and brain datasets: 66%) using LAmbDA Feedforward 1 Layer Neural Network with bagging. This method achieved higher weighted accuracy in labeling cellular subtypes than two other state-of-the-art methods, scmap and CaSTLe in brain (66% versus 60% and 32%). Furthermore, it achieved better performance in correctly predicting ambiguous cellular subtype labels across datasets in 88% of test cases compared with CaSTLe (63%), scmap (50%) and MetaNeighbor (50%). LAmbDA is model- and dataset-independent and generalizable to diverse data types representing an advance in biocomputing. Availability and implementation github.com/tsteelejohnson91/LAmbDA Supplementary information Supplementary data are available at Bioinformatics online.

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 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.

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

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.

scholarly journals souporcell: Robust clustering of single cell RNAseq by genotype and ambient RNA inference without reference genotypes

2019 ◽  
Author(s):  
Haynes Heaton ◽  
Arthur M. Talman ◽  
Andrew Knights ◽  
Maria Imaz ◽  
Daniel Gaffney ◽  
...  
Keyword(s):  
Single Cell ◽  
High Accuracy ◽  
Batch Effects ◽  
Robust Clustering ◽  
Wide Range ◽  
Single Cell Rna Sequencing ◽  
Natural Mixture ◽  
Novel Method ◽  
Reducing Costs ◽  
Genotype Clustering

Methods to deconvolve single-cell RNA sequencing (scRNAseq) data are necessary for samples containing a natural mixture of genotypes and for scRNAseq experiments that multiplex cells from different donors1. Multiplexing across donors is a popular experimental design with many benefits including avoiding batch effects2, reducing costs, and improving doublet detection. Using variants detected in the RNAseq reads, it is possible to assign cells to the individuals from which they arose. These variants can also be used to identify and remove cross-genotype doublet cells that may have highly similar transcriptional profiles precluding detection by transcriptional profile. More subtle cross-genotype variant contamination can be used to estimate the amount of ambient RNA in the system. Ambient RNA is caused by cell lysis prior to droplet partitioning and is an important confounder of scRNAseq analysis3. Souporcell is a novel method to cluster cells using only the genetic variants detected within the scRNAseq reads. We show that it achieves high accuracy on genotype clustering, doublet detection, and ambient RNA estimation as demonstrated across a wide range of challenging scenarios.

scholarly journals Deep learning enables accurate clustering and batch effect removal in single-cell RNA-seq analysis

2019 ◽  
Author(s):  
Xiangjie Li ◽  
Yafei Lyu ◽  
Jihwan Park ◽  
Jingxiao Zhang ◽  
Dwight Stambolian ◽  
...  
Keyword(s):  
Single Cell ◽  
Cell Types ◽  
Specific Gene ◽  
Rna Seq ◽  
Batch Effects ◽  
Cluster Assignment ◽  
Cell Clustering ◽  
Deep Embedding ◽  
Single Cell Rna Sequencing ◽  
Number Of Cells

Single-cell RNA sequencing (scRNA-seq) can characterize cell types and states through unsupervised clustering, but the ever increasing number of cells imposes computational challenges. We present an unsupervised deep embedding algorithm for single-cell clustering (DESC) that iteratively learns cluster-specific gene expression signatures and cluster assignment. DESC significantly improves clustering accuracy across various datasets and is capable of removing complex batch effects while maintaining true biological variations.

scholarly journals Flexible Experimental Designs for Valid Single-cell RNA-sequencing Experiments Allowing Batch Effects Correction

2019 ◽  
Author(s):  
Fangda Song ◽  
Ga Ming Chan ◽  
Yingying Wei
Keyword(s):  
Single Cell ◽  
Rna Sequencing ◽  
Real Data ◽  
Cell Types ◽  
Experimental Designs ◽  
Batch Effects ◽  
Bayesian Hierarchical ◽  
Single Cell Rna Sequencing ◽  
Randomized Experimental Design ◽  
Chain Type

AbstractDespite their widespread applications, single-cell RNA-sequencing (scRNA-seq) experiments are still plagued by batch effects and dropout events. Although the completely randomized experimental design has frequently been advocated to control for batch effects, it is rarely implemented in real applications due to time and budget constraints. Here, we mathematically prove that under two more flexible and realistic experimental designs—the “reference panel” and the “chain-type” designs—true biological variability can also be separated from batch effects. We develop Batch effects correction with Unknown Subtypes for scRNA-seq data (BUSseq), which is an interpretable Bayesian hierarchical model that closely follows the data-generating mechanism of scRNA-seq experiments. BUSseq can simultaneously correct batch effects, cluster cell types, impute missing data caused by dropout events, and detect differentially expressed genes without requiring a preliminary normalization step. We demonstrate that BUSseq outperforms existing methods with simulated and real data.

scholarly journals EmptyNN: A neural network based on positive-unlabeled learning to remove cell-free droplets and recover lost cells in single-cell RNA sequencing data

2021 ◽  
Author(s):  
Fangfang Yan ◽  
Zhongming Zhao ◽  
Lukas M. Simon
Keyword(s):  
Neural Network ◽  
Single Cell ◽  
Rna Sequencing ◽  
Ground Truth ◽  
Cell Types ◽  
Superior Performance ◽  
Sequencing Data ◽  
Operating Characteristics ◽  
Current State ◽  
Single Cell Rna Sequencing

ABSTRACTDroplet-based single-cell RNA sequencing (scRNA-seq) has significantly increased the number of cells profiled per experiment and revolutionized the study of individual transcriptomes. However, to maximize the biological signal robust computational methods are needed to distinguish cell-free from cell-containing droplets. Here, we introduce a novel cell-calling algorithm called EmptyNN, which trains a neural network based on positive-unlabeled learning for improved filtering of barcodes. We leveraged cell hashing and genetic variation to provide ground-truth. EmptyNN accurately removed cell-free droplets while recovering lost cell clusters, and achieved an Area Under the Receiver Operating Characteristics (AUROC) of 94.73% and 96.30%, respectively. The comparisons to current state-of-the-art cell-calling algorithms demonstrated the superior performance of EmptyNN, as measured by the number of recovered cell-containing droplets and cell types. EmptyNN was further applied to two additional datasets and showed good performance. Therefore, EmptyNN represents a powerful tool to enhance scRNA-seq quality control analyses.

scholarly journals 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 ◽  
Marker Genes ◽  
Complex Data ◽  
Cell Type ◽  
Human T Cell ◽  
Single Cell Rna Sequencing

AbstractCell 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 3 hidden layers, trains on datasets with predefined cell types, and predicts cell types for other datasets based on the trained parameters. 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.Author SummarySingle cell RNA sequencing (scRNA-seq) provides high resolution profiling of the transcriptomes of individual cells, which inevitably results in high volumes of data that require complex data processing pipelines. Usually, one of the first steps in the analysis of scRNA-seq is to assign individual cells to known cell types. To accomplish this, traditional methods first group the cells into different clusters, then find marker genes, and finally use these to manually assign cell types for each cluster. Thus these methods require prior knowledge of cell type canonical markers, and some level of subjectivity to make the cell type assignments. As a result, the process is often laborious and requires domain specific expertise, which is a barrier for inexperienced users. By contrast, our neural network ACTINN automatically learns the features for each predefined cell type and uses these features to predict cell types for individual cells. This approach is computationally efficient and requires no domain expertise of the tissues being studied. We believe ACTINN allows users to rapidly identify cell types in their datasets, thus rendering the analysis of their scRNA-seq datasets more efficient.

scholarly journals Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

2021 ◽  
Author(s):  
Yifan Zhao ◽  
Huiyu Cai ◽  
Zuobai Zhang ◽  
Jian Tang ◽  
Yue Li
Keyword(s):  
Single Cell ◽  
Topic Model ◽  
Cell Types ◽  
Gene Signature ◽  
Batch Effects ◽  
Cell Type ◽  
Transcriptomic Data ◽  
Variational Autoencoder ◽  
Single Cell Rna Sequencing ◽  
Cell Type Specific

Abstract The advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, integrative analysis of scRNA-seq data remains a challenge largely due to batch effects. We present single-cell Embedded Topic Model (scETM), an unsupervised deep generative model that recapitulates known cell types by inferring the latent cell topic mixtures via a variational autoencoder. scETM is scalable to over 10^6 cells and enables effective knowledge transfer across datasets. scETM also offers high interpretability and allows the incorporation of prior pathway knowledge into the gene embeddings. The scETM-inferred topics show enrichment in cell-type-specific and disease-related pathways.

Sign in / Sign up

Export Citation Format

Share Document