A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data

Clustering analysis is widely utilized in single-cell RNA-sequencing (scRNA-seq) data to discover cell heterogeneity and cell states. While many clustering methods have been developed for scRNA-seq analysis, most of these methods require to provide the number of clusters. However, it is not easy to know the exact number of cell types in advance, and experienced determination is not always reliable. Here, we have developed ADClust, an automatic deep embedding clustering method for scRNA-seq data, which can accurately cluster cells without requiring a predefined number of clusters. Specifically, ADClust first obtains low-dimensional representation through pre-trained autoencoder, and uses the representations to cluster cells into initial micro-clusters. The clusters are then compared in between by a statistical test, and similar micro-clusters are merged into larger clusters. According to the clustering, cell representations are updated so that each cell will be pulled toward centres of its assigned cluster and similar clusters, while cells are separated to keep distances between clusters. This is accomplished through jointly optimizing the carefully designed clustering and autoencoder loss functions. This merging process continues until convergence. ADClust was tested on eleven real scRNA-seq datasets, and shown to outperform existing methods in terms of both clustering performance and the accuracy on the number of the determined clusters. More importantly, our model provides high speed and scalability for large datasets.

Download Full-text

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

10.1101/2020.10.06.327601 ◽

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.

Download Full-text

Unsupervised cell functional annotation for single-cell RNA-Seq

10.1101/2021.11.20.469410 ◽

2021 ◽

Author(s):

Dongshunyi Li ◽

Jun Ding ◽

Ziv Bar-Joseph

Keyword(s):

Single Cell ◽

Dimensional Space ◽

Cell Types ◽

Specific Gene ◽

Rna Seq ◽

Cell Type ◽

Sequencing Data ◽

Gene Sets ◽

Supervised Methods ◽

Low Dimensional

One of the first steps in the analysis of single cell RNA-Sequencing data (scRNA-Seq) is the assignment of cell types. While a number of supervised methods have been developed for this, in most cases such assignment is performed by first clustering cells in low-dimensional space and then assigning cell types to different clusters. To overcome noise and to improve cell type assignments we developed UNIFAN, a neural network method that simultaneously clusters and annotates cells using known gene sets. UNIFAN combines both, low dimension representation for all genes and cell specific gene set activity scores to determine the clustering. We applied UNIFAN to human and mouse scRNA-Seq datasets from several different organs. As we show, by using knowledge on gene sets, UNIFAN greatly outperforms prior methods developed for clustering scRNA-Seq data. The gene sets assigned by UNIFAN to different clusters provide strong evidence for the cell type that is represented by this cluster making annotations easier.

Download Full-text

FEATS: Feature selection based clustering of single-cell RNA-seq data

10.1101/2020.07.13.200485 ◽

2020 ◽

Author(s):

Edwin Vans ◽

Ashwini Patil ◽

Alok Sharma

Keyword(s):

Feature Selection ◽

Single Cell ◽

Outlier Detection ◽

Cell Types ◽

Superior Performance ◽

Adjusted Rand Index ◽

Marker Genes ◽

Rna Seq ◽

Number Of Clusters ◽

Computational Performance

ABSTRACTAdvances in next-generation sequencing (NGS) have made it possible to carry out transcriptomic studies at single-cell resolution and generate vast amounts of single-cell RNA-seq data rapidly. Thus, tools to analyze this data need to evolve as well to improve accuracy and efficiency. We present FEATS, a python software package that performs clustering on single-cell RNA-seq data. FEATS is capable of performing multiple tasks such as estimating the number of clusters, conducting outlier detection, and integrating data from various experiments. We develop a univariate feature selection based approach for clustering, which involves the selection of top informative features to improve clustering performance. This is motivated by the fact that cell types are often manually determined using the expression of only a few known marker genes. On a variety of single-cell RNA-seq datasets, FEATS gives superior performance compared to the current tools, in terms of adjusted rand index (ARI) and estimating the number of clusters. In addition to cluster estimation, FEATS also performs outlier detection and data integration while giving an excellent computational performance. Thus, FEATS is a comprehensive clustering tool capable of addressing the challenges during the clustering of single-cell RNA-seq data. The installation instructions and documentation of FEATS is available at https://edwinv87.github.io/feats/.

Download Full-text

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

10.1101/530378 ◽

2019 ◽

Cited By ~ 5

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.

Download Full-text

Model-based deep embedding for constrained clustering analysis of single cell RNA-seq data

Nature Communications ◽

10.1038/s41467-021-22008-3 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Tian Tian ◽

Jie Zhang ◽

Xiang Lin ◽

Zhi Wei ◽

Hakon Hakonarson

Keyword(s):

Single Cell ◽

Domain Knowledge ◽

Ad Hoc ◽

A Priori ◽

Unsupervised Clustering ◽

Rna Seq ◽

Clustering Methods ◽

Cell Type ◽

Type Assignment ◽

Deep Embedding

AbstractClustering is a critical step in single cell-based studies. Most existing methods support unsupervised clustering without the a priori exploitation of any domain knowledge. When confronted by the high dimensionality and pervasive dropout events of scRNA-Seq data, purely unsupervised clustering methods may not produce biologically interpretable clusters, which complicates cell type assignment. In such cases, the only recourse is for the user to manually and repeatedly tweak clustering parameters until acceptable clusters are found. Consequently, the path to obtaining biologically meaningful clusters can be ad hoc and laborious. Here we report a principled clustering method named scDCC, that integrates domain knowledge into the clustering step. Experiments on various scRNA-seq datasets from thousands to tens of thousands of cells show that scDCC can significantly improve clustering performance, facilitating the interpretability of clusters and downstream analyses, such as cell type assignment.

Download Full-text

SAME-clustering: Single-cell Aggregated Clustering via Mixture Model Ensemble

10.1101/645820 ◽

2019 ◽

Cited By ~ 1

Author(s):

Ruth Huh ◽

Yuchen Yang ◽

Yuchao Jiang ◽

Yin Shen ◽

Yun Li

Keyword(s):

Single Cell ◽

Mixture Model ◽

Single Cells ◽

Cell Types ◽

Rna Seq ◽

Model Ensemble ◽

Clustering Ensemble ◽

Number Of Clusters ◽

Wide Range ◽

Level Cluster

ABSTRACTClustering is an essential step in the analysis of single cell RNA-seq (scRNA-seq) data to shed light on tissue complexity including the number of cell types and transcriptomic signatures of each cell type. Due to its importance, novel methods have been developed recently for this purpose. However, different approaches generate varying estimates regarding the number of clusters and the single-cell level cluster assignments. This type of unsupervised clustering is challenging and it is often times hard to gauge which method to use because none of the existing methods outperform others across all scenarios. We present SAME-clustering, a mixture model-based approach that takes clustering solutions from multiple methods and selects a maximally diverse subset to produce an improved ensemble solution. We tested SAME-clustering across 15 scRNA-seq datasets generated by different platforms, with number of clusters varying from 3 to 15, and number of single cells from 49 to 32,695. Results show that our SAME-clustering ensemble method yields enhanced clustering, in terms of both cluster assignments and number of clusters. The mixture model ensemble clustering is not limited to clustering scRNA-seq data and may be useful to a wide range of clustering applications.

Download Full-text

Straightforward clustering of single-cell RNA-Seq data with t-SNE and DBSCAN

10.1101/770388 ◽

2019 ◽

Cited By ~ 3

Author(s):

Florian Wagner

Keyword(s):

Single Cell ◽

Mononuclear Cells ◽

Gene Selection ◽

Real Data ◽

Cell Types ◽

Fine Tuning ◽

Rna Seq ◽

Clustering Methods ◽

Cell Type ◽

Peripheral Blood Mononuclear

AbstractClustering of cells by cell type is arguably the most common and repetitive task encountered during the analysis of single-cell RNA-Seq data. However, as popular clustering methods operate largely independently of visualization techniques, the fine-tuning of clustering parameters can be unintuitive and time-consuming. Here, I propose Galapagos, a simple and effective clustering workflow based on t-SNE and DBSCAN that does not require a gene selection step. In practice, Galapagos only involves the fine-tuning of two parameters, which is straightforward, as clustering is performed directly on the t-SNE visualization results. Using peripheral blood mononuclear cells as a model tissue, I validate the effectiveness of Galapagos in different ways. First, I show that Galapagos generates clusters corresponding to all main cell types present. Then, I demonstrate that the t-SNE results are robust to parameter choices and initialization points. Next, I employ a simulation approach to show that clustering with Galapagos is accurate and robust to the high levels of technical noise present. Finally, to demonstrate Galapagos’ accuracy on real data, I compare clustering results to true cell type identities established using CITE-Seq data. In this context, I also provide an example of the primary limitation of Galapagos, namely the difficulty to resolve related cell types in cases where t-SNE fails to clearly separate the cells. Galapagos helps to make clustering scRNA-Seq data more intuitive and reproducible, and can be implemented in most programming languages with only a few lines of code.

Download Full-text

SAME-clustering: Single-cell Aggregated Clustering via Mixture Model Ensemble

Nucleic Acids Research ◽

10.1093/nar/gkz959 ◽

2019 ◽

Vol 48 (1) ◽

pp. 86-95 ◽

Cited By ~ 5

Author(s):

Ruth Huh ◽

Yuchen Yang ◽

Yuchao Jiang ◽

Yin Shen ◽

Yun Li

Keyword(s):

Single Cell ◽

Mixture Model ◽

Single Cells ◽

Cell Types ◽

Rna Seq ◽

Model Ensemble ◽

Clustering Ensemble ◽

Number Of Clusters ◽

Wide Range ◽

Level Cluster

Abstract Clustering is an essential step in the analysis of single cell RNA-seq (scRNA-seq) data to shed light on tissue complexity including the number of cell types and transcriptomic signatures of each cell type. Due to its importance, novel methods have been developed recently for this purpose. However, different approaches generate varying estimates regarding the number of clusters and the single-cell level cluster assignments. This type of unsupervised clustering is challenging and it is often times hard to gauge which method to use because none of the existing methods outperform others across all scenarios. We present SAME-clustering, a mixture model-based approach that takes clustering solutions from multiple methods and selects a maximally diverse subset to produce an improved ensemble solution. We tested SAME-clustering across 15 scRNA-seq datasets generated by different platforms, with number of clusters varying from 3 to 15, and number of single cells from 49 to 32 695. Results show that our SAME-clustering ensemble method yields enhanced clustering, in terms of both cluster assignments and number of clusters. The mixture model ensemble clustering is not limited to clustering scRNA-seq data and may be useful to a wide range of clustering applications.

Download Full-text

Analysis of Single-Cell RNA-seq Data by Clustering Approaches

Current Bioinformatics ◽

10.2174/1574893614666181120095038 ◽

2019 ◽

Vol 14 (4) ◽

pp. 314-322 ◽

Cited By ~ 3

Author(s):

Xiaoshu Zhu ◽

Hong-Dong Li ◽

Lilu Guo ◽

Fang-Xiang Wu ◽

Jianxin Wang

Keyword(s):

Feature Selection ◽

Single Cell ◽

Cell Types ◽

Semisupervised Learning ◽

Similarity Measurement ◽

Marker Genes ◽

Rna Seq ◽

Selection Methods ◽

Clustering Methods ◽

Similarity Calculation

Background: The recently developed single-cell RNA sequencing (scRNA-seq) has attracted a great amount of attention due to its capability to interrogate expression of individual cells, which is superior to traditional bulk cell sequencing that can only measure mean gene expression of a population of cells. scRNA-seq has been successfully applied in finding new cell subtypes. New computational challenges exist in the analysis of scRNA-seq data. Objective: We provide an overview of the features of different similarity calculation and clustering methods, in order to facilitate users to select methods that are suitable for their scRNA-seq. We would also like to show that feature selection methods are important to improve clustering performance. Results: We first described similarity measurement methods, followed by reviewing some new clustering methods, as well as their algorithmic details. This analysis revealed several new questions, including how to automatically estimate the number of clustering categories, how to discover novel subpopulation, and how to search for new marker genes by using feature selection methods. Conclusion: Without prior knowledge about the number of cell types, clustering or semisupervised learning methods are important tools for exploratory analysis of scRNA-seq data.</P>

Download Full-text

SAFE-clustering: Single-cell Aggregated (From Ensemble) Clustering for Single-cell RNA-seq Data

10.1101/215723 ◽

2017 ◽

Cited By ~ 8

Author(s):

Yuchen Yang ◽

Ruth Huh ◽

Houston W. Culpepper ◽

Yuan Lin ◽

Michael I. Love ◽

...

Keyword(s):

Single Cell ◽

Single Cells ◽

Supplementary Information ◽

Adjusted Rand Index ◽

Ensemble Clustering ◽

Rna Seq ◽

Clustering Methods ◽

Cluster Assignment ◽

Absolute Deviation ◽

Number Of Clusters

ABSTRACTMotivationAccurately clustering cell types from a mass of heterogeneous cells is a crucial first step for the analysis of single-cell RNA-seq (scRNA-Seq) data. Although several methods have been recently developed, they utilize different characteristics of data and yield varying results in terms of both the number of clusters and actual cluster assignments.ResultsHere, we present SAFE-clustering, Single-cell Aggregated (From Ensemble) clustering, a flexible, accurate and robust method for clustering scRNA-Seq data. SAFE-clustering takes as input, results from multiple clustering methods, to build one consensus solution. SAFE-clustering currently embeds four state-of-the-art methods, SC3, CIDR, Seurat and t-SNE + k-means; and ensembles solutions from these four methods using three hypergraph-based partitioning algorithms. Extensive assessment across 12 datasets with the number of clusters ranging from 3 to 14, and the number of single cells ranging from 49 to 32,695 showcases the advantages of SAFE-clustering in terms of both cluster number (18.9 - 50.0% reduction in absolute deviation to the truth) and cluster assignment (on average 28.9% improvement, and up to 34.5% over the best of the four methods, measured by adjusted rand index). Moreover, SAFE-clustering is computationally efficient to accommodate large datasets, taking <10 minutes to process 28,733 cells.Availability and implementationSAFE-clustering, including source codes and tutorial, is free available on the web at http://yunliweb.its.unc.edu/safe/[email protected] informationSupplementary data are available at Bioinformatics online.

Download Full-text