scholarly journals scSemiAE: A Deep Model with Semi-Supervised Learning for Single-Cell Transcriptomics

2021 ◽  
Author(s):  
Jiayi Dong ◽  
Yin Zhang ◽  
Fei Wang
Keyword(s):  
Dimensionality Reduction ◽  
Single Cell ◽  
Cell Subpopulation ◽  
High Dimensions ◽  
Deep Model ◽  
Unsupervised Approach ◽  
Cell Subpopulations ◽  
Downstream Analysis ◽  
Low Dimensional ◽  
Public Datasets

Abstract Background: With the development of modern sequencing technology, hundreds of thousands of single-cell RNA-sequencing(scRNA-seq) profiles allow to explore the heterogeneity in the cell level, but it faces the challenges of high dimensions and high sparsity. Dimensionality reduction is essential for downstream analysis, such as clustering to identify cell subpopulations. Usually, dimensionality reduction follows unsupervised approach. Results: In this paper, we introduce a semi-supervised dimensionality reduction method named scSemiAE, which is based on an autoencoder model. It transfers the information contained in available datasets with cell subpopulation labels to guide the search of better low-dimensional representations, which can ease further analysis. Conclusions: Experiments on five public datasets show that, scSemiAE outperforms both unsupervised and semi-supervised baselines whether the transferred information embodied in the number of labeled cells and labeled cell subpopulations is much or less.

scholarly journals A quantitative framework for evaluating single-cell data structure preservation by dimensionality reduction techniques

2019 ◽  
Author(s):  
Cody N. Heiser ◽  
Ken S. Lau
Keyword(s):  
Data Structure ◽  
Dimensionality Reduction ◽  
Single Cell ◽  
Structure Preservation ◽  
Reduction Techniques ◽  
Reduction Methods ◽  
Biological Interpretation ◽  
Low Dimensional ◽  
Genome Scale ◽  
Global And Local

SummaryHigh-dimensional data, such as those generated using single-cell RNA sequencing, present challenges in interpretation and visualization. Numerical and computational methods for dimensionality reduction allow for low-dimensional representation of genome-scale expression data for downstream clustering, trajectory reconstruction, and biological interpretation. However, a comprehensive and quantitative evaluation of the performance of these techniques has not been established. We present an unbiased framework that defines metrics of global and local structure preservation in dimensionality reduction transformations. Using discrete and continuous scRNA-seq datasets, we find that input cell distribution and method parameters are largely determinant of global, local, and organizational data structure preservation by eleven published dimensionality reduction methods. Code available atgithub.com/KenLauLab/DR-structure-preservationallows for rapid evaluation of further datasets and methods.

scholarly journals Single-Cell Manifold Preserving Feature Selection (SCMER)

2020 ◽  
Author(s):  
Ken Chen ◽  
Shaoheng Liang ◽  
Vakul Mohanty ◽  
Jinzhuang Dou ◽  
Miao Qi ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Single Cell ◽  
Cost Effective ◽  
High Dimensional ◽  
Compact Set ◽  
Cell Lineages ◽  
Molecular Features ◽  
Unsupervised Approach ◽  
Cell Data ◽  
Common Cell

Abstract A key challenge in studying organisms and diseases is to detect rare molecular programs and rare cell populations (RCPs) that drive development, differentiation, and transformation. Molecular features such as genes and proteins defining RCPs are often unknown and difficult to detect from unenriched single-cell data, using conventional dimensionality reduction and clustering-based approaches. Here, we propose a novel unsupervised approach, named SCMER, which performs UMAP style dimensionality reduction via selecting a compact set of molecular features with definitive meanings. We applied SCMER in the context of hematopoiesis, lymphogenesis, tumorigenesis, and drug resistance and response. We found that SCMER can identify non-redundant features that sensitively delineate both common cell lineages and rare cellular states ignored by current approaches. SCMER can be widely used for discovering novel molecular features in a high dimensional dataset, designing targeted, cost-effective assays for clinical applications, and facilitating multi-modality integration.

CaMelia: imputation in single-cell methylomes based on local similarities between cells

2021 ◽  
Author(s):  
Jianxiong Tang ◽  
Jianxiao Zou ◽  
Mei Fan ◽  
Qi Tian ◽  
Jiyang Zhang ◽  
...  
Keyword(s):  
Single Cell ◽  
Regulation Of Gene Expression ◽  
Cell Types ◽  
Supplementary Information ◽  
Gradient Boosting ◽  
Raw Data ◽  
Boosting Method ◽  
Cell Subpopulations ◽  
Downstream Analysis ◽  
Almost All

Abstract Motivation Single-cell DNA methylation sequencing detects methylation levels with single-cell resolution, while this technology is upgrading our understanding of the regulation of gene expression through epigenetic modifications. Meanwhile, almost all current technologies suffer from the inherent problem of detecting low coverage of the number of CpGs. Therefore, addressing the inherent sparsity of raw data is essential for quantitative analysis of the whole genome. Results Here, we reported CaMelia, a CatBoost gradient boosting method for predicting the missing methylation states based on the locally paired similarity of intercellular methylation patterns. On real single-cell methylation datasets, CaMelia yielded significant imputation performance gains over previous methods. Furthermore, applying the imputed data to the downstream analysis of cell-type identification, we found that CaMelia helped to discover more intercellular differentially methylated loci that were masked by the sparsity in raw data, and the clustering results demonstrated that CaMelia could preserve cell-cell relationships and improve the identification of cell types and cell subpopulations. Availability and implementation Python code is available at https://github.com/JxTang-bioinformatics/CaMelia. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Cytosplore-Transcriptomics: a scalable inter-active framework for single-cell RNA sequencing data analysis

2020 ◽  
Author(s):  
Tamim Abdelaal ◽  
Jeroen Eggermont ◽  
Thomas Höllt ◽  
Ahmed Mahfouz ◽  
Marcel J.T. Reinders ◽  
...  
Keyword(s):  
Data Analysis ◽  
Single Cell ◽  
Rna Sequencing ◽  
Visual Exploration ◽  
Sequencing Data ◽  
Interactive Analysis ◽  
Levels Of Detail ◽  
Single Cell Rna Sequencing ◽  
Downstream Analysis ◽  
Low Dimensional

SummaryThe ever-increasing number of analyzed cells in Single-cell RNA sequencing (scRNA-seq) experiments imposes several challenges on the data analysis. Current analysis methods lack scalability to large datasets hampering interactive visual exploration of the data. We present Cytosplore-Transcriptomics, a framework to analyze scRNA-seq data, including data preprocessing, visualization and downstream analysis. At its core, it uses a hierarchical, manifold preserving representation of the data that allows the inspection and annotation of scRNA-seq data at different levels of detail. Consequently, Cytosplore-Transcriptomics provides interactive analysis of the data using low-dimensional visualizations that scales to millions of cells.AvailabilityCytosplore-Transcriptomics can be freely downloaded from [email protected]

scholarly journals scGAE: topology-preserving dimensionality reduction for single-cell RNA-seq data using graph autoencoder

2021 ◽  
Author(s):  
Zixiang Luo ◽  
Chenyu Xu ◽  
Zhen Zhang ◽  
Wenfei Jin
Keyword(s):  
Dimensionality Reduction ◽  
Single Cell ◽  
Topological Structure ◽  
Dimensional Space ◽  
Simulated Data ◽  
Oriented Graph ◽  
Developmental Trajectory ◽  
Structure Information ◽  
Low Dimensional ◽  
Cell Graph

ABSTRACTDimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.

scholarly journals Phenotype-guided subpopulation identification from single-cell sequencing data

2020 ◽  
Author(s):  
Duanchen Sun ◽  
Xiangnan Guan ◽  
Amy E. Moran ◽  
David Z. Qian ◽  
Pepper Schedin ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Single Cell ◽  
Clinical Information ◽  
Single Step ◽  
Cell Subpopulation ◽  
Clustering Methods ◽  
Sequencing Data ◽  
Single Cell Sequencing ◽  
Cell Subpopulations ◽  
Cell Data

AbstractSingle-cell sequencing yields novel discoveries by distinguishing cell types, states and lineages within the context of heterogeneous tissues. However, interpreting complex single-cell data from highly heterogeneous cell populations remains challenging. Currently, most existing single-cell data analyses focus on cell type clusters defined by unsupervised clustering methods, which cannot directly link cell clusters with specific biological and clinical phenotypes. Here we present Scissor, a novel approach that utilizes disease phenotypes to identify cell subpopulations from single-cell data that most highly correlate with a given phenotype. This “phenotype-to-cell within a single step” strategy enables the utilization of a large amount of clinical information that has been collected for bulk assays to identify the most highly phenotype-associated cell subpopulations. When applied to a lung cancer single-cell RNA-seq (scRNA-seq) dataset, Scissor identified a subset of cells exhibiting high hypoxia activities, which predicted worse survival outcomes in lung cancer patients. Furthermore, in a melanoma scRNA-seq dataset, Scissor discerned a T cell subpopulation with low PDCD1/CTLA4 and high TCF7 expressions, which is associated with a favorable immunotherapy response. Thus, Scissor provides a novel framework to identify the biologically and clinically relevant cell subpopulations from single-cell assays by leveraging the wealth of phenotypes and bulk-omics datasets.

scholarly journals Building Recognition on Subregion’s Multiscale Gist Feature Extraction and Corresponding Columns Information Based Dimensionality Reduction

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Bin Li ◽  
Wei Pang ◽  
Yuhao Liu ◽  
Xiangchun Yu ◽  
Anan Du ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Dimensional Subspace ◽  
Dimensional Manifold ◽  
Feature Maps ◽  
High Dimensions ◽  
Recognition Method ◽  
Second Stage ◽  
Building Recognition ◽  
Reduction Methods ◽  
Low Dimensional

In this paper, we proposed a new building recognition method named subregion’s multiscale gist feature (SM-gist) extraction and corresponding columns information based dimensionality reduction (CCI-DR). Our proposed building recognition method is presented as a two-stage model: in the first stage, a building image is divided into 4 × 5 subregions, and gist vectors are extracted from these regions individually. Then, we combine these gist vectors into a matrix with relatively high dimensions. In the second stage, we proposed CCI-DR to project the high dimensional manifold matrix to low dimensional subspace. Compared with the previous building recognition method the advantages of our proposed method are that (1) gist features extracted by SM-gist have the ability to adapt to nonuniform illumination and that (2) CCI-DR can address the limitation of traditional dimensionality reduction methods, which convert gist matrices into vectors and thus mix the corresponding gist vectors from different feature maps. Our building recognition method is evaluated on the Sheffield buildings database, and experiments show that our method can achieve satisfactory performance.

scholarly journals D-EE: Distributed software for visualizing intrinsic structure of large-scale single-cell data

GigaScience ◽  
2020 ◽  
Vol 9 (11) ◽  
Author(s):  
Shaokun An ◽  
Jizu Huang ◽  
Lin Wan
Keyword(s):  
Time Series ◽  
Dimensionality Reduction ◽  
Single Cell ◽  
High Performance ◽  
Large Scale ◽  
Distributed Storage ◽  
Distributed Computation ◽  
Low Dimensional ◽  
Cell Data ◽  
Performance Computing

Abstract Background Dimensionality reduction and visualization play vital roles in single-cell RNA sequencing (scRNA-seq) data analysis. While they have been extensively studied, state-of-the-art dimensionality reduction algorithms are often unable to preserve the global structures underlying data. Elastic embedding (EE), a nonlinear dimensionality reduction method, has shown promise in revealing low-dimensional intrinsic local and global data structure. However, the current implementation of the EE algorithm lacks scalability to large-scale scRNA-seq data. Results We present a distributed optimization implementation of the EE algorithm, termed distributed elastic embedding (D-EE). D-EE reveals the low-dimensional intrinsic structures of data with accuracy equal to that of elastic embedding, and it is scalable to large-scale scRNA-seq data. It leverages distributed storage and distributed computation, achieving memory efficiency and high-performance computing simultaneously. In addition, an extended version of D-EE, termed distributed optimization implementation of time-series elastic embedding (D-TSEE), enables the user to visualize large-scale time-series scRNA-seq data by incorporating experimentally temporal information. Results with large-scale scRNA-seq data indicate that D-TSEE can uncover oscillatory gene expression patterns by using experimentally temporal information. Conclusions D-EE is a distributed dimensionality reduction and visualization tool. Its distributed storage and distributed computation technique allow us to efficiently analyze large-scale single-cell data at the cost of constant time speedup. The source code for D-EE algorithm based on C and MPI tailored to a high-performance computing cluster is available at https://github.com/ShaokunAn/D-EE.

scholarly journals Integrated decoding hematopoiesis and leukemogenesis using single-cell sequencing and its medical implication

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Pengfei Qin ◽  
Yakun Pang ◽  
Wenhong Hou ◽  
Ruiqing Fu ◽  
Yingchi Zhang ◽  
...  
Keyword(s):  
Single Cell ◽  
Cell Population ◽  
Mononuclear Cells ◽  
Leukemia Cell ◽  
Cellular Heterogeneity ◽  
Leukemia Cells ◽  
Cell Subpopulation ◽  
Clinical Samples ◽  
Leukemia Patient ◽  
Cell Subpopulations

AbstractSingle-cell RNA sequencing provides exciting opportunities to unbiasedly study hematopoiesis. However, our understanding of leukemogenesis was limited due to the high individual differences. Integrated analyses of hematopoiesis and leukemogenesis potentially provides new insights. Here we analyzed ~200,000 single-cell transcriptomes of bone marrow mononuclear cells (BMMCs) and its subsets from 23 clinical samples. We constructed a comprehensive cell atlas as hematopoietic reference. We developed counterpart composite index (CCI; available at GitHub: https://github.com/pengfeeei/cci) to search for the healthy counterpart of each leukemia cell subpopulation, by integrating multiple statistics to map leukemia cells onto reference hematopoietic cells. Interestingly, we found leukemia cell subpopulations from each patient had different healthy counterparts. Analysis showed the trajectories of leukemia cell subpopulations were similar to that of their healthy counterparts, indicating that developmental termination of leukemia initiating cells at different phases leads to different leukemia cell subpopulations thus explained the origin of leukemia heterogeneity. CCI further predicts leukemia subtypes, cellular heterogeneity, and cellular stemness of each leukemia patient. Analyses of leukemia patient at diagnosis, refractory, remission and relapse vividly presented dynamics of cell population during leukemia treatment. CCI analyses showed the healthy counterparts of relapsed leukemia cells were closer to the root of hematopoietic tree than that of other leukemia cells, although single-cell transcriptomic genetic variants and haplotype tracing analyses showed the relapsed leukemia cell were derived from an early minor leukemia cell population. In summary, this study developed a unified framework for understanding leukemogenesis with hematopoiesis reference, which provided novel biological and medical implication.

netAE: semi-supervised dimensionality reduction of single-cell RNA sequencing to facilitate cell labeling

2020 ◽  
Author(s):  
Zhengyang Dong ◽  
Gil Alterovitz
Keyword(s):  
Dimensionality Reduction ◽  
Single Cell ◽  
Rna Sequencing ◽  
Gold Standard ◽  
Cell Labeling ◽  
Supplementary Information ◽  
Manual Inspection ◽  
Current Cell ◽  
Single Cell Rna Sequencing ◽  
Public Datasets

Abstract Motivation Single-cell RNA sequencing allows us to study cell heterogeneity at an unprecedented cell-level resolution and identify known and new cell populations. Current cell labeling pipeline uses unsupervised clustering and assigns labels to clusters by manual inspection. However, this pipeline does not utilize available gold-standard labels because there are usually too few of them to be useful to most computational methods. This article aims to facilitate cell labeling with a semi-supervised method in an alternative pipeline, in which a few gold-standard labels are first identified and then extended to the rest of the cells computationally. Results We built a semi-supervised dimensionality reduction method, a network-enhanced autoencoder (netAE). Tested on three public datasets, netAE outperforms various dimensionality reduction baselines and achieves satisfactory classification accuracy even when the labeled set is very small, without disrupting the similarity structure of the original space. Availability and implementation The code of netAE is available on GitHub: https://github.com/LeoZDong/netAE. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document