1
|
Sun Y, Kong L, Huang J, Deng H, Bian X, Li X, Cui F, Dou L, Cao C, Zou Q, Zhang Z. A comprehensive survey of dimensionality reduction and clustering methods for single-cell and spatial transcriptomics data. Brief Funct Genomics 2024:elae023. [PMID: 38860675 DOI: 10.1093/bfgp/elae023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Revised: 02/29/2024] [Accepted: 05/27/2024] [Indexed: 06/12/2024] Open
Abstract
In recent years, the application of single-cell transcriptomics and spatial transcriptomics analysis techniques has become increasingly widespread. Whether dealing with single-cell transcriptomic or spatial transcriptomic data, dimensionality reduction and clustering are indispensable. Both single-cell and spatial transcriptomic data are often high-dimensional, making the analysis and visualization of such data challenging. Through dimensionality reduction, it becomes possible to visualize the data in a lower-dimensional space, allowing for the observation of relationships and differences between cell subpopulations. Clustering enables the grouping of similar cells into the same cluster, aiding in the identification of distinct cell subpopulations and revealing cellular diversity, providing guidance for downstream analyses. In this review, we systematically summarized the most widely recognized algorithms employed for the dimensionality reduction and clustering analysis of single-cell transcriptomic and spatial transcriptomic data. This endeavor provides valuable insights and ideas that can contribute to the development of novel tools in this rapidly evolving field.
Collapse
Affiliation(s)
- Yidi Sun
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Lingling Kong
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Jiayi Huang
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Hongyan Deng
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Xinling Bian
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Xingfeng Li
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Feifei Cui
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| | - Lijun Dou
- Genomic Medicine Institute, Lerner Research Institute, Cleveland, OH 44106, United States
| | - Chen Cao
- School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing 210029, China
| | - Quan Zou
- Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China
- Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
| | - Zilong Zhang
- School of Computer Science and Technology, Hainan University, Haikou 570228, China
| |
Collapse
|
2
|
Cottrell S, Hozumi Y, Wei GW. K-nearest-neighbors induced topological PCA for single cell RNA-sequence data analysis. Comput Biol Med 2024; 175:108497. [PMID: 38678944 PMCID: PMC11090715 DOI: 10.1016/j.compbiomed.2024.108497] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2024] [Revised: 04/08/2024] [Accepted: 04/21/2024] [Indexed: 05/01/2024]
Abstract
Single-cell RNA sequencing (scRNA-seq) is widely used to reveal heterogeneity in cells, which has given us insights into cell-cell communication, cell differentiation, and differential gene expression. However, analyzing scRNA-seq data is a challenge due to sparsity and the large number of genes involved. Therefore, dimensionality reduction and feature selection are important for removing spurious signals and enhancing downstream analysis. Traditional PCA, a main workhorse in dimensionality reduction, lacks the ability to capture geometrical structure information embedded in the data, and previous graph Laplacian regularizations are limited by the analysis of only a single scale. We propose a topological Principal Components Analysis (tPCA) method by the combination of persistent Laplacian (PL) technique and L2,1 norm regularization to address multiscale and multiclass heterogeneity issues in data. We further introduce a k-Nearest-Neighbor (kNN) persistent Laplacian technique to improve the robustness of our persistent Laplacian method. The proposed kNN-PL is a new algebraic topology technique which addresses the many limitations of the traditional persistent homology. Rather than inducing filtration via the varying of a distance threshold, we introduced kNN-tPCA, where filtrations are achieved by varying the number of neighbors in a kNN network at each step, and find that this framework has significant implications for hyper-parameter tuning. We validate the efficacy of our proposed tPCA and kNN-tPCA methods on 11 diverse benchmark scRNA-seq datasets, and showcase that our methods outperform other unsupervised PCA enhancements from the literature, as well as popular Uniform Manifold Approximation (UMAP), t-Distributed Stochastic Neighbor Embedding (tSNE), and Projection Non-Negative Matrix Factorization (NMF) by significant margins. For example, tPCA provides up to 628%, 78%, and 149% improvements to UMAP, tSNE, and NMF, respectively on classification in the F1 metric, and kNN-tPCA offers 53%, 63%, and 32% improvements to UMAP, tSNE, and NMF, respectively on clustering in the ARI metric.
Collapse
Affiliation(s)
- Sean Cottrell
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| | - Yuta Hozumi
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA; Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA; Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, MI 48824, USA.
| |
Collapse
|
3
|
Baul S, Tanvir Ahmed K, Jiang Q, Wang G, Li Q, Yong J, Zhang W. Integrating spatial transcriptomics and bulk RNA-seq: predicting gene expression with enhanced resolution through graph attention networks. Brief Bioinform 2024; 25:bbae316. [PMID: 38960406 PMCID: PMC11221891 DOI: 10.1093/bib/bbae316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2024] [Revised: 06/04/2024] [Accepted: 06/17/2024] [Indexed: 07/05/2024] Open
Abstract
Spatial transcriptomics data play a crucial role in cancer research, providing a nuanced understanding of the spatial organization of gene expression within tumor tissues. Unraveling the spatial dynamics of gene expression can unveil key insights into tumor heterogeneity and aid in identifying potential therapeutic targets. However, in many large-scale cancer studies, spatial transcriptomics data are limited, with bulk RNA-seq and corresponding Whole Slide Image (WSI) data being more common (e.g. TCGA project). To address this gap, there is a critical need to develop methodologies that can estimate gene expression at near-cell (spot) level resolution from existing WSI and bulk RNA-seq data. This approach is essential for reanalyzing expansive cohort studies and uncovering novel biomarkers that have been overlooked in the initial assessments. In this study, we present STGAT (Spatial Transcriptomics Graph Attention Network), a novel approach leveraging Graph Attention Networks (GAT) to discern spatial dependencies among spots. Trained on spatial transcriptomics data, STGAT is designed to estimate gene expression profiles at spot-level resolution and predict whether each spot represents tumor or non-tumor tissue, especially in patient samples where only WSI and bulk RNA-seq data are available. Comprehensive tests on two breast cancer spatial transcriptomics datasets demonstrated that STGAT outperformed existing methods in accurately predicting gene expression. Further analyses using the TCGA breast cancer dataset revealed that gene expression estimated from tumor-only spots (predicted by STGAT) provides more accurate molecular signatures for breast cancer sub-type and tumor stage prediction, and also leading to improved patient survival and disease-free analysis. Availability: Code is available at https://github.com/compbiolabucf/STGAT.
Collapse
Affiliation(s)
- Sudipto Baul
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, United States
| | - Khandakar Tanvir Ahmed
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, United States
| | - Qibing Jiang
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, United States
| | - Guangyu Wang
- Houston Methodist Research Institute, Weill Cornell Medical College, Houston, TX 77030, United States
| | - Qian Li
- Department of Biostatistics, St. Jude Children’s Research Hospital, Memphis, TN 38105, United States
| | - Jeongsik Yong
- Department of Biochemistry, Molecular Biology and Biophysics, University of Minnesota Twin Cities, Minneapolis, MN 55455, United States
| | - Wei Zhang
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, United States
| |
Collapse
|
4
|
Brendel M, Su C, Bai Z, Zhang H, Elemento O, Wang F. Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review. GENOMICS, PROTEOMICS & BIOINFORMATICS 2022; 20:814-835. [PMID: 36528240 PMCID: PMC10025684 DOI: 10.1016/j.gpb.2022.11.011] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/23/2022] [Revised: 08/17/2022] [Accepted: 11/24/2022] [Indexed: 12/23/2022]
Abstract
Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.
Collapse
Affiliation(s)
- Matthew Brendel
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; Institute for Computational Biomedicine, Caryl and Israel Englander Institute for Precision Medicine, Department of Physiology and Biophysics, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA
| | - Chang Su
- Department of Health Service Administration and Policy, Temple University, Philadelphia, PA 19122, USA.
| | - Zilong Bai
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA
| | - Hao Zhang
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA
| | - Olivier Elemento
- Institute for Computational Biomedicine, Caryl and Israel Englander Institute for Precision Medicine, Department of Physiology and Biophysics, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA.
| |
Collapse
|
5
|
Sardoo AM, Zhang S, Ferraro TN, Keck TM, Chen Y. Decoding brain memory formation by single-cell RNA sequencing. Brief Bioinform 2022; 23:6713514. [PMID: 36156112 PMCID: PMC9677489 DOI: 10.1093/bib/bbac412] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Revised: 07/10/2022] [Accepted: 08/25/2022] [Indexed: 12/14/2022] Open
Abstract
To understand how distinct memories are formed and stored in the brain is an important and fundamental question in neuroscience and computational biology. A population of neurons, termed engram cells, represents the physiological manifestation of a specific memory trace and is characterized by dynamic changes in gene expression, which in turn alters the synaptic connectivity and excitability of these cells. Recent applications of single-cell RNA sequencing (scRNA-seq) and single-nucleus RNA sequencing (snRNA-seq) are promising approaches for delineating the dynamic expression profiles in these subsets of neurons, and thus understanding memory-specific genes, their combinatorial patterns and regulatory networks. The aim of this article is to review and discuss the experimental and computational procedures of sc/snRNA-seq, new studies of molecular mechanisms of memory aided by sc/snRNA-seq in human brain diseases and related mouse models, and computational challenges in understanding the regulatory mechanisms underlying long-term memory formation.
Collapse
Affiliation(s)
- Atlas M Sardoo
- Department of Biological & Biomedical Sciences, Rowan University, Glassboro, NJ 08028, USA
| | - Shaoqiang Zhang
- College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China
| | - Thomas N Ferraro
- Department of Biomedical Sciences, Cooper Medical School of Rowan University, Camden, NJ 08103, USA
| | - Thomas M Keck
- Department of Biological & Biomedical Sciences, Rowan University, Glassboro, NJ 08028, USA,Department of Chemistry & Biochemistry, Rowan University, Glassboro, NJ 08028, USA
| | - Yong Chen
- Corresponding author. Yong Chen, Department of Biological and Biomedical Sciences, Rowan University, Glassboro, NJ 08028, USA. Tel.: +1 856 256 4500; E-mail:
| |
Collapse
|
6
|
Baul S, Ahmed KT, Filipek J, Zhang W. omicsGAT: Graph Attention Network for Cancer Subtype Analyses. Int J Mol Sci 2022; 23:10220. [PMID: 36142140 PMCID: PMC9499656 DOI: 10.3390/ijms231810220] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2022] [Revised: 08/14/2022] [Accepted: 08/31/2022] [Indexed: 12/01/2022] Open
Abstract
The use of high-throughput omics technologies is becoming increasingly popular in all facets of biomedical science. The mRNA sequencing (RNA-seq) method reports quantitative measures of more than tens of thousands of biological features. It provides a more comprehensive molecular perspective of studied cancer mechanisms compared to traditional approaches. Graph-based learning models have been proposed to learn important hidden representations from gene expression data and network structure to improve cancer outcome prediction, patient stratification, and cell clustering. However, these graph-based methods cannot rank the importance of the different neighbors for a particular sample in the downstream cancer subtype analyses. In this study, we introduce omicsGAT, a graph attention network (GAT) model to integrate graph-based learning with an attention mechanism for RNA-seq data analysis. The multi-head attention mechanism in omicsGAT can more effectively secure information of a particular sample by assigning different attention coefficients to its neighbors. Comprehensive experiments on The Cancer Genome Atlas (TCGA) breast cancer and bladder cancer bulk RNA-seq data and two single-cell RNA-seq datasets validate that (1) the proposed model can effectively integrate neighborhood information of a sample and learn an embedding vector to improve disease phenotype prediction, cancer patient stratification, and cell clustering of the sample and (2) the attention matrix generated from the multi-head attention coefficients provides more useful information compared to the sample correlation-based adjacency matrix. From the results, we can conclude that some neighbors play a more important role than others in cancer subtype analyses of a particular sample based on the attention coefficient.
Collapse
Affiliation(s)
- Sudipto Baul
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
- Genomics and Bioinformatics Cluster, University of Central Florida, Orlando, FL 32816, USA
| | - Khandakar Tanvir Ahmed
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
- Genomics and Bioinformatics Cluster, University of Central Florida, Orlando, FL 32816, USA
| | - Joseph Filipek
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
- Genomics and Bioinformatics Cluster, University of Central Florida, Orlando, FL 32816, USA
| | - Wei Zhang
- Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA
- Genomics and Bioinformatics Cluster, University of Central Florida, Orlando, FL 32816, USA
| |
Collapse
|
7
|
Wang HY, Zhao JP, Zheng CH, Su YS. scCNC: A method based on Capsule Network for Clustering scRNA-seq Data. Bioinformatics 2022; 38:3703-3709. [PMID: 35699473 DOI: 10.1093/bioinformatics/btac393] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2021] [Revised: 05/28/2022] [Accepted: 06/11/2022] [Indexed: 11/12/2022] Open
Abstract
MOTIVATION A large number of studies have shown that clustering is a crucial step in scRNA-seq analysis. Most existing methods are based on unsupervised learning without the prior exploitation of any domain knowledge, which does not utilize available gold-standard labels. When confronted by the high dimensionality and general dropout events of scRNA-seq data, purely unsupervised clustering methods may not produce biologically interpretable clusters, which complicates cell type assignment. RESULTS In this paper, we propose a semi-supervised clustering method based on a capsule network named scCNC, that integrates domain knowledge into the clustering step. Significantly, we also propose a Semi-supervised Greedy Iterative Training (SGIT) method used to train the whole network. Experiments on some real scRNA-seq datasets show that scCNC can significantly improve clustering performance and facilitate downstream analyses. AVAILABILITY The source code of scCNC is freely available at https://github.com/WHY-17/scCNC. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Hai-Yun Wang
- College of Mathematics and System Sciences, Xinjiang University, Urumqi, China
| | - Jian-Ping Zhao
- College of Mathematics and System Sciences, Xinjiang University, Urumqi, China.,Institute of Mathematics and Physics, Xinjiang University, Urumqi, China
| | - Chun-Hou Zheng
- College of Mathematics and System Sciences, Xinjiang University, Urumqi, China.,School of Artificial Intelligence, Anhui University, Hefei, China
| | - Yan-Sen Su
- School of Artificial Intelligence, Anhui University, Hefei, China
| |
Collapse
|