VoPo leverages cellular heterogeneity for predictive modeling of single-cell data.
Ontology highlight
ABSTRACT:
SUBMITTER: Stanley N
PROVIDER: S-EPMC7385162 | biostudies-literature | 2020 Jul
REPOSITORIES: biostudies-literature
Publications
VoPo leverages cellular heterogeneity for predictive modeling of single-cell data.
Stanley Natalie N Stelzer Ina A IA Tsai Amy S AS Fallahzadeh Ramin R Ganio Edward E Becker Martin M Phongpreecha Thanaphong T Nassar Huda H Ghaemi Sajjad S Maric Ivana I Culos Anthony A Chang Alan L AL Xenochristou Maria M Han Xiaoyuan X Espinosa Camilo C Rumer Kristen K Peterson Laura L Verdonk Franck F Gaudilliere Dyani D Tsai Eileen E Feyaerts Dorien D Einhaus Jakob J Ando Kazuo K Wong Ronald J RJ Obermoser Gerlinde G Shaw Gary M GM Stevenson David K DK Angst Martin S MS Gaudilliere Brice B Aghaeepour Nima N
Nature communications 20200727 1
High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity of cellular systems. We introduce VoPo (https://github.com/stanleyn/VoPo), a machine learning algorithm for predictive modeling and comprehensive visualization of the heterogeneity captured in large single-cell datasets. In three mass cytometry datasets, with the largest measuring hundreds of millions of cells over hundreds of samples, VoPo defines phenotypically and fu ...[more]
Similar Datasets
Project description:Single-cell DNA methylation data has become increasingly abundant and has uncovered many genes with a positive correlation between expression and promoter methylation, challenging the common dogma based on bulk data. However, computational tools for analyzing single-cell methylome data are lagging far behind. A number of tasks, including cell type calling and integration with transcriptome data, requires the construction of a robust gene activity matrix as the prerequisite but challenging task. The advent of multi-omics data enables measurement of both DNA methylation and gene expression for the same single cells. Although such data is rather sparse, they are sufficient to train supervised models that capture the complex relationship between DNA methylation and gene expression and predict gene activities at single-cell level. Here, we present methylome association by predictive linkage to expression (MAPLE), a computational framework that learns the association between DNA methylation and expression using both gene- and cell-dependent statistical features. Using multiple data sets generated with different experimental protocols, we show that using predicted gene activity values significantly improves several analysis tasks, including clustering, cell type identification, and integration with transcriptome data. Application of MAPLE revealed several interesting biological insights into the relationship between methylation and gene expression, including asymmetric importance of methylation signals around transcription start site for predicting gene expression, and increased predictive power of methylation signals in promoters located outside CpG islands and shores. With the rapid accumulation of single-cell epigenomics data, MAPLE provides a general framework for integrating such data with transcriptome data.
| S-EPMC7849382 | biostudies-literature
Project description:Recent technological advances have enabled spatially resolved measurements of expression profiles for hundreds to thousands of genes in fixed tissues at single-cell resolution. However, scalable computational analysis methods able to take into consideration the inherent 3D spatial organization of cell types and nonuniform cellular densities within tissues are still lacking. To address this, we developed MERINGUE, a computational framework based on spatial autocorrelation and cross-correlation analysis to identify genes with spatially heterogeneous expression patterns, infer putative cell-cell communication, and perform spatially informed cell clustering in 2D and 3D in a density-agnostic manner using spatially resolved transcriptomic data. We applied MERINGUE to a variety of spatially resolved transcriptomic data sets including multiplexed error-robust fluorescence in situ hybridization (MERFISH), spatial transcriptomics, Slide-seq, and aligned in situ hybridization (ISH) data. We anticipate that such statistical analysis of spatially resolved transcriptomic data will facilitate our understanding of the interplay between cell state and spatial organization in tissue development and disease.
| S-EPMC8494224 | biostudies-literature
Project description:A pervasive challenge in brain imaging is the presence of noise that hinders investigation of underlying neural processes, with Magnetoencephalography (MEG) in particular having very low Signal-to-Noise Ratio (SNR). The established strategy to increase MEG's SNR involves averaging multiple repetitions of data corresponding to the same stimulus. However, repetition of stimulus can be undesirable, because underlying neural activity has been shown to change across trials, and repeating stimuli limits the breadth of the stimulus space experienced by subjects. In particular, the rising popularity of naturalistic studies with a single viewing of a movie or story necessitates the discovery of new approaches to increase SNR. We introduce a simple framework to reduce noise in single-trial MEG data by leveraging correlations in neural responses across subjects as they experience the same stimulus. We demonstrate its use in a naturalistic reading comprehension task with 8 subjects, with MEG data collected while they read the same story a single time. We find that our procedure results in data with reduced noise and allows for better discovery of neural phenomena. As proof-of-concept, we show that the N400m's correlation with word surprisal, an established finding in literature, is far more clearly observed in the denoised data than the original data. The denoised data also shows higher decoding and encoding accuracy than the original data, indicating that the neural signals associated with reading are either preserved or enhanced after the denoising procedure.
| S-EPMC8632362 | biostudies-literature
Project description:Mural cells (MCs) wrap around the endothelium, and participate in the development and homeostasis of vasculature. MCs have been reported as heterogeneous population morphologically and functionally. However, the transcriptional heterogeneity of MCs was rarely studied. In this study, we illustrated the transcriptional heterogeneity of MCs with different perspectives by using publicly available single-cell dataset GSE109774. Specifically, MCs are transcriptionally different from other cell types, and ligand-receptor interactions of different cells with MCs vary. Re-clustering of MCs identified five distinct subclusters. The heterogeneity of MCs in tissues was reflected by MC coverage, various distribution of MC subclusters, and ligand-receptor interactions of MCs and parenchymal cells. The transcriptomic diversity of MCs revealed in this article will help facilitate further research into MCs.
| S-EPMC7649565 | biostudies-literature
Project description:A fundamental goal in the biological sciences is to determine how individual cells with varied gene expression profiles and diverse functional characteristics contribute to development, physiology, and disease. Here, we report a novel strategy to assess gene expression and cell physiology in single living cells. Our approach utilizes fluorescently labeled mRNA-specific anti-sense RNA probes and dsRNA-binding protein to identify the expression of specific genes in real-time at single-cell resolution via FRET. We use this technology to identify distinct myocardial subpopulations expressing the structural proteins myosin heavy chain ? and myosin light chain 2a in real-time during early differentiation of human pluripotent stem cells. We combine this live-cell gene expression analysis with detailed physiologic phenotyping to capture the functional evolution of these early myocardial subpopulations during lineage specification and diversification. This live-cell mRNA imaging approach will have wide ranging application wherever heterogeneity plays an important biological role.
| S-EPMC6861004 | biostudies-literature
Project description:Asthma is a chronic inflammatory disease of the airways that afflicts over 30 million individuals in the United States and over 300 million individuals worldwide. The inflammatory response in the airways is often characterized by the analysis of sputum, which contains multiple types of cells including neutrophils, macrophages, lymphocytes, and rare bronchial epithelial cells. Subtyping patients using microscopy of the sputum has identified both neutrophilic and eosinophilic infiltrates in airway inflammation. However, with the extensive heterogeneity among these cell types, a higher resolution understanding of the inflammatory cell types present in the sputum is needed to dissect the heterogeneity of disease. Improved recognition of the distinct phenotypes and sources of inflammation in asthmatic granulocytes may identify relevant pathways for clinical management or investigation of novel therapeutic mediators. Here, we employed mass cytometry or cytometry by time-of-flight to quantify frequency and define functional status of sputum derived airway cells in asthmatic patients and healthy controls. This in-depth single cell analysis method identified multiple distinct subtypes of airway immune cells, especially in neutrophils. Significance was discovered by statistical analysis as well as a data-driven unbiased clustering approach. Our multidimensional assessment method identifies differences in cellular function and supports identification of cellular status that may contribute to diverse clinical responses. This technical advance is relevant for studies of pathogenesis and may provide meaningful insights to advance our knowledge of asthmatic inflammation.
| S-EPMC8087109 | biostudies-literature
Project description:Study questionWhat are the cellular composition and single-cell transcriptomic differences between myometrium and leiomyomas as defined by single-cell RNA sequencing?Summary answerWe discovered cellular heterogeneity in smooth muscle cells (SMCs), fibroblast and endothelial cell populations in both myometrium and leiomyoma tissues.What is known alreadyPrevious studies have shown the presence of SMCs, fibroblasts, endothelial cells and immune cells in myometrium and leiomyomas. However, there is no information on the cellular heterogeneity in these tissues and the transcriptomic differences at the single-cell level between these tissues.Study design, size, durationWe collected five leiomyoma and five myometrium samples from a total of eight patients undergoing hysterectomy. We then performed single-cell RNA sequencing to generate a cell atlas for both tissues. We utilized our single-cell sequencing data to define cell types, compare cell types by tissue type (leiomyoma versus myometrium) and determine the transcriptional changes at a single-cell resolution between leiomyomas and myometrium. Additionally, we performed MED12-variant analysis at the single-cell level to determine the genotype heterogeneity within leiomyomas.Participants/materials, setting, methodsWe collected five MED12-variant positive leiomyomas and five myometrium samples from a total of eight patients. We then performed single-cell RNA sequencing on freshly isolated single-cell preparations. Histopathological assessment confirmed the identity of the samples. Sanger sequencing was performed to confirm the presence of the MED12 variant in leiomyomas.Main results and role of chanceOur data revealed previously unknown heterogeneity in the SMC, fibroblast cell and endothelial cell populations of myometrium and leiomyomas. We discovered the presence of two different lymphatic endothelial cell populations specific to uterine leiomyomas. We showed that both myometrium and MED12-variant leiomyomas are relatively similar in cellular composition but differ in cellular transcriptomic profiles. We found that fibroblasts influence the leiomyoma microenvironment through their interactions with endothelial cells, immune cells and SMCs. Variant analysis at the single-cell level revealed the presence of both MED12 variants as well as the wild-type MED12 allele in SMCs of leiomyomatous tissue. These results indicate genotype heterogeneity of cellular composition within leiomyomas.Large scale dataThe datasets are available in the NCBI Gene Expression Omnibus (GEO) using GSE162122.Limitations, reasons for cautionOur study focused on MED12-variant positive leiomyomas for single-cell RNA sequencing analyses. Leiomyomas carrying other genetic rearrangements may differ in their cellular composition and transcriptomic profiles.Wider implications for the findingsOur study provides a cellular atlas for myometrium and MED12-variant positive leiomyomas as defined by single-cell RNA sequencing. Our analysis provides significant insight into the differences between myometrium and leiomyomas at the single-cell level and reveals hitherto unknown genetic heterogeneity in multiple cell types within human leiomyomas. Our results will be important for future studies into the origin and growth of human leiomyomas.Study funding/competing interest(s)This work was supported by funding from the National Institute of Child Health and Human Development (HD098580 and HD088629). The authors declare no competing interests.
| S-EPMC9802286 | biostudies-literature
Project description:"A world in a wild flower, and a bodhi in a leaf," small cells contain huge secrets. The vasculature is composed of many multifunctional cell subpopulations, each of which is involved in the occurrence and development of cardiovascular diseases. Single-cell transcriptomics captures the full picture of genes expressed within individual cells, identifies rare or de novo cell subpopulations, analyzes single-cell trajectory and stem cell or progenitor cell lineage conversion, and compares healthy tissue and disease-related tissue at single-cell resolution. Single-cell transcriptomics has had a profound effect on the field of cardiovascular research over the past decade, as evidenced by the construction of cardiovascular cell landscape, as well as the clarification of cardiovascular diseases and the mechanism of stem cell or progenitor cell differentiation. The classification and proportion of cell subpopulations in vasculature vary with species, location, genotype, and disease, exhibiting unique gene expression characteristics in organ development, disease progression, and regression. Specific gene markers are expected to be the diagnostic criteria, therapeutic targets, or prognostic indicators of diseases. Therefore, treatment of vascular disease still has lots of potentials to develop. Herein, we summarize the cell clusters and gene expression patterns in normal vasculature and atherosclerosis, aortic aneurysm, and pulmonary hypertension to reveal vascular heterogeneity and new regulatory factors of cardiovascular disease in the use of single-cell transcriptomics and discuss its current limitations and promising clinical potential.
| S-EPMC8225933 | biostudies-literature
Project description:In recent years, mass spectrometry (MS)-based metabolomics has been extensively applied to characterize biochemical mechanisms, and study physiological processes and phenotypic changes associated with disease. Metabolomics has also been important for identifying biomarkers of interest suitable for clinical diagnosis. For the purpose of predictive modeling, in this chapter, we will review various supervised learning algorithms such as random forest (RF), support vector machine (SVM), and partial least squares-discriminant analysis (PLS-DA). In addition, we will also review feature selection methods for identifying the best combination of metabolites for an accurate predictive model. We conclude with best practices for reproducibility by including internal and external replication, reporting metrics to assess performance, and providing guidelines to avoid overfitting and to deal with imbalanced classes. An analysis of an example data will illustrate the use of different machine learning methods and performance metrics.
| S-EPMC7423323 | biostudies-literature
Project description:MotivationSingle-cell multimodal assays allow us to simultaneously measure two different molecular features of the same cell, enabling new insights into cellular heterogeneity, cell development and diseases. However, most existing methods suffer from inaccurate dimensionality reduction for the joint-modality data, hindering their discovery of novel or rare cell subpopulations.ResultsHere, we present VIMCCA, a computational framework based on variational-assisted multi-view canonical correlation analysis to integrate paired multimodal single-cell data. Our statistical model uses a common latent variable to interpret the common source of variances in two different data modalities. Our approach jointly learns an inference model and two modality-specific non-linear models by leveraging variational inference and deep learning. We perform VIMCCA and compare it with 10 existing state-of-the-art algorithms on four paired multi-modal datasets sequenced by different protocols. Results demonstrate that VIMCCA facilitates integrating various types of joint-modality data, thus leading to more reliable and accurate downstream analysis. VIMCCA improves our ability to identify novel or rare cell subtypes compared to existing widely used methods. Besides, it can also facilitate inferring cell lineage based on joint-modality profiles.Availability and implementationThe VIMCCA algorithm has been implemented in our toolkit package scbean (≥0.5.0), and its code has been archived at https://github.com/jhu99/scbean under MIT license.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9857983 | biostudies-literature