Cytosplore: Interactive Immune Cell Phenotyping for Large Single‐Cell Datasets

Höllt, Thomas; Pezzotti, Nicola; Unen, Vincent van; Koning, Frits; Eisemann, Elmar; Lelieveldt, Boudewijn P. F.; Vilanova, Anna

doi:10.1111/cgf.12893

Cited by 117 publications

(123 citation statements)

References 24 publications

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…Cytosplore [11] is an example of tools that use t-SNE for visual data exploration within a specific domain: single-cell analysis with mass cytometry data. Apart from showing a t-SNE projection of the data, Cytosplore is also supported by a domain-specific clustering technique which serves as the base for the rest of the provided visualizations, but is not generalizable to other domains.…”

Section: Comparison With Other Toolsmentioning

confidence: 99%

t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections

Chatzimparmpas

Martins

Kerren

2020

IEEE Trans. Visual. Comput. Graphics

115

View full text Add to dashboard Cite

t-Distributed Stochastic Neighbor Embedding (t-SNE) for the visualization of multidimensional data has proven to be a popular approach, with successful applications in a wide range of domains. Despite their usefulness, t-SNE projections can be hard to interpret or even misleading, which hurts the trustworthiness of the results. Understanding the details of t-SNE itself and the reasons behind specific patterns in its output may be a daunting task, especially for non-experts in dimensionality reduction. In this work, we present t-viSNE, an interactive tool for the visual exploration of t-SNE projections that enables analysts to inspect different aspects of their accuracy and meaning, such as the effects of hyper-parameters, distance and neighborhood preservation, densities and costs of specific neighborhoods, and the correlations between dimensions and visual patterns. We propose a coherent, accessible, and well-integrated collection of different views for the visualization of t-SNE projections. The applicability and usability of t-viSNE are demonstrated through hypothetical usage scenarios with real data sets. Finally, we present the results of a user study where the tool's effectiveness was evaluated. By bringing to light information that would normally be lost after running t-SNE, we hope to support analysts in using t-SNE and making its results better understandable.

show abstract

Section: Comparison With Other Toolsmentioning

confidence: 99%

t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections

Chatzimparmpas

Martins

Kerren

2020

IEEE Trans. Visual. Comput. Graphics

115

View full text Add to dashboard Cite

show abstract

“…Viable immune cells were manually gated from all acquired events and subsequently clustered by hierarchical-stochastic neighbour embedding (h-sne) using Cytosplore software (Fig. 1C,2) (Abdelmoula et al, 2018; Hollt et al, 2016; van Unen et al, 2017). H-sne is a recently developed method in which t-distributed stochastic neighbor embedding (t-sne) is performed sequentially to cluster first global cell populations, each of which is then in turn clustered into subpopulations.…”

Section: Resultsmentioning

confidence: 99%

Defining mucosal immunity using mass cytometry following experimental human pneumococcal challenge

Jochems

Ruiter

Solórzano

et al. 2019

Preprint

View full text Add to dashboard Cite

1 Streptococcus pneumoniae (Spn) is a common cause of respiratory infection, but also frequently 2 colonises the nasopharynx in the absence of disease. We used mass cytometry to study immune 3 cells from nasal biopsy samples, collected following experimental human pneumococcal challenge, 4 in order to identify immunological changes that follow and control spn colonisation. Using 37 5 markers, we characterized 293 nasal immune cell clusters, of which 7 were associated with Spn 6 colonisation. B cell and CD8 + CD161 + T cell clusters were significantly higher in non-colonised than 7 in colonised subjects. Spn colonization led to recirculation of not only Spn-specific but also 8 aspecific nasal B cells. This associated with increased numbers of circulating plasmablasts and 9 increased antibody levels against the unrelated bacterium Haemophilus influenzae. In addition, we 10 demonstrated that baseline functionality of blood mucosal associated invariant T (MAIT) cells 11 associated with protection against Spn. These results identify new host-pathogen interactions at 12 the mucosa upon Spn colonisation.13 14

show abstract

“…CellProfiler [14] is a widely-used open-source tool for cell-based screening that can segment and quantify cells grown in multi-well dishes using preconfigured pipelines. Related open-source and commercial tools include, Phaedra [53], HCSanalyzer [50], ScreenIt [22], Cytosplore [33], PerkElmer's High Content Profiler [24], and Genedata Screener [27]. Few of these tools are applicable to tissue imaging where image size is typically very large, the number of different cell types is substantial, and cells are crowded closely together in a complex environment.…”

Section: Related Workmentioning

confidence: 99%

Facetto: Combining Unsupervised and Supervised Learning for Hierarchical Phenotype Analysis in Multi-Channel Image Data

Krueger

Beyer

Jang

et al. 2019

Preprint

View full text Add to dashboard Cite

Fig. 1. Multiple coordinated views in Facetto for interactive and hierarchical phenotype analysis of 36-channel image data (image resolution: 31, 616 × 22, 272 pixels; raw image size: 49.8 GB). (a) Phenotype tree resulting from hierarchical data filtering and cell calling. (b) Multi-channel visualization of high-resolution CyCIF image data showing the current clustering and classification results. (c) Ridgeplot of high-dimensional feature data to steer visual analysis and data filtering. (d) UMAP projection of the sampled feature space of cells, colored by cluster ID. (e) Scatterplots showing feature value correlations. (f) Table view of all cells and their features.Abstract-Facetto is a scalable visual analytics application that is used to discover single-cell phenotypes in high-dimensional multi-channel microscopy images of human tumors and tissues. Such images represent the cutting edge of digital histology and promise to revolutionize how diseases such as cancer are studied, diagnosed, and treated. Highly multiplexed tissue images are complex, comprising 10 9 or more pixels, 60-plus channels, and millions of individual cells. This makes manual analysis challenging and error-prone. Existing automated approaches are also inadequate, in large part, because they are unable to effectively exploit the deep knowledge of human tissue biology available to anatomic pathologists. To overcome these challenges, Facetto enables a semi-automated analysis of cell types and states. It integrates unsupervised and supervised learning into the image and feature exploration process and offers tools for analytical provenance. Experts can cluster the data to discover new types of cancer and immune cells and use clustering results to train a convolutional neural network that classifies new cells accordingly. Likewise, the output of classifiers can be clustered to discover aggregate patterns and phenotype subsets. We also introduce a new hierarchical approach to keep track of analysis steps and data subsets created by users; this assists in the identification of cell types. Users can build phenotype trees and interact with the resulting hierarchical structures of both high-dimensional feature and image spaces. We report on use-cases in which domain scientists explore various large-scale fluorescence imaging datasets. We demonstrate how Facetto assists users in steering the clustering and classification process, inspecting analysis results, and gaining new scientific insights into cancer biology.

show abstract

Cytosplore: Interactive Immune Cell Phenotyping for Large Single‐Cell Datasets

Cited by 117 publications

References 24 publications

t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections

t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections

Defining mucosal immunity using mass cytometry following experimental human pneumococcal challenge

Facetto: Combining Unsupervised and Supervised Learning for Hierarchical Phenotype Analysis in Multi-Channel Image Data

Contact Info

Product

Resources

About