Thomas Höllt

Approximated and User Steerable tSNE for Progressive Visual Analytics

Progressive Visual Analytics aims at improving the interactivity in existing analytics techniques by means of visualization as well as interaction with intermediate results. One key method for data analysis is dimensionality reduction, for example, to produce 2D embeddings that can be visualized and analyzed efficiently. t-Distributed Stochastic Neighbor Embedding (tSNE) is a well-suited technique for the visualization of high-dimensional data. tSNE can create meaningful intermediate results but suffers from a slow initialization that constrains its application in Progressive Visual Analytics. We introduce a controllable tSNE approximation (A-tSNE), which trades off speed and accuracy, to enable interactive data exploration. We offer real-time visualization techniques, including a density-based solution and a Magic Lens to inspect the degree of approximation. With this feedback, the user can decide on local refinements and steer the approximation level during the analysis. We demonstrate our technique with several datasets, in a real-world research scenario and for the real-time analysis of high-dimensional streams to illustrate its effectiveness for interactive data analysis.

Hierarchical stochastic neighbor embedding

In recent years, dimensionality‐reduction techniques have been developed and are widely used for hypothesis generation in Exploratory Data Analysis. However, these techniques are confronted with overcoming the trade‐off between computation time and the quality of the provided dimensionality reduction. In this work, we address this limitation, by introducing Hierarchical Stochastic Neighbor Embedding (Hierarchical‐SNE). Using a hierarchical representation of the data, we incorporate the well‐known mantra of Overview‐First, Details‐On‐Demand in non‐linear dimensionality reduction. First, the analysis shows an embedding, that reveals only the dominant structures in the data (Overview). Then, by selecting structures that are visible in the overview, the user can filter the data and drill down in the hierarchy. While the user descends into the hierarchy, detailed visualizations of the high‐dimensional structures will lead to new insights. In this paper, we explain how Hierarchical‐SNE scales to the analysis of big datasets. In addition, we show its application potential in the visualization of Deep‐Learning architectures and the analysis of hyperspectral images.

DeepEyes: Progressive Visual Analytics for Designing Deep Neural Networks

Deep neural networks are now rivaling human accuracy in several pattern recognition problems. Compared to traditional classifiers, where features are handcrafted, neural networks learn increasingly complex features directly from the data. Instead of handcrafting the features, it is now the network architecture that is manually engineered. The network architecture parameters such as the number of layers or the number of filters per layer and their interconnections are essential for good performance. Even though basic design guidelines exist, designing a neural network is an iterative trial-and-error process that takes days or even weeks to perform due to the large datasets used for training. In this paper, we present DeepEyes, a Progressive Visual Analytics system that supports the design of neural networks during training. We present novel visualizations, supporting the identification of layers that learned a stable set of patterns and, therefore, are of interest for a detailed analysis. The system facilitates the identification of problems, such as superfluous filters or layers, and information that is not being captured by the network. We demonstrate the effectiveness of our system through multiple use cases, showing how a trained network can be compressed, reshaped and adapted to different problems.

Visual analysis of mass cytometry data by hierarchical stochastic neighbour embedding reveals rare cell types

Mass cytometry allows high-resolution dissection of the cellular composition of the immune system. However, the high-dimensionality, large size, and non-linear structure of the data poses considerable challenges for the data analysis. In particular, dimensionality reduction-based techniques like t-SNE offer single-cell resolution but are limited in the number of cells that can be analyzed. Here we introduce Hierarchical Stochastic Neighbor Embedding (HSNE) for the analysis of mass cytometry data sets. HSNE constructs a hierarchy of non-linear similarities that can be interactively explored with a stepwise increase in detail up to the single-cell level. We apply HSNE to a study on gastrointestinal disorders and three other available mass cytometry data sets. We find that HSNE efficiently replicates previous observations and identifies rare cell populations that were previously missed due to downsampling. Thus, HSNE removes the scalability limit of conventional t-SNE analysis, a feature that makes it highly suitable for the analysis of massive high-dimensional data sets.Single cell profiling yields high dimensional data of very large numbers of cells, posing challenges of visualization and analysis. Here the authors introduce a method for analysis of mass cytometry data that can handle very large datasets and allows their intuitive and hierarchical exploration.

Mass cytometry reveals innate lymphoid cell differentiation pathways in the human fetal intestine

Innate lymphoid cells (ILCs) are abundant in mucosal tissues and involved in tissue homeostasis and barrier function. Although several ILC subsets have been identified, it is unknown if additional heterogeneity exists, and their differentiation pathways remain largely unclear. We applied mass cytometry to analyze ILCs in the human fetal intestine and distinguished 34 distinct clusters through a t-SNE–based analysis. A lineage (Lin)−CD7+CD127−CD45RO+CD56+ population clustered between the CD127+ ILC and natural killer (NK) cell subsets, and expressed diverse levels of Eomes, T-bet, GATA3, and ROR&ggr;t. By visualizing the dynamics of the t-SNE computation, we identified smooth phenotypic transitions from cells within the Lin−CD7+CD127−CD45RO+CD56+ cluster to both the NK cells and CD127+ ILCs, revealing potential differentiation trajectories. In functional differentiation assays, the Lin−CD7+CD127−CD45RO+CD56+CD8a− cells could develop into CD45RA+ NK cells and CD127+ROR&ggr;t+ ILC3-like cells. Thus, we identified a previously unknown intermediate innate subset that can differentiate into ILC3 and NK cells.

BrainScope : Interactive visual exploration of the spatial and temporal human brain transcriptome

Abstract Spatial and temporal brain transcriptomics has recently emerged as an invaluable data source for molecular neuroscience. The complexity of such data poses considerable challenges for analysis and visualization. We present BrainScope: a web portal for fast, interactive visual exploration of the Allen Atlases of the adult and developing human brain transcriptome. Through a novel methodology to explore high-dimensional data (dual t-SNE), BrainScope enables the linked, all-in-one visualization of genes and samples across the whole brain and genome, and across developmental stages. We show that densities in t-SNE scatter plots of the spatial samples coincide with anatomical regions, and that densities in t-SNE scatter plots of the genes represent gene co-expression modules that are significantly enriched for biological functions. We also show that the topography of the gene t-SNE maps reflect brain region-specific gene functions, enabling hypothesis and data driven research. We demonstrate the discovery potential of BrainScope through three examples: (i) analysis of cell type specific gene sets, (ii) analysis of a set of stable gene co-expression modules across the adult human donors and (iii) analysis of the evolution of co-expression of oligodendrocyte specific genes over developmental stages. BrainScope is publicly accessible at www.brainscope.nl.

The Contribution of Cytomegalovirus Infection to Immune Senescence Is Set by the Infectious Dose

The relationship between human cytomegalovirus (HCMV) infections and accelerated immune senescence is controversial. Whereas some studies reported a CMV-associated impaired capacity to control heterologous infections at old age, other studies could not confirm this. We hypothesized that these discrepancies might relate to the variability in the infectious dose of CMV occurring in real life. Here, we investigated the influence of persistent CMV infection on immune perturbations and specifically addressed the role of the infectious dose on the contribution of CMV to accelerated immune senescence. We show in experimental mouse models that the degree of mouse CMV (MCMV)-specific memory CD8+ T cell accumulation and the phenotypic T cell profile are directly influenced by the infectious dose, and data on HCMV-specific T cells indicate a similar connection. Detailed cluster analysis of the memory CD8+ T cell development showed that high-dose infection causes a differentiation pathway that progresses faster throughout the life span of the host, suggesting a virus–host balance that is influenced by aging and infectious dose. Importantly, short-term MCMV infection in adult mice is not disadvantageous for heterologous superinfection with lymphocytic choriomeningitis virus (LCMV). However, following long-term CMV infection the strength of the CD8+ T cell immunity to LCMV superinfection was affected by the initial CMV infectious dose, wherein a high infectious dose was found to be a prerequisite for impaired heterologous immunity. Altogether our results underscore the importance of stratification based on the size and differentiation of the CMV-specific memory T cell pools for the impact on immune senescence, and indicate that reduction of the latent/lytic viral load can be beneficial to diminish CMV-associated immune senescence.

Overview + Detail Visualization for Ensembles of Diffusion Tensors

A Diffusion Tensor Imaging (DTI) group study consists of a collection of volumetric diffusion tensor datasets (i.e., an ensemble) acquired from a group of subjects. The multivariate nature of the diffusion tensor imposes challenges on the analysis and the visualization. These challenges are commonly tackled by reducing the diffusion tensors to scalar‐valued quantities that can be analyzed with common statistical tools. However, reducing tensors to scalars poses the risk of losing intrinsic information about the tensor. Visualization of tensor ensemble data without loss of information is still a largely unsolved problem. In this work, we propose an overview + detail visualization to facilitate the tensor ensemble exploration. We define an ensemble representative tensor and variations in terms of the three intrinsic tensor properties (i.e., scale, shape, and orientation) separately. The ensemble summary information is visually encoded into the newly designed aggregate tensor glyph which, in a spatial layout, functions as the overview. The aggregate tensor glyph guides the analyst to interesting areas that would need further detailed inspection. The detail views reveal the original information that is lost during aggregation. It helps the analyst to further understand the sources of variation and formulate hypotheses. To illustrate the applicability of our prototype, we compare with most relevant previous work through a user study and we present a case study on the analysis of a brain diffusion tensor dataset ensemble from healthy volunteers.

Predicting cell types in single cell mass cytometry data

Motivation Mass cytometry (CyTOF) is a valuable technology for high-dimensional analysis at the single cell level. Identification of different cell populations is an important task during the data analysis. Many clustering tools can perform this task, however, they are time consuming, often involve a manual step, and lack reproducibility when new data is included in the analysis. Learning cell types from an annotated set of cells solves these problems. However, currently available mass cytometry classifiers are either complex, dependent on prior knowledge of the cell type markers during the learning process, or can only identify canonical cell types. Results We propose to use a Linear Discriminant Analysis (LDA) classifier to automatically identify cell populations in CyTOF data. LDA shows comparable results with two state-of-the-art algorithms on four benchmark datasets and also outperforms a non-linear classifier such as the k-nearest neighbour classifier. To illustrate its scalability to large datasets with deeply annotated cell subtypes, we apply LDA to a dataset of ~3.5 million cells representing 57 cell types. LDA has high performance on abundant cell types as well as the majority of rare cell types, and provides accurate estimates of cell type frequencies. Further incorporating a rejection option, based on the estimated posterior probabilities, allows LDA to identify cell types that were not encountered during training. Altogether, reproducible prediction of cell type compositions using LDA opens up possibilities to analyse large cohort studies based on mass cytometry data. Availability Implementation is available on GitHub (https://github.com/tabdelaal/CyTOF-Linear-Classifier). Contact a.mahfouz@lumc.nl

Heterogeneity of circulating CD8 T-cells specific to islet, neo-antigen and virus in patients with type 1 diabetes mellitus

Auto-reactive CD8 T-cells play an important role in the destruction of pancreatic β-cells resulting in type 1 diabetes (T1D). However, the phenotype of these auto-reactive cytolytic CD8 T-cells has not yet been extensively described. We used high-dimensional mass cytometry to phenotype autoantigen- (pre-proinsulin), neoantigen- (insulin-DRIP) and virus- (cytomegalovirus) reactive CD8 T-cells in peripheral blood mononuclear cells (PBMCs) of T1D patients. A panel of 33 monoclonal antibodies was designed to further characterise these cells at the single-cell level. HLA-A2 class I tetramers were used for the detection of antigen-specific CD8 T-cells. Using a novel Hierarchical Stochastic Neighbor Embedding (HSNE) tool (implemented in Cytosplore), we identified 42 clusters within the CD8 T-cell compartment of three T1D patients and revealed profound heterogeneity between individuals, as each patient displayed a distinct cluster distribution. Single-cell analysis of pre-proinsulin, insulin-DRIP and cytomegalovirus-specific CD8 T-cells showed that the detected specificities were heterogeneous between and within patients. These findings emphasize the challenge to define the obscure nature of auto-reactive CD8 T-cells.