CIME4R: Exploring iterative, AI-guided chemical reaction optimization campaigns in their parameter space.

Chemical reaction optimization (RO) is an iterative process that results in large, high-dimensional datasets. Current tools allow for only limited analysis and understanding of parameter spaces, making it hard for scientists to review or follow changes throughout the process. With the recent emergence of using artificial intelligence (AI) models to aid RO, another level of complexity has been added. Helping to assess the quality of a model's prediction and understand its decision is critical to supporting human-AI collaboration and trust calibration. To address this, we propose CIME4R-an open-source interactive web application for analyzing RO data and AI predictions. CIME4R supports users in (i) comprehending a reaction parameter space, (ii) investigating how an RO process developed over iterations, (iii) identifying critical factors of a reaction, and (iv) understanding model predictions. This facilitates making informed decisions during the RO process and helps users to review a completed RO process, especially in AI-guided RO. CIME4R aids decision-making through the interaction between humans and AI by combining the strengths of expert experience and high computational precision. We developed and tested CIME4R with domain experts and verified its usefulness in three case studies. Using CIME4R the experts were able to produce valuable insights from past RO campaigns and to make informed decisions on which experiments to perform next. We believe that CIME4R is the beginning of an open-source community project with the potential to improve the workflow of scientists working in the reaction optimization domain. SCIENTIFIC CONTRIBUTION: To the best of our knowledge, CIME4R is the first open-source interactive web application tailored to the peculiar analysis requirements of reaction optimization (RO) campaigns. Due to the growing use of AI in RO, we developed CIME4R with a special focus on facilitating human-AI collaboration and understanding of AI models. We developed and evaluated CIME4R in collaboration with domain experts to verify its practical usefulness.

Marjorie: Visualizing Type 1 Diabetes Data to Support Pattern Exploration.

In this work we propose Marjorie, a visual analytics approach to address the challenge of analyzing patients' diabetes data during brief regular appointments with their diabetologists. Designed in consultation with diabetologists, Marjorie uses a combination of visual and algorithmic methods to support the exploration of patterns in the data. Patterns of interest include seasonal variations of the glucose profiles, and non-periodic patterns such as fluctuations around mealtimes or periods of hypoglycemia (i.e., glucose levels below the normal range). We introduce a unique representation of glucose data based on modified horizon graphs and hierarchical clustering of adjacent carbohydrate or insulin entries. Semantic zooming allows the exploration of patterns on different levels of temporal detail. We evaluated our solution in a case study, which demonstrated Marjorie's potential to provide valuable insights into therapy parameters and unfavorable eating habits, among others. The study results and informal feedback collected from target users suggest that Marjorie effectively supports patients and diabetologists in the joint exploration of patterns in diabetes data, potentially enabling more informed treatment decisions. A free copy of this paper and all supplemental materials are available at https://osf.io/34t8c/.

Transitioning to a Commercial Dashboarding System: Socio-Technical Observations and Opportunities.

Many long-established, traditional manufacturing businesses are becoming more digital and data-driven to improve their production. These companies are embracing visual analytics in these transitions through their adoption of commercial dashboarding systems. Although a number of studies have looked at the technical challenges of adopting these systems, very few have focused on the socio-technical issues that arise. In this paper, we report on the results of an interview study with 17 participants working in a range of roles at a long-established, traditional manufacturing company as they adopted Microsoft Power BI. The results highlight a number of socio-technical challenges the employees faced, including difficulties in training, using and creating dashboards, and transitioning to a modern digital company. Based on these results, we propose a number of opportunities for both companies and visualization researchers to improve these difficult transitions, as well as opportunities for rethinking how we design dashboarding systems for real-world use.

Fuzzy Spreadsheet: Understanding and Exploring Uncertainties in Tabular Calculations.

Spreadsheet-based tools provide a simple yet effective way of calculating values, which makes them the number-one choice for building and formalizing simple models for budget planning and many other applications. A cell in a spreadsheet holds one specific value and gives a discrete, overprecise view of the underlying model. Therefore, spreadsheets are of limited use when investigating the inherent uncertainties of such models and answering what-if questions. Existing extensions typically require a complex modeling process that cannot easily be embedded in a tabular layout. In Fuzzy Spreadsheet, a cell can hold and display a distribution of values. This integrated uncertainty-handling immediately conveys sensitivity and robustness information. The fuzzification of the cells enables calculations not only with precise values but also with distributions, and probabilities. We conservatively added and carefully crafted visuals to maintain the look and feel of a traditional spreadsheet while facilitating what-if analyses. Given a user-specified reference cell, Fuzzy Spreadsheet automatically extracts and visualizes contextually relevant information, such as impact, uncertainty, and degree of neighborhood, for the selected and related cells. To evaluate its usability and the perceived mental effort required, we conducted a user study. The results show that our approach outperforms traditional spreadsheets in terms of answer correctness, response time, and perceived mental effort in almost all tasks tested.

Provectories: Embedding-Based Analysis of Interaction Provenance Data.

Understanding user behavior patterns and visual analysis strategies is a long-standing challenge. Existing approaches rely largely on time-consuming manual processes such as interviews and the analysis of observational data. While it is technically possible to capture a history of user interactions and application states, it remains difficult to extract and describe analysis strategies based on interaction provenance. In this article, we propose a novel visual approach to the meta-analysis of interaction provenance. We capture single and multiple user sessions as graphs of high-dimensional application states. Our meta-analysis is based on two different types of two-dimensional embeddings of these high-dimensional states: layouts based on (i) topology and (ii) attribute similarity. We applied these visualization approaches to synthetic and real user provenance data captured in two user studies. From our visualizations, we were able to extract patterns for data types and analytical reasoning strategies.

Visual Exploration of Relationships and Structure in Low-Dimensional Embeddings.

In this work, we propose an interactive visual approach for the exploration and formation of structural relationships in embeddings of high-dimensional data. These structural relationships, such as item sequences, associations of items with groups, and hierarchies between groups of items, are defining properties of many real-world datasets. Nevertheless, most existing methods for the visual exploration of embeddings treat these structures as second-class citizens or do not take them into account at all. In our proposed analysis workflow, users explore enriched scatterplots of the embedding, in which relationships between items and/or groups are visually highlighted. The original high-dimensional data for single items, groups of items, or differences between connected items and groups are accessible through additional summary visualizations. We carefully tailored these summary and difference visualizations to the various data types and semantic contexts. During their exploratory analysis, users can externalize their insights by setting up additional groups and relationships between items and/or groups. We demonstrate the utility and potential impact of our approach by means of two use cases and multiple examples from various domains.

ParaDime: A Framework for Parametric Dimensionality Reduction.

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.

ChemInformatics Model Explorer (CIME): exploratory analysis of chemical model explanations.

The introduction of machine learning to small molecule research- an inherently multidisciplinary field in which chemists and data scientists combine their expertise and collaborate - has been vital to making screening processes more efficient. In recent years, numerous models that predict pharmacokinetic properties or bioactivity have been published, and these are used on a daily basis by chemists to make decisions and prioritize ideas. The emerging field of explainable artificial intelligence is opening up new possibilities for understanding the reasoning that underlies a model. In small molecule research, this means relating contributions of substructures of compounds to their predicted properties, which in turn also allows the areas of the compounds that have the greatest influence on the outcome to be identified. However, there is no interactive visualization tool that facilitates such interdisciplinary collaborations towards interpretability of machine learning models for small molecules. To fill this gap, we present CIME (ChemInformatics Model Explorer), an interactive web-based system that allows users to inspect chemical data sets, visualize model explanations, compare interpretability techniques, and explore subgroups of compounds. The tool is model-agnostic and can be run on a server or a workstation.

ConfusionFlow: A Model-Agnostic Visualization for Temporal Analysis of Classifier Confusion.

Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. During model selection and debugging, data scientists need to assess classifiers' performances, evaluate their learning behavior over time, and compare different models. Typically, this analysis is based on single-number performance measures such as accuracy. A more detailed evaluation of classifiers is possible by inspecting class errors. The confusion matrix is an established way for visualizing these class errors, but it was not designed with temporal or comparative analysis in mind. More generally, established performance analysis systems do not allow a combined temporal and comparative analysis of class-level information. To address this issue, we propose ConfusionFlow, an interactive, comparative visualization tool that combines the benefits of class confusion matrices with the visualization of performance characteristics over time. ConfusionFlow is model-agnostic and can be used to compare performances for different model types, model architectures, and/or training and test datasets. We demonstrate the usefulness of ConfusionFlow in a case study on instance selection strategies in active learning. We further assess the scalability of ConfusionFlow and present a use case in the context of neural network pruning.

Coral: a web-based visual analysis tool for creating and characterizing cohorts.

SUMMARY: A main task in computational cancer analysis is the identification of patient subgroups (i.e. cohorts) based on metadata attributes (patient stratification) or genomic markers of response (biomarkers). Coral is a web-based cohort analysis tool that is designed to support this task: Users can interactively create and refine cohorts, which can then be compared, characterized and inspected down to the level of single items. Coral visualizes the evolution of cohorts and also provides intuitive access to prevalence information. Furthermore, findings can be stored, shared and reproduced via the integrated session management. Coral is pre-loaded with data from over 128 000 samples from the AACR Project GENIE, the Cancer Genome Atlas and the Cell Line Encyclopedia. AVAILABILITY AND IMPLEMENTATION: Coral is publicly available at https://coral.caleydoapp.org. The source code is released at https://github.com/Caleydo/coral. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Guide Me in Analysis: A Framework for Guidance Designers.

Guidance is an emerging topic in the field of visual analytics. Guidance can support users in pursuing their analytical goals more efficiently and help in making the analysis successful. However, it is not clear how guidance approaches should be designed and what specific factors should be considered for effective support. In this paper, we approach this problem from the perspective of guidance designers. We present a framework comprising requirements and a set of specific phases designers should go through when designing guidance for visual analytics. We relate this process with a set of quality criteria we aim to support with our framework, that are necessary for obtaining a suitable and effective guidance solution. To demonstrate the practical usability of our methodology, we apply our framework to the design of guidance in three analysis scenarios and a design walk-through session. Moreover, we list the emerging challenges and report how the framework can be used to design guidance solutions that mitigate these issues.

Ordino: a visual cancer analysis tool for ranking and exploring genes, cell lines and tissue samples.

SUMMARY: Ordino is a web-based analysis tool for cancer genomics that allows users to flexibly rank, filter and explore genes, cell lines and tissue samples based on pre-loaded data, including The Cancer Genome Atlas, the Cancer Cell Line Encyclopedia and manually uploaded information. Interactive tabular data visualization that facilitates the user-driven prioritization process forms a core component of Ordino. Detail views of selected items complement the exploration. Findings can be stored, shared and reproduced via the integrated session management. AVAILABILITY AND IMPLEMENTATION: Ordino is publicly available at https://ordino.caleydoapp.org. The source code is released at https://github.com/Caleydo/ordino under the Mozilla Public License 2.0. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Juniper: A Tree+ Table Approach to Multivariate Graph Visualization.

Analyzing large, multivariate graphs is an important problem in many domains, yet such graphs are challenging to visualize. In this paper, we introduce a novel, scalable, tree+table multivariate graph visualization technique, which makes many tasks related to multivariate graph analysis easier to achieve. The core principle we follow is to selectively query for nodes or subgraphs of interest and visualize these subgraphs as a spanning tree of the graph. The tree is laid out linearly, which enables us to juxtapose the nodes with a table visualization where diverse attributes can be shown. We also use this table as an adjacency matrix, so that the resulting technique is a hybrid node-link/adjacency matrix technique. We implement this concept in Juniper and complement it with a set of interaction techniques that enable analysts to dynamically grow, restructure, and aggregate the tree, as well as change the layout or show paths between nodes. We demonstrate the utility of our tool in usage scenarios for different multivariate networks: a bipartite network of scholars, papers, and citation metrics and a multitype network of story characters, places, books, etc.

KnowledgePearls: Provenance-Based Visualization Retrieval.

Storing analytical provenance generates a knowledge base with a large potential for recalling previous results and guiding users in future analyses. However, without extensive manual creation of meta information and annotations by the users, search and retrieval of analysis states can become tedious. We present KnowledgePearls, a solution for efficient retrieval of analysis states that are structured as provenance graphs containing automatically recorded user interactions and visualizations. As a core component, we describe a visual interface for querying and exploring analysis states based on their similarity to a partial definition of a requested analysis state. Depending on the use case, this definition may be provided explicitly by the user by formulating a search query or inferred from given reference states. We explain our approach using the example of efficient retrieval of demographic analyses by Hans Rosling and discuss our implementation for a fast look-up of previous states. Our approach is independent of the underlying visualization framework. We discuss the applicability for visualizations which are based on the declarative grammar Vega and we use a Vega-based implementation of Gapminder as guiding example. We additionally present a biomedical case study to illustrate how KnowledgePearls facilitates the exploration process by recalling states from earlier analyses.

TACO: Visualizing Changes in Tables Over Time.

Multivariate, tabular data is one of the most common data structures used in many different domains. Over time, tables can undergo changes in both structure and content, which results in multiple versions of the same table. A challenging task when working with such derived tables is to understand what exactly has changed between versions in terms of additions/deletions, reorder, merge/split, and content changes. For textual data, a variety of commonplace "diff" tools exist that support the task of investigating changes between revisions of a text. Although there are some comparison tools which assist users in inspecting differences between multiple table instances, the resulting visualizations are often difficult to interpret or do not scale to large tables with thousands of rows and columns. To address these challenges, we developed TACO, an interactive comparison tool that visualizes the differences between multiple tables at various levels of detail. With TACO we show (1) the aggregated differences between multiple table versions over time, (2) the aggregated changes between two selected table versions, and (3) detailed changes between the selected tables. To demonstrate the effectiveness of our approach, we show its application by means of two usage scenarios.

WeightLifter: Visual Weight Space Exploration for Multi-Criteria Decision Making.

A common strategy in Multi-Criteria Decision Making (MCDM) is to rank alternative solutions by weighted summary scores. Weights, however, are often abstract to the decision maker and can only be set by vague intuition. While previous work supports a point-wise exploration of weight spaces, we argue that MCDM can benefit from a regional and global visual analysis of weight spaces. Our main contribution is WeightLifter, a novel interactive visualization technique for weight-based MCDM that facilitates the exploration of weight spaces with up to ten criteria. Our technique enables users to better understand the sensitivity of a decision to changes of weights, to efficiently localize weight regions where a given solution ranks high, and to filter out solutions which do not rank high enough for any plausible combination of weights. We provide a comprehensive requirement analysis for weight-based MCDM and describe an interactive workflow that meets these requirements. For evaluation, we describe a usage scenario of WeightLifter in automotive engineering and report qualitative feedback from users of a deployed version as well as preliminary feedback from decision makers in multiple domains. This feedback confirms that WeightLifter increases both the efficiency of weight-based MCDM and the awareness of uncertainty in the ultimate decisions.

Characterizing Guidance in Visual Analytics.

Visual analytics (VA) is typically applied in scenarios where complex data has to be analyzed. Unfortunately, there is a natural correlation between the complexity of the data and the complexity of the tools to study them. An adverse effect of complicated tools is that analytical goals are more difficult to reach. Therefore, it makes sense to consider methods that guide or assist users in the visual analysis process. Several such methods already exist in the literature, yet we are lacking a general model that facilitates in-depth reasoning about guidance. We establish such a model by extending van Wijk's model of visualization with the fundamental components of guidance. Guidance is defined as a process that gradually narrows the gap that hinders effective continuation of the data analysis. We describe diverse inputs based on which guidance can be generated and discuss different degrees of guidance and means to incorporate guidance into VA tools. We use existing guidance approaches from the literature to illustrate the various aspects of our model. As a conclusion, we identify research challenges and suggest directions for future studies. With our work we take a necessary step to pave the way to a systematic development of guidance techniques that effectively support users in the context of VA.

ThermalPlot: Visualizing Multi-Attribute Time-Series Data Using a Thermal Metaphor.

Multi-attribute time-series data plays a vital role in many different domains, such as economics, sensor networks, and biology. An important task when making sense of such data is to provide users with an overview to identify items that show an interesting development over time, including both absolute and relative changes in multiple attributes simultaneously. However, this is not well supported by existing visualization techniques. To address this issue, we present ThermalPlot, a visualization technique that summarizes combinations of multiple attributes over time using an items position, the most salient visual variable. More precisely, the x-position in the ThermalPlot is based on a user-defined degree-of-interest (DoI) function that combines multiple attributes over time. The y-position is determined by the relative change in the DoI value ( ∆DoI) within a user-specified time window. Animating this mapping via a moving time window gives rise to circular movements of items over time-as in thermal systems. To help the user to identify important items that match user-defined temporal patterns and to increase the technique's scalability, we adapt the level of detail of the items' representation based on the DoI value. Furthermore, we present an interactive exploration environment for multi-attribute time-series data that ties together a carefully chosen set of visualizations, designed to support analysts in interacting with the ThermalPlot technique. We demonstrate the effectiveness of our technique by means of two usage scenarios that address the visual analysis of economic development data and of stock market data.