Our founders and our team have a long track record of developing and publishing cutting-edge visualization methods, and we continue to do research and publish it at datavisyn. Our basic research work is also often funded by public agencies, which we gratefully acknowledge.
BioInsight is a unique solution to integrate large-scale pharmacogenomic data that enables biomarker exploration, validation, and discovery across preclinical models and drug screening studies from public and internal resources.
Go to publication→
We propose CIME4R—an open-source interactive web application for analyzing reaction optimization data and AI predictions, developed and tested with domain experts across three case studies.
Go to publication→
We present a design study created in collaboration with domain experts, using real-world data from live ultrasound sensor measurements to guide operators of injection molding machines.
Go to publication→
We present CIME, an interactive web-based system that allows users to inspect chemical data sets, visualize model explanations, compare interpretability techniques, and explore subgroups of compounds.
Go to publication→
Three studies comparing onboarding approaches for visualization tools, finding that an in-situ scrollytelling approach works well for visualization onboarding, and video tutorials help introduce interaction techniques.
Go to publication→
A systematic design space for onboarding in visualization, surveying academic and commercial approaches and the educational theories that inform them.
Go to publication→
We propose a process model for dashboard onboarding that formalizes and unifies diverse onboarding strategies, serving as an actionable blueprint for developing new onboarding systems.
Go to publication→
A novel visual approach to meta-analysis of interaction provenance, capturing user sessions as graphs of high-dimensional application states to extract patterns for analytical reasoning strategies.
Go to publication→
We describe patterns emerging from embedded decision-making trajectories across logic puzzles, strategy games, and optimization problems, and discuss the importance of suitably chosen representation spaces.
Go to publication→
Taggle is a tabular visualization technique for exploring and presenting large and complex tables, demonstrated on a case study of complex genomics data analysis for drug discovery.
Go to publication→
TourDino helps users who are not experts in statistics verify hypotheses and confirm insights, integrated into the Ordino drug discovery platform for identifying new drug targets.
Go to publication→
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, with findings stored, shared and reproduced via session management.
Go to publication→
A solution for efficient retrieval of analysis states structured as provenance graphs, demonstrated with a biomedical case study illustrating how it facilitates exploration by recalling states from earlier analyses.
Go to publication→
We present CLUE (Capture, Label, Understand, Explain), a model that tightly integrates data exploration and presentation of discoveries into shareable, retraceable visual stories.
Go to publication→
Domino is a multiform visualization technique for representing subsets and the relationships between them, demonstrated on a use case from cancer genomics analysis for drug discovery.
Go to publication→
LineUp is a scalable visualization technique using bar charts that supports ranking items on multiple heterogeneous attributes, and comparing multiple alternative rankings via integrated slope graphs.
Go to publication→Systems specially tailored to biomedical research are being developed with fully integrated provenance tracking, structured validation of research results, cutting-edge visual analytics and domain-specific support — designed to make the drug target discovery phase more efficient and improve the quality of drug candidates.
View project details→SEVA aims to help people quickly learn new tools for visual data analysis by developing automatically generated onboarding methods, evaluated through an iterative, user- and problem-oriented research process.
Visit project website→We're always open to academic partnerships and funded research projects — reach out anytime.
