What does it mean to live, anyway?bookmark_border

Virtual cells employ machine learning models to simulate and predict cellular behaviors, serving as a critical computational framework for investigating health and disease. Injecting causal graphs into virtual cells can improve the interpretability, but such graphs are usually not available in real-world applications. Recently, many methods have been proposed to construct causal graphs from data, which group genes based on their similarities to form concepts and extract their causal relationships. However, since this automatic process is unsupervised, the causal graphs usually contain errors. In this paper, we propose a human-guided causal knowledge injection method for virtual cells. We developed a gene-similarity-aware causal graph visualization supported by a hybrid optimization algorithm to help explore both the causal relationships between concepts and the similarities between genes. Based on the exploration, we further developed a counterfactual analysis strategy supported by a counterfactual visualization and a causal path visualization to help validate and refine causal graphs. The effectiveness of our method is demonstrated through two real-world case studies, the extraction of scientifically meaningful causal insights, and positive feedback from domain experts.

We present Loom, a spatial transcriptomics (ST) visual computing system to support the analysis of pseudo-temporal trajectories, comparative investigation across samples and regions of interest, and the examination of spatially structured processes within local microenvironments. ST is a molecular profiling technology that measures gene expression directly within a thin tissue section while preserving its spatial organization. For practical application-driven analyses, the ST local microenvironment data needs to be integrated with cell reference datasets and temporal simulations of cell behavior. This integration is challenging due to multi-modal registration issues and the complexity of the pseudo-temporal patterns, spatial enrichment data, and gene expression dynamics. Loom leverages a novel glyph coupled with a computational backbone to facilitate the detailed pseudo-temporal exploration of local microenvironments, cross-sample comparisons, and investigation of spatiotemporal biological mechanisms. We evaluate Loom quantitatively through a performance study, through two case studies developed with experts in tissue pathology and oncologists, and through an external usability study. The results demonstrate that Loom supports effectively the discovery of cellular transitions and spatiotemporal expression dynamics.

Chemists and materials scientists increasingly use machine learning models, such as graph neural networks (GNNs), to predict properties of molecules and the outcomes of their reactions. Beyond predictive performance, understanding how these models organize chemical information internally in their latent spaces, i.e., the embeddings of the molecules, is critical. Analyzing latent spaces helps diagnose model behavior and assess whether the learned embeddings are organized in ways that reflect meaningful chemical relationships. Unfortunately, existing methods provide limited support for analyzing latent spaces across layers and across different model states (e.g., training epochs, model configurations, and input data), making it difficult to understand how these latent spaces evolve throughout a model or relate to chemical concepts. We present LatentFlow, a visual analytics system developed in collaboration with a domain expert for analyzing latent spaces in molecular GNNs. LatentFlow groups embeddings into clusters and supports exploration of latent spaces by tracking how these clusters change across layers and model states using a modified Sankey diagram. To support interpretation, LatentFlow links these clusters to representative molecules and their shared substructures, and it allows scientists to introduce their own domain knowledge and compare it with the patterns found in the latent spaces. We evaluate LatentFlow through two case studies. The results show that LatentFlow helps scientists understand how latent spaces evolve, identify meaningful molecular patterns, and better interpret model behavior.

Contemporary materials science research is heavily conducted in silico, involving massive simulations of the atomic-scale evolution of materials. Cataloging basic patterns in the atomic displacements is key to understanding and predicting the evolution of physical properties. However, the combinatorial complexity of the space of possible transitions coupled with the overwhelming amount of data being produced by high-throughput simulations make such an analysis extremely challenging and time-consuming for domain experts. The development of visual analytics systems that facilitate the exploration of simulation data is an active field of research. While these systems excel in identifying temporal regions of interest, they treat each timestep of a simulation as an independent event without considering the behavior of the atomic displacements between timesteps. We address this gap by introducing LAMDA, a visual analytics system that allows domain experts to quickly and systematically explore state-to-state transitions. In LAMDA, transitions are hierarchically categorized, providing a basis for cataloging displacement behavior, as well as enabling the analysis of simulations at different resolutions, ranging from very broad qualitative classes of transitions to very narrow definitions of unit processes. LAMDA supports navigating the hierarchy of transitions, enabling scientists to visualize the commonalities between different transitions in each class in terms of invariant features characterizing local atomic environments, and LAMDA simplifies the analysis by capturing user inputs through annotations. We evaluate our system through a case study and report on findings from our domain experts.

Effective visualization is essential for interpreting genomics data, yet researchers often face challenges in finding relevant, reusable examples. Existing tools offer limited support for searching the vast landscape of genomics visualizations, making the process of authoring new visualizations time-consuming and inefficient. To address this gap, we introduce Geranium, a data visualization retrieval system for searching and authoring genomics visualizations. Geranium supports multimodal retrieval, enabling users to query with images, text, or grammar based specifications. Retrieved examples serve as scaffolds for authoring, providing templates that researchers can adapt with their own data, thereby streamlining the mechanics of visualization construction. Geranium integrates three embedding methods to combine specialized and general knowledge: grammar-based embeddings tailored to genomics visualizations, multimodalem beddings from a biomedical vision-language foundation model, and text embeddings from a fine-tuned large language model. For each visualization, we construct a multimodal representation that includes a Gosling specification, a pixel-based rendering, and natural language descriptions. We evaluate embedding strategies to maximize top-k retrieval accuracy and conduct user studies with domain collaborators to gather feedback on usability. Our collection comprises 3,200 visualizations across 50 categories, ranging from single-view to coordinated multi-view designs and supporting applications from single-cell epigenomics to structural variation analysis.

Gene perturbation analysis plays a critical role in drug discovery by enabling researchers to investigate how interventions on specific genes influence global gene expression patterns within cells. Recent advances in artificial intelligence (AI)-driven virtual cell models have made it possible to predict gene expression outcomes for a wide range of perturbation strategies in silico, substantially reducing reliance on costly and time-consuming biological experiments. However, effectively exploring and interpreting the high-dimensional perturbation spaces produced by these models remains challenging due to the combinatorial nature of perturbations and the complex, cell-specific gene expression responses they generate. In this work, we present CellPrism, a visual analytics system designed to support the systematic exploration of gene perturbation strategies for drug discovery. Specifically, CellPrism integrates clustering-based overviews to summarize perturbation outcomes, a glyph-based representation to compactly encode gene expression patterns across cell types, and coordinated views that enable fine-grained comparison and interpretation of perturbation effects. We demonstrate the effectiveness of CellPrism through a real-world case study and expert interviews. This work highlights the value of visual analytics in bridging virtual cell modeling with expert-driven decision-making in drug discovery.

Rendering huge biological scenes with atomistic detail presents a significant challenge in molecular visualization due to the memory limitations inherent in traditional rendering approaches. In this paper, we propose a novel method for the interactive rendering of massive molecular scenes based on hardware-accelerated ray tracing. Our approach circumvents GPU memory constraints by introducing virtual instantiation of full-detail scene elements. Using instancing significantly reduces memory consumption while preserving the full atomistic detail of scenes comprising trillions of atoms, with interactive rendering performance and completely free user exploration. We utilize coarse meshes as proxy geometries to approximate the overall shape of biological compartments, and access all atomistic detail dynamically during ray tracing. We do this via a novel adaptive technique utilizing a volumetric shell layer of prisms extruded around proxy geometry triangles, and a virtual volume grid for the interior of each compartment. Our algorithm scales to enormous molecular scenes with minimal memory consumption and the potential to accommodate even larger scenes. Our method also supports advanced effects such as clipping planes and animations. We demonstrate the efficiency and scalability of our approach by rendering tens of instances of Red Blood Cell and SARS-CoV-2 models theoretically containing more than 20 trillion atoms.