Our lab studies interactive workflows for multiview data science. We draw inspiration from daily collaboration with researchers studying complex ecosystems, especially those within the microbiome.

We explore how data visualization, simulation, and representation learning can guide reasoning about data gathered from heterogeneous platforms, making it easy to see living systems from multiple perspectives simultaneously. In the process, we critically examine widespread data analysis practices, engage with developments in statistics methodology, and build modular, user-centric software. Ultimately, we aim to facilitate fluid, formal, and imaginative data analysis in problems critical to human and planetary health.

• Generative Models: An Interdisciplinary Perspective
• Tackling Climate Change with Machine Learning
• Multiscale Analysis of Count Data through Topic Alignment
• MolPad: An R-Shiny Package for Cluster Co-Expression Analysis in Longitudinal Microbiomics
• Mapping Glacial Lakes Using Historically Guided Segmentation Models
• Latent Variable Modeling for the Microbiome
• Multitable Methods for Microbiome Data Integration

Code adapted from Slime Mold Simulation through a CC BY-NA-SA 3.0 license.