Featured Publication
Stellar quality control for single-cell image-based profiling with coSMicQC
Quality control for single-cell image-based profiling.
Research Focus
My work sits at the intersection of quantitative biology, image analysis, and machine learning. I study how image quality, segmentation quality, and robust computational methods can strengthen biological discovery and improve our ability to identify meaningful cellular phenotypes.
Publications
Progress and new challenges in image-based profiling
Scalable data harmonization for single-cell image-based profiling with CytoTable
High-content live-cell time-lapse imaging predicts cells about to die via apoptosis
High-content microscopy and machine learning characterize a cell morphology signature of NF1 genotype in Schwann cells
A morphology and secretome map of pyroptosis
Cell Painting and Machine Learning Distinguish Fibroblasts From Nonfailing and Failing Human Hearts
Joshua G. Travers and Jenna Tomkinson contributed equally as co-first authors.
Reproducible image-based profiling with Pycytominer
Toward generalizable phenotype prediction from single-cell morphology representations
Jenna Tomkinson and Roshan Kern contributed equally as co-first authors.
Presentations
Cell Painting and High-Content Imaging for Cellular Profiling
Invited talk for workshop hosted by the Office of Research Innovation covering how Cell Painting and high-content imaging can be used to profile cellular phenotypes for drug discovery.
Multiparametric data analysis, dimensionality & visualization methods
Invited talk educating attendees on methods for preprocessing single-cell image-based data, dimensionality reduction, and visualization techniques.
High-content imaging and machine learning predicts fibrosis in cardiac fibroblasts
Accepted podium presentation describing how high-content imaging and machine learning can predict fibrosis in cardiac fibroblasts.
Toward generalizable single-cell phenotype prediction from nucleus morphology representations
Invited talk for JUMP consortium describing work on developing model to predict single-cell phenotypes from nuclear morphology from Mitocheck consortium applied to JUMP-pilot data.
Technical Skills
Programming languages, workflow tools, and open-source image analysis software I use regularly for my research and work in quantitative biology.
Programming & Workflow
Languages and tools I use for data analysis, automation, and reproducible computational work.
Image Analysis Software
Open-source platforms, libraries, and development workflows I use for microscopy image processing, segmentation, and exploration.