Kimberly S. Smythe

The paper introduces an interactive spatial proteomics workflow for analyzing imaging data, enabling reproducible and customizable analysis of protein expression and localization in tissues.

PhenoBIC is a deep learning model that automates cell phenotyping in multiplex imaging data, outperforming manual methods and other ML approaches with an F1-score of ~0.88.

The paper shows that B cells specific for viral oncoproteins in Merkel cell carcinoma tumors predict long-term disease control and enhance T cell responses.

BayesSpace enhances spatial transcriptomics resolution and clustering, revealing tissue structures undetectable at lower resolutions.