Jeff Winchell

I am an M.S. student in Computational Biology at Carnegie Mellon University, where I am fortunate to work in the Ma Lab with Spencer Krieger (now at Dartmouth). I develop machine-learning methods for spatial transcriptomics and single-cell data, with an emphasis on robust representation learning, interpretable models, and biologically grounded evaluation.

My current research focuses on a framework for identifying and removing transcript admixture from imaging-based spatial transcriptomics data. I study how segmentation errors and measurement noise affect cell-type annotations, marker-gene specificity, and downstream biological conclusions, and whether learned cleaning methods can improve robustness across tissues and experimental conditions.

Before joining CMU, I was a data scientist at the New York Stem Cell Foundation. I worked on high-content microscopy, image-quality assessment, interpretable feature extraction, and models of cellular state. This work contributed to first- and co-first-author publications in SLAS Discovery and iScience. I also developed research software, collaborated with experimental scientists, and mentored junior researchers.

More broadly, I am interested in representation learning for biological data, spatial and single-cell genomics, multimodal integration, and methods that remain reliable under noisy or mismatched experimental conditions. I plan to pursue a Ph.D. in computational biology and develop machine-learning approaches that provide both strong predictive performance and useful biological insight.

Outside research, I enjoy running, traveling, watching movies, and playing classical guitar.