Devin P. Sullivan

Carnegie Mellon University, Science for Life Laboratory

Papers

Total Citations

H-Index

About

Devin P. Sullivan is a computational biologist whose work bridges machine learning and high-throughput microscopy to accelerate biological discovery. His primary research focuses on developing active learning frameworks that optimize experimental design, enabling researchers to efficiently determine compound effects on protein patterns without relying on strong modeling assumptions. His most-cited paper, "Active machine learning-driven experimentation to determine compound effects on protein patterns" (2016, 57 citations), introduced a data-driven approach that reduces the need for separate screens across multiple biological targets—a significant contribution to phenotypic screening. Sullivan also co-authored "Seeing More: A Future of Augmented Microscopy" (2018, 23 citations), a forward-looking perspective on integrating computational tools with imaging to enhance data interpretation. His work exemplifies how machine learning can transform traditional experimental workflows, making high-throughput biology more adaptive and resource-efficient. By pioneering active learning in cellular imaging, Sullivan has laid groundwork for smarter, faster hypothesis generation in drug discovery and systems biology.