After earning a Data Science and Mathematics degree at New York University in 2024, Zirui (Frank) Feng, MDSAI, enrolled in Mount Sinai’s Master of Science in Biomedical Data Science and AI program. In the following Q&A, Mr. Feng discusses the experiences that shaped him and how he excelled.
What is your background?
I grew up in Hunan province, China. The COVID-19 pandemic shaped my early college years in a very personal way: I completed my freshman year remotely from home while watching how scientists fight with the rapidly evolving virus. I gained strong training in quantitative modeling, programming, machine learning, and large-scale data analysis. I later joined the laboratory of Yi Shi, PhD, at Mount Sinai as a part-time research assistant and began the Master of Science in Biomedical Data Science and AI program, where I found a way to connect my computational background with real biomedical discovery.
What first attracted you to this field?
My field is AI-guided antibody and protein design, which combines immunology, structural biology, machine learning, and computational modeling to design better therapeutic molecules. I was first attracted to this field because antibodies are one of the most powerful modalities in medicine, and AI creates new opportunities to understand and engineer them at a larger and faster scale. The COVID-19 pandemic made this interest feel urgent to me. I saw how quickly new viral variants could emerge, and I became interested in how AI could help rapidly design therapeutics against future pandemics. By modeling antibody–antigen interactions, exploring large sequence and structure spaces, and prioritizing promising candidates for experimental testing, AI can make therapeutic discovery more scalable and responsive. This is what drew me toward computational structural biology, nanobody discovery, and AI-guided therapeutic design.
Who were your mentors in the master program, and what are some of your research highlights?
Under Dr. Shi’s guidance, one of my major research highlights was leading the first-author study “One Thousand SARS-CoV-2 Antibody Structures Reveal Convergent Binding and Near-Universal Immune Escape,” published in Cell Systems in 2026. In this work, I analyzed more than 1,000 SARS-CoV-2 antibody structures and identified broad antigenicity across the receptor-binding domain, distinct binding strategies between IgGs and nanobodies, and near-universal immune escape by advanced Omicron variants.
I also contributed to “Repertoire-scale antibody structural prediction informs therapeutic design,” published in 2026 in Science Advances, which presents AF3-TurboAb, a high-throughput AlphaFold 3-based framework for repertoire-scale antibody–antigen structural prediction and therapeutic antibody design. Together, these accomplishments reflect my growth as a computational biomedical scientist and were recognized with the 2026 Commencement Award for Scientific Excellence in Biomedical Data Science at Mount Sinai.
Why Mount Sinai—what, specifically, are the strong points of this master program?
Mount Sinai was the right place for me because it combines biomedical research, quantitative training, translational science, and strong mentorship. The master’s program allowed me to learn computational and AI methods while applying them directly to real biological problems through highly accessible research resources. What I value most about the program is its supportive environment and flexibility. The curriculum gives students room to personalize their study track, choose courses that fit their goals, and shape their training around their own scientific direction. At the same time, the program offers abundant opportunities to rotate in different laboratories and gain research experience across multiple areas of biomedicine. This flexibility allowed me to build a path that connected data science, structural biology, immunology, and therapeutic design, while also helping me explore the broader biomedical research environment.
How else did you excel at Mount Sinai?
I grew as a scientific communicator. I presented my antibody research three times in the Department of Pharmacological Sciences: first as a poster at the 2024 Annual Research Retreat, then as an oral presentation in the Work in Progress Discussion Series, and later as an oral presentation at the 2025 Annual Research Retreat. These experiences trained me to explain complex computational and structural biology projects clearly and to receive feedback from an interdisciplinary audience. Beyond Mount Sinai, I also explored how biomedical AI is applied in industry through internships at New York Stem Cell Foundation (NYSCF) and Regeneron Pharmaceuticals. At NYSCF, I worked on machine-learning-based contamination detection for cell-culture plates, and at Regeneron, I developed an AI system for scientific document search. These experiences helped me understand how industry teams organize research, build practical solutions, and translate computational methods into real biomedical workflows.
What’s Next?
I will continue my training in the PhD in Biomedical Sciences program at Mount Sinai, focusing on computational structural biology, antibody engineering, and AI-guided protein design. My goal is to understand the key principles behind effective therapeutic molecules and use them to design better treatments. Long term, I hope to become a biotech entrepreneur and help translate computational protein design into real therapeutic platforms. The master’s program at Mount Sinai helped me move from data science into biomedical discovery, and the next step for me is to become an independent scientist who can build technologies that turn molecular insight into medicines.