​Agenda

​10:00 AM · Welcome and introductions

​10:15 AM · Research Spotlight: Xiaojing Sui, PhD
“Structural Proteomics Uncovers Systemic Conformational Remodeling in Early Aging and Stress”

​10:30 AM · Research Spotlight: Aleena Iraqui
“Trials We Can’t Run: Target Trial Emulation and the Future of Evidence from Real-World Data”

​10:45 AM · Research Spotlight: Julia Gross, PhD
“Evaluating AI Agents for Cross-Indication Evidence Review in Immunology”

​11:00 AM · Virtual networking

​What You'll Get

• ​Fresh perspectives on data analysis methods, from proteomics to AI agent evaluation

• ​Ideas for using biobank data creatively to answer big clinical questions without the cost of a clinical trial

• ​A chance to ask the speakers questions directly

• ​Thirty minutes of relaxed networking with peers across the world

​Featured Speakers:

​Xiaojing Sui, Ph.D.

​Dr. Sui is an aging and proteomics researcher who earned her PhD at the University of Melbourne and conducted independent postdoctoral research at Northwestern University. Recently recognized as a Rising Star in Proteomics and Metabolomics by the Journal of Proteome Research, she investigates how changes in protein structure contribute to aging, neurodegeneration, and loss of cellular resilience. In her talk, “Structural Proteomics Uncovers Systemic Conformational Remodeling in Early Aging and Stress,” she will present findings from quantitative structural proteomics studies in C. elegans, revealing that nearly one-third of the proteome undergoes structural changes early in aging, well before physiological decline. Her research also demonstrates how localized protein stress can trigger organism-wide structural instability, highlighting the interconnected nature of proteostasis and identifying new opportunities to understand and potentially intervene in aging-related dysfunction.

​Aleena Iraqui

​Aleena Iraqui is an M.S. Bioinformatics student and Zanghi-Dow Fellow at Northeastern University whose research bridges computational biology, machine learning, and clinical data science. As a visiting graduate student at the Broad Institute of MIT and Harvard, she applied causal inference and survival analysis to electronic health records to investigate the potential of diabetes medications in dementia prevention. Her work also spans drug discovery, neurobiology, and epilepsy classification, and she has led award-winning teams at several AI and biotechnology hackathons. In her talk, “Trials We Can't Run: Target Trial Emulation and the Future of Evidence from Real-World Data,” she will explore how target trial emulation can help researchers draw more reliable causal conclusions from observational health data when randomized clinical trials are impractical or impossible. Drawing on her research comparing metformin and sulfonylureas using the NIH All of Us cohort, she will discuss the strengths and limitations of this approach and its role alongside AI and emerging methodologies in accelerating the generation of trustworthy, human-relevant medical evidence.

​Julie Gross, Ph.D.

​Julia Gross is the resident biologist at GXL, where she evaluates AI agents against real-world scientific research questions and helps translate researchers’ needs into more reliable agentic tools. Trained as an immunologist, she earned her Ph.D. through NIAID and Emory University and published first-author research in Nature Communications on antibiotic-induced inflammation mediated by TLR9. As part of the inaugural AI for Science Fellowship at Worldwide Studios, she developed Watch Agent Run, a tool for independently verifying what research agents actually retrieve and read. In her talk, “Evaluating AI Agents for Cross-Indication Evidence Review in Immunology,” she will present a prototype that systematically evaluates evidence across 44 groups of immunomodulatory drugs and 27 autoimmune conditions. Drawing on early findings, she will highlight common failure modes, such as mistaking animal studies for human evidence or confusing mechanistic explanations with clinical efficacy, and discuss how transparent, source-grounded evidence grading can improve the accuracy, reliability, and scientific usefulness of AI agents in biomedical research.

​Call for Speakers

​Are you preparing for a conference talk, job talk, or thesis defense? Working on a new analysis or method you'd like input on? Share and receive feedbacks from colleagues and leaders across industry and academia in a 15, 30, or 60-minute talk at a future session. Whether you're in pharma/biotech or academia, working on anything from analytics to AI/ML methods, we'd love to hear from you! Works in progress are welcome. Reach out to one of the organizers to get started.