Madhu Sevvana
Principal Scientist in Structural Biology & Protein Design, Integration Lead Sanofi
Madhu is Structural Biology and Protein Design (SBPD) Integration Lead and Principal Scientist at Sanofi, where she shapes cross-site, cross-functional strategies that connect structural biology, AI/ML-driven design, and data-guided engineering to advance next-generation biologics and antibody discovery. With deep expertise spanning cryo-EM, X-ray crystallography, and computational biologics; and a track record of delivering 3D structures across 20+ portfolio projects, she combines experimental rigor with machine learning to translate molecular complexity into innovative therapeutics, while mentoring scientific talent and fostering global collaboration.
Seminars
As high-resolution cryo-EM becomes routine for biologics characterization, structure-guided protein design/engineering, increasingly augmented by machine learning, is transitioning from a specialized capability to a core accelerator of R&D timelines. However, many teams continue to encounter common bottlenecks: construct design decisions made too late in the process, inconsistent solubility/stability outcomes, and limited ability to engineer specific properties reliably without repeated iteration cycles.
This practical workshop will equip attendees with a structure-first, ML-informed framework for biologics engineering, emphasizing developability as critical gatekeepers for downstream success. Using literature-based examples and widely accessible tools such as Pymol, the session will demonstrate how structural biologists assess targets, select constructs, and propose engineering strategies achievable within industrial timelines.
Workshop Highlights:
- Construct Selection Strategies: Practical approaches to selecting constructs early in the design process including domains, truncations, linkers, and formats to enhance expression and structural tractability
- Integrated Feedback Loops: How experimental, data science, and ML teams collaborate to transform structural and biophysical data into fewer design iterations
- Hands-On Demonstrations: Step-by-step walkthroughs using published structures and common tools, complemented by peer discussion on how attendees approach similar decisions in their own work
