Yao Fan
Director, Protein Design & Optimization Tectonic Therapeutic
Yao Fan has worked in the biotechnology and pharmaceutical industries since 2007. Yao began their career at Argonne National Laboratory, where they served as a Computational Postdoc Fellow and Postdoc. In 2013, they moved to UCSF as a Research Specialist. In 2016, they held two positions simultaneously: Senior Scientist at Boehringer Ingelheim, where they were responsible for technology development for new biotherapeutic molecules, and Senior Scientist at SRI International, where they headed the structural biology lab and was a biophysicist in the drug discovery pipeline. From 2019 to present, Yao Fan has been at AbbVie, where they have held the roles of Principal Research Scientist I and Senior Scientist III. Yao is currently the Director of Protein Design and Optimization at Tectonic Therapeutic, Inc.
Seminars
Late-stage failures driven by aggregation, instability, and manufacturability issues continue to impact biologics pipelines, often because developability is overlooked during early design. As organizations aim to reduce downstream re-engineering, this workshop will explore how to embed developability and CMC considerations earlier through better data strategies, integrated screening, and stronger alignment between discovery and CMC teams to select candidates that are both functional and scalable.
This workshop will focus on:
- How to identify developability risks such as aggregation, viscosity, instability and, poor expression earlier in design workflows using physicochemical and biophysical indicators
- How to integrate developability screening with sequence design and candidate selection to prioritize molecules that are stable at high concentration and suitable for manufacture
- How to improve data quality for developability prediction, including use of representative formulation conditions and more consistent screening assays
- How to embed manufacturability considerations, such as expression purification and, formulation constraints earlier to reduce downstream re-engineering
- How to improve alignment between discovery and CMC teams to enable better decision making and smoother progression from design to development
- Where has computational design actually moved the needle, and how are you proving it internally to speed up drug pipelines?
- How to control for data quality and biological reality in ML-driven design loops? And what specific changes have you made to your data generation strategy to make it truly usable for training models?
- How are you deciding what to prioritize today across de novo design, optimization workflows, and engineering, given they sit at different points in the hype cycle?
