Yew Mun Yip

Computational Chemistry Expert The Francis Crick Institute

With over four years of experience in computational chemistry, I have developed and applied a range of advanced techniques and tools to design and evaluate potential drug candidates for various therapeutic targets and indications. My core competencies include structure-based and ligand-based drug design, molecular docking, virtual screening, molecular dynamics simulations, and protein structure prediction and analysis.

As a computational chemist at Talo Labs, I designed AUTACs using state-of-the-art computational modeling and simulation tools, applying a deep understanding of protein-ligand interactions and the latest developments in drug discovery. Previously, I worked as a research scientist at Travecta Therapeutics, where I employed molecular dynamics simulations to gain insights into the transport mechanism of the protein MFSD2a, and to guide the optimization of asset molecules. I also collaborated with multiple research groups within the University as a research fellow at SysteMED Private Limited, where I used structural biology and computational chemistry techniques to provide atomistic insights into the target proteins and their interactions with potential drug candidates. My work has resulted in multiple publications, patents, and presentations in prestigious journals and conferences.

I am passionate about learning, creating, and working as a community in the exciting field of computational chemistry. I thrive in collaborative environments where diverse minds come together to brainstorm ideas and solve problems. I am eager to continue exploring and contributing to the discovery and development of novel and effective therapeutic agents.

Seminars

Tuesday 1st December 2026
Harnessing AI & Computational Chemistry: Accelerating Peptide Discovery from Hit Identification to Clinical Candidates

Are your AI-driven discovery workflows accelerating innovation, or simply generating more noise?

With AI rapidly transforming peptide discovery, how can you separate genuinely impactful technologies from overhyped solutions? Which computational approaches are delivering measurable improvements in hit identification, optimisation and candidate selection? And how can researchers overcome the limitations of current AI models when designing peptides with non-canonical amino acids and increasingly complex modalities?

This workshop will gather experts to discuss:

  • Distinguish between AI tools that deliver real value versus overhyped solutions that waste resources and time
  • Master co-folding methods like AlphaFold for identifying binders against challenging targets with non-canonical amino acids
  • Learn how molecular dynamics simulations can test and refine co-folding predictions by capturing how peptides behave in motion
  • Learn how to combine AI predictions, molecular dynamics simulations and experimental data generation with informed model training for superior hit discovery
  • Discover which AI-driven design approaches work for macrocyclic peptides versus structured mini-binders.
Yew Mun Yip, Computational Chemistry Expert at The Francis Crick Institute.