Pengfei Tian

I’m Fei, a Research Scientist at Google DeepMind, where I’m interested in using AI to make fundamental biological discoveries.

• 2026 – Joined Google DeepMind.

Designing therapeutics for human health

• 2025 – Designed de novo antibodies and mini-binders, both validated in the wet lab.
• 2025 – Designed state-of-the-art DNA regulatory elements for DNA-based therapeutics.
• 2024 – Designed regulatory elements for ultra-stable mRNA, enabling an in vivo CAR-T therapy that outperformed the leading benchmark in non-human primates.
• 2023 – First use of generative models to engineer CRISPR–Cas.
• 2023 – Joined Lila Sciences as a founding member.

Designing enzymes for global sustainability

• 2019 – Joined R&D at Novonesis, where I designed enzyme variants across six classes, some of them in products used by billions of people:
  • DNase (Pristine®)
  • Mannanase (Mannaway®)
  • Lipase
  • Cellulase
  • PETase
  • Carbonic anhydrase

Before that

• 2018 – During my postdoc with Robert Best at the NIH, we published what is arguably the first study to design highly diverse protein sequences with a generative model and validate them in the wet lab.
• 2014 – Earned my PhD in Physics from the Niels Bohr Institute at the University of Copenhagen, advised by Kresten Lindorff-Larsen, Wouter Boomsma, Mogens Høgh Jensen, and Daniel Otzen. There, I accurately predicted the structure of an amyloid protein by decoding evolutionary patterns in protein sequences.