Accurate structure prediction of biomolecular interactions with AlphaFold 3
Nature 630, 493–500 Core Contributor
I am currently a Staff Research Scientist at Google DeepMind, working on methods to identify, design, and improve proteins. Here, I have been fortunate to work with wonderful colleagues and collaborators on a number of projects, such as AlphaFold for protein complex prediction and AlphaProteo for protein design. Before this, I was a graduate student in Frances Arnold’s research group at the California Institute of Technology, where I co-established the machine learning subgroup. Prior to this, I did my undergraduate research at Cornell University with Matthew DeLisa.
And before that, I grew up in a small Texas town and spent a significant part of my childhood practicing piano and cello. My favorite composers are Bach, Beethoven, and Tchaikovsky.
If you’d like to drop a message, I am pretty responsive on twitter (@zvxywu), and slightly slower on linkedin.
Papers
Google Scholar2024
2023
Machine learning for protein engineering
Machine Learning in Molecular Sciences, 277–311 Corresponding Author
2021
Highly accurate protein structure prediction for the human proteome
Nature 596, 590–596
Protein sequence design with deep generative models
Current Opinion in Chemical Biology 65, 18–27
Advances in machine learning for directed evolution
Current Opinion in Structural Biology 69, 11–18
2020
Signal peptides generated by attention-based neural networks
ACS Synthetic Biology 9, 2154–2161
2019
Machine learning-assisted directed protein evolution with combinatorial libraries
PNAS 116, 8852–8858
Machine-learning-guided directed evolution for protein engineering
Nature Methods 16, 687–694
2018
Learned protein embeddings for machine learning
Bioinformatics 34, 2642–2648
Stereoselective enzymatic synthesis of heteroatom-substituted cyclopropanes
ACS Catalysis 8, 2629–2634