doi.bio/chloe_hsu

Chloe Hsu

Chloe Hsu is a researcher and 3rd-year PhD student at UC Berkeley, advised by Jennifer Listgarten and Moritz Hardt. Her research interests lie in the application of machine learning to the design, engineering, and interpretation of proteins. Outside of her academic pursuits, Hsu has also explored the worlds of art and business.

Education and Work

Hsu is currently pursuing her PhD at the University of California, Berkeley, where she also completed her undergraduate studies in mathematics and theoretical computer science. During her time at Caltech, she worked as a machine learning engineer at Google Health.

Research Focus

Hsu's research contributes to the machine learning foundation for protein structure prediction and design. Her work involves developing machine learning methods for structure-based protein design and sequence ranking in protein engineering. One of her notable contributions is her paper on "Learning inverse folding from millions of predicted structures," which was recognized as an Outstanding Paper Runner Up at ICML in 2022. In this work, she presented a more accurate approach to structure-based sequence design, utilizing 12M new predicted structures as additional training data.

Hsu has also co-authored papers on protein fitness models, epigenetic modifications, and the application of machine learning techniques in immunology. Her PhD work is supported by the Berkeley Graduate Fellowship and the Microsoft Research PhD Fellowship.

Art and Business

Chloe Hsu has also explored creative pursuits, winning the 2016 Scholastic California Regional Awards Gold Key for her drypoint print with watercolor and linocut prints. Additionally, she has worked in the business world, with experience at KPMG and as a Dragon Systems Engineer at SpaceX.

Chloe Hsu

Chloe Hsu is a researcher in the field of machine learning and protein engineering. She is currently a 3rd-year PhD student at the University of California, Berkeley, advised by Jennifer Listgarten and Moritz Hardt. Her research focuses on the application of machine learning techniques to the design, engineering, and interpretation of proteins.

Education and Career

Prior to her PhD, Hsu studied mathematics and theoretical computer science at Caltech and worked as a machine learning engineer at Google Health. She has also received a number of awards and honours, including the Gold Presidential Volunteer Service Award and the Bronze Congressional Award.

Research and Publications

Hsu's research contributes to the machine learning basis for protein engineering and design. She has published several papers in this field, including:

"Learning inverse folding from millions of predicted structures" (2022), which won the ICML Outstanding Paper Runner Up Award.
"Learning protein fitness models from evolutionary and assay-labeled data" (2022), which proposed a hybrid approach to protein fitness prediction.
"Generative models for protein structures and sequences" (2024), published in Nature Biotechnology.