TY - JOUR

T1 - De novo design of high-affinity binders of bioactive helical peptides

AU - Vázquez Torres, Susana

AU - Leung, Philip J.Y.

AU - Venkatesh, Preetham

AU - Lutz, Isaac D.

AU - Hink, Fabian

AU - Huynh, Huu Hien

AU - Becker, Jessica

AU - Yeh, Andy Hsien Wei

AU - Juergens, David

AU - Bennett, Nathaniel R.

AU - Hoofnagle, Andrew N.

AU - Huang, Eric

AU - MacCoss, Michael J.

AU - Expòsit, Marc

AU - Lee, Gyu Rie

AU - Bera, Asim K.

AU - Kang, Alex

AU - De La Cruz, Joshmyn

AU - Levine, Paul M.

AU - Li, Xinting

AU - Lamb, Mila

AU - Gerben, Stacey R.

AU - Murray, Analisa

AU - Heine, Piper

AU - Korkmaz, Elif Nihal

AU - Nivala, Jeff

AU - Stewart, Lance

AU - Watson, Joseph L.

AU - Rogers, Joseph M.

AU - Baker, David

N1 - Publisher Copyright: © The Author(s) 2023.

PY - 2024

Y1 - 2024

N2 - Many peptide hormones form an α-helix on binding their receptors1–4, and sensitive methods for their detection could contribute to better clinical management of disease5. De novo protein design can now generate binders with high affinity and specificity to structured proteins6,7. However, the design of interactions between proteins and short peptides with helical propensity is an unmet challenge. Here we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that by extending RFdiffusion8 to enable binder design to flexible targets, and to refining input structure models by successive noising and denoising (partial diffusion), picomolar-affinity binders can be generated to helical peptide targets by either refining designs generated with other methods, or completely de novo starting from random noise distributions without any subsequent experimental optimization. The RFdiffusion designs enable the enrichment and subsequent detection of parathyroid hormone and glucagon by mass spectrometry, and the construction of bioluminescence-based protein biosensors. The ability to design binders to conformationally variable targets, and to optimize by partial diffusion both natural and designed proteins, should be broadly useful.

AB - Many peptide hormones form an α-helix on binding their receptors1–4, and sensitive methods for their detection could contribute to better clinical management of disease5. De novo protein design can now generate binders with high affinity and specificity to structured proteins6,7. However, the design of interactions between proteins and short peptides with helical propensity is an unmet challenge. Here we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that by extending RFdiffusion8 to enable binder design to flexible targets, and to refining input structure models by successive noising and denoising (partial diffusion), picomolar-affinity binders can be generated to helical peptide targets by either refining designs generated with other methods, or completely de novo starting from random noise distributions without any subsequent experimental optimization. The RFdiffusion designs enable the enrichment and subsequent detection of parathyroid hormone and glucagon by mass spectrometry, and the construction of bioluminescence-based protein biosensors. The ability to design binders to conformationally variable targets, and to optimize by partial diffusion both natural and designed proteins, should be broadly useful.

U2 - 10.1038/s41586-023-06953-1

DO - 10.1038/s41586-023-06953-1

M3 - Journal article

C2 - 38109936

AN - SCOPUS:85183900079

VL - 626

SP - 435

EP - 442

JO - Nature Genetics

JF - Nature Genetics

SN - 1061-4036

IS - 7998

ER -