Multistate and functional protein design using RoseTTAFold sequence space diffusion

Sidney Lyayuga Lisanza; Jacob Merle Gershon; Samuel W K Tipps; Jeremiah Nelson Sims; Lucas Arnoldt; Samuel J Hendel; Miriam K Simma; Ge Liu; Muna Yase; Hongwei Wu; Claire D Tharp; Xinting Li; Alex Kang; Evans Brackenbrough; Asim K Bera; Stacey Gerben; Bruce J Wittmann; Andrew C McShan; David Baker

doi:10.1038/s41587-024-02395-w

Multistate and functional protein design using RoseTTAFold sequence space diffusion

Nat Biotechnol. 2024 Sep 25. doi: 10.1038/s41587-024-02395-w. Online ahead of print.

Authors

Sidney Lyayuga Lisanza^#^{1

2

3}, Jacob Merle Gershon^#^{1

2

4}, Samuel W K Tipps^#^{1

2}, Jeremiah Nelson Sims^#^{2

5}, Lucas Arnoldt^#^{1

2

6}, Samuel J Hendel^{1

2}, Miriam K Simma⁷, Ge Liu^{1

2}, Muna Yase^{1

2

4}, Hongwei Wu⁷, Claire D Tharp⁷, Xinting Li^{1

2}, Alex Kang², Evans Brackenbrough², Asim K Bera², Stacey Gerben², Bruce J Wittmann⁸, Andrew C McShan⁷, David Baker^{9

10

11}

Affiliations

¹ Department of Biochemistry, University of Washington, Seattle, WA, USA.
² Institute for Protein Design, University of Washington, Seattle, WA, USA.
³ Graduate Program in Biological Physics, Structure and Design, University of Washington, Seattle, WA, USA.
⁴ Department of Molecular Engineering, University of Washington, Seattle, WA, USA.
⁵ Molecular & Cellular Biology, Medical Scientist Training Program, University of Washington, Seattle, WA, USA.
⁶ Faculty of Engineering Sciences, Heidelberg University, Heidelberg, Germany.
⁷ School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, GA, USA.
⁸ Office of the Chief Scientific Officer, Microsoft, Redmond, WA, USA.
⁹ Department of Biochemistry, University of Washington, Seattle, WA, USA. [email protected].
¹⁰ Institute for Protein Design, University of Washington, Seattle, WA, USA. [email protected].
¹¹ Howard Hughes Medical Institute, University of Washington, Seattle, WA, USA. [email protected].

^# Contributed equally.

PMID: 39322764
DOI: 10.1038/s41587-024-02395-w

Abstract

Protein denoising diffusion probabilistic models are used for the de novo generation of protein backbones but are limited in their ability to guide generation of proteins with sequence-specific attributes and functional properties. To overcome this limitation, we developed ProteinGenerator (PG), a sequence space diffusion model based on RoseTTAFold that simultaneously generates protein sequences and structures. Beginning from a noised sequence representation, PG generates sequence and structure pairs by iterative denoising, guided by desired sequence and structural protein attributes. We designed thermostable proteins with varying amino acid compositions and internal sequence repeats and cage bioactive peptides, such as melittin. By averaging sequence logits between diffusion trajectories with distinct structural constraints, we designed multistate parent-child protein triples in which the same sequence folds to different supersecondary structures when intact in the parent versus split into two child domains. PG design trajectories can be guided by experimental sequence-activity data, providing a general approach for integrated computational and experimental optimization of protein function.

Abstract

Grants and funding