Rapid and automated design of two-component protein nanomaterials using ProteinMPNN

Abstract

The design of novel protein-protein interfaces using physics-based design methods such as Rosetta requires substantial computational resources and manual refinement by expert structural biologists. A new generation of deep learning methods promises to simplify protein-protein interface design and enable its application to a wide variety of problems by researchers from various scientific disciplines. Here we test the ability of a deep learning method for protein sequence design, ProteinMPNN, to design two-component tetrahedral protein nanomaterials and benchmark its performance against Rosetta. ProteinMPNN had a similar success rate to Rosetta, yielding 13 new experimentally confirmed assemblies, but required orders of magnitude less computation and no manual refinement. The interfaces designed by ProteinMPNN were substantially more polar than those designed by Rosetta, which facilitated in vitro assembly of the designed nanomaterials from independently purified components. Crystal structures of several of the assemblies confirmed the accuracy of the design method at high resolution. Our results showcase the potential of deep learning-based methods to unlock the widespread application of designed protein-protein interfaces and self-assembling protein nanomaterials in biotechnology.

A Suite of Designed Protein Cages Using Machine Learning Algorithms and Protein Fragment-Based Protocols

“…Introducing complex, native-like, structural features by intentional design is a major computational challenge, and this is particularly true with regard to polar interactions such as hydrogen bonds, which rely on greater atomic precision than hydrophobic interactions. Our successful results, as well as contemporary reports 59 , indicate that machine learning methods are favorably suited for such complex tasks. Also notable for our design work was the allowance in machine learning for considerable backbone variation ( e .…”

Reengineering of a flavin‐binding fluorescent protein using ProteinMPNN

“…There, a more conservative cutoff of 7 Å for fixing the ligand‐proximal amino acids during reengineering was chosen, but given the larger size of myoglobin, resulting designs had 41%–55% sequence identity with the most similar protein in the UniRef100 database (Sumida et al, 2024). Several examples where protein‐ or peptide‐binding proteins (TEV protease, ubiquitin, ghrelin receptor) were reengineered using ProteinMPNN similarly display high success rates (de Haas et al, 2023; Goverde et al, 2023; Sumida et al, 2024). Finally, new methods called LigandMPNN and CARBonAra were recently described that explicitly model non‐protein components, but their codes are not yet readily available (Dauparas et al, 2023; Krapp et al, 2023; Krishna et al, 2023).…”

Designed fluorescent protein cages as fiducial markers for targeted cell imaging

“…To address these limitations, we have developed fluorescent designed protein cages that enable targeted imaging of proteins inside cells by acting as identifiable markers. Protein cages are hollow, nanoscale structures that can be designed to spontaneously self-assemble from multiple copies of modular protein subunits [11][12][13][14][15][16][17] . The resulting cage structures have well-defined sizes and shapes and can be engineered to encapsulate guest molecules, display functional proteins on their surfaces, and work as imaging scaffolds for cryo-electron microscopy (cryo-EM) [18][19][20][21][22][23][24][25][26] .…”