Hallucinating symmetric protein assemblies

Abstract

Deep learning generative approaches provide an opportunity to broadly explore protein structure space beyond the sequences and structures of natural proteins. Here we use deep network hallucination to generate a wide range of symmetric protein homo-oligomers given only a specification of the number of protomers and the protomer length. Crystal structures of 7 designs are very close to the computational models (median RMSD: 0.6 Å), as are 3 cryoEM structures of giant 10 nanometer rings with up to 1550 residues and C33 symmetry; all differ considerably from previously solved structures. Our results highlight the rich diversity of new protein structures that can be generated using deep learning, and pave the way for the design of increasingly complex components for nanomachines and biomaterials.

Robust deep learning–based protein sequence design using ProteinMPNN

“…3D). Crystal structures and cryo-EM structures of 10 cyclic homo-oligomers with 130 to 1800 amino acids were also very close to the design target backbones ( 15 ). Thus, ProteinMPNN can robustly and accurately design sequences for both monomers and cyclic oligomers.…”

“…The high rate of experimental design success of ProteinMPNN, together with the compute efficiency, applicability to almost any protein sequence design problem, and lack of requirement for customization, should make it very broadly useful for protein design. ProteinMPNN-generated sequences also have a much higher propensity to crystallize, greatly facilitating structure determination of designed proteins ( 15 ). The observation that ProteinMPNN-generated sequences are predicted to fold to native protein backbones more confidently and accurately than the original native sequences (using single-sequence information in both cases) suggests that ProteinMPNN may also be widely useful in improving expression and stability of recombinantly expressed native proteins (with residues required for function kept fixed).…”

“…We first tested the ability of ProteinMPNN to design amino acid sequences for protein backbones generated by deep network hallucination using AlphaFold. Starting from a random sequence, a Monte Carlo trajectory is carried out to optimize the extent to which AlphaFold predicts the sequence to fold to a well-defined structure ( 15 ). These calculations generated a wide range of protein sequences and backbones for both monomers and oligomers that differ considerably from those of native structures.…”

Building blocks of non-Euclidean ribbons: Size-controlled self-assembly via discrete, frustrated particles

“…[27][28][29] In principle, recent progress in the synthesis of colloidal-scale particles with programmed shape can allow for tunable shape frustration that can more fully test the continuum theory description of size control. [30,31] Notably, advances in DNA nanotechnology [32,33] as well as synthetic protein engineering [34][35][36][37] allow for both careful design and control of the shape frustration of self-assembling nanoscale units as well as new opportunities for programming the interactions to separately tune the strength of cohesion and costs associated with distinct modes of assembly deformation. However, due to the primary reliance on continuum descriptions of GFA, several basic challenges remain to relate emergent thermodynamic behaviors in a particular system of selfassembling frustrated subunits.…”

Scientists are using AI to dream up revolutionary new proteins

“…The vaccine is based on a spherical protein 'nanoparticle' that was created by researchers nearly a decade ago, through a labour-intensive trial-anderror-process 1 . Now, thanks to gargantuan advances in artificial intelligence (AI), a team led by David Baker, a biochemist at the University of Washington in Seattle, reports in Science 2,3 that it can design such molecules in seconds instead of months.…”