Robust deep learning based protein sequence design using ProteinMPNN

Dauparas, Justas; Anishchenko, Ivan; Bennett, Nathaniel R.; Bai, Hua; Ragotte, Robert J.; Milles, Lukas F.; Wicky, Basile I. M.; Courbet, Alexis; Haas, Robbert J. de; Bethel, Neville; Leung, Philip J. Y.; Huddy, Timothy F.; Pellock, S.J.; Tischer, Doug; Chan, Frederick; Koepnick, Brian; Nguyen, Hannah; Kang, Alex; Sankaran, Banumathi; Bera, Asim K.; King, Neil P.; Baker, David

doi:10.1101/2022.06.03.494563

Cited by 63 publications

(127 citation statements)

References 28 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…However, this representation is coarse-grained and ignores additional backbone atomic coordinates, namely the backbone carbon and nitrogen atoms. Dauparas et al [8] observed additionally modeling the heavy atoms of the backbone nitrogen and carbon atoms along with the C-β of every residue (to capture side-chain information) improved performance (by sequence recovery) for fixed-backbone sequence design. We hypothesize modeling additional coordinates of every residue would also improve designability performance of ProtDiff.…”

Section: Discussionmentioning

confidence: 99%

“…Our evaluation with AF2 is as follows. For each generated scaffold we use a C-α only version of ProteinMPNN [8] with a temperature of 0.1 to sample 8 amino acid sequences likely to fold to the same backbone structure. We then run AF2 with the released CASP14 1 weights and 15 recycling iterations.…”

Section: In Silico Evaluation Of Designed Backbonesmentioning

confidence: 99%

“…Another class of methods, referred to as fixed backbone sequence design [12,20,40,27,18], attempts to solve the problem of identifying a sequence that folds into any given designable backbone structure. In the present work, we utilize a particular sequence design method, ProteinMPNN [8], but in principle any other fixed-backbone sequence design method could be used in its place. [1,25,39] propose generative adversarial networks, variational autoencoders, and energy-based models, respectively, on distance matrices, but these approaches (1) do not generate backbones compatible with a specified motif and (2) rely on an unwieldy optimization step to translate the distance matrix into backbone coordinates.…”

Section: Appendix Table Of Contentsmentioning

confidence: 99%

“…Next, we run SMCDiff, our conditional sampling algorithm, with ProtDiff to generate scaffolds (colored in red) conditioned on the motif (colored in blue). For selfconsistency evaluation, we use a pretrained fixed-backbone sequence-design model (ProteinMPNN [8]) to generate the scaffold sequence from a sampled backbone. We then input the sequence to a structure prediction model, in our case AlphaFold2 (AF2) [22], to generate the full protein structure from the generated sequence.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

Trippe¹,

Yim²,

Tischer³

et al. 2022

Preprint

View full text Add to dashboard Cite

Construction of a scaffold structure that supports a desired motif, conferring protein function, shows promise for the design of vaccines and enzymes. But a general solution to this motif-scaffolding problem remains open. Current machine-learning techniques for scaffold design are either limited to unrealistically small scaffolds (up to length 20) or struggle to produce multiple diverse scaffolds. We propose to learn a distribution over diverse and longer protein backbone structures via an E(3)equivariant graph neural network. We develop SMCDiff to efficiently sample scaffolds from this distribution conditioned on a given motif; our algorithm is the first to theoretically guarantee conditional samples from a diffusion model in the largecompute limit. We evaluate our designed backbones by how well they align with AlphaFold2-predicted structures. We show that our method can (1) sample scaffolds up to 80 residues and (2) achieve structurally diverse scaffolds for a fixed motif.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: In Silico Evaluation Of Designed Backbonesmentioning

confidence: 99%

Section: Appendix Table Of Contentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

Trippe¹,

Yim²,

Tischer³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We investigated whether the recently developed deep learning based sequence design method ProteinMPNN 12 could be used to increase the efficiency of the design pipeline. ProteinMPNN is very fast, generating a sequence for a minibinder backbone in ~2 CPU-s compared to ~350 CPU-s for Rosetta-design.…”

Section: Prospective Analysismentioning

confidence: 99%

Improving de novo Protein Binder Design with Deep Learning

Bennett

Coventry

Goreshnik

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We explore the improvement of energy-based protein binder design using deep learning. We find that using AlphaFold2 or RoseTTAFold to assess the probability that a designed sequence adopts the designed monomer structure, and the probability that this structure binds the target as designed, increases design success rates nearly 10-fold. We find further that sequence design using ProteinMPNN rather than Rosetta considerably increases computational efficiency.

show abstract

Neural network‐derived Potts models for structure‐based protein design using backbone atomic coordinates and tertiary motifs

Desta

et al. 2023

Protein Science

View full text Add to dashboard Cite

Designing novel proteins to perform desired functions, such as binding or catalysis, is a major goal in synthetic biology. A variety of computational approaches can aid in this task. An energy‐based framework rooted in the sequence‐structure statistics of tertiary motifs (TERMs) can be used for sequence design on predefined backbones. Neural network models that use backbone coordinate‐derived features provide another way to design new proteins. In this work, we combine the two methods to make neural structure‐based models more suitable for protein design. Specifically, we supplement backbone‐coordinate features with TERM‐derived data, as inputs, and we generate energy functions as outputs. We present two architectures that generate Potts models over the sequence space: TERMinator, which uses both TERM‐based and coordinate‐based information, and COORDinator, which uses only coordinate‐based information. Using these two models, we demonstrate that TERMs can be utilized to improve native sequence recovery performance of neural models. Furthermore, we demonstrate that sequences designed by TERMinator are predicted to fold to their target structures by AlphaFold. Finally, we show that both TERMinator and COORDinator learn notions of energetics, and these methods can be fine‐tuned on experimental data to improve predictions. Our results suggest that using TERM‐based and coordinate‐based features together may be beneficial for protein design and that structure‐based neural models that produce Potts energy tables have utility for flexible applications in protein science.

show abstract

Robust deep learning based protein sequence design using ProteinMPNN

Cited by 63 publications

References 28 publications

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

Improving de novo Protein Binder Design with Deep Learning

Neural network‐derived Potts models for structure‐based protein design using backbone atomic coordinates and tertiary motifs

Contact Info

Product

Resources

About