Protein Sequence Design with a Learned Potential

Anand, Namrata; Eguchi, Raphael R.; Mathews, Vikram; Cp, Perez; Derry, Alexander; Altman, Russ B.; Huang, P. G.

doi:10.1101/2020.01.06.895466

Cited by 32 publications

(49 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With recent advances in deep learning technology, machine learning tools have seen increasing applications in protein science, with deep neural networks being applied to tasks such as sequence design [11], fold recognition [12], binding site prediction [13], and structure prediction [14,15]. Generative models, which approximate the distributions of the data they are trained on, have garnered interest as a data-driven way to create novel proteins.…”

Section: Introductionmentioning

confidence: 99%

Ig-VAE: Generative Modeling of Protein Structure by Direct 3D Coordinate Generation

Eguchi¹,

Anand²,

Choe³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation -- an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model's generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model.

show abstract

Section: Introductionmentioning

confidence: 99%

Ig-VAE: Generative Modeling of Protein Structure by Direct 3D Coordinate Generation

Eguchi¹,

Anand²,

Choe³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There has been growing interest in using neural network-based approaches for protein representation learning and design (19,(37)(38)(39)(40), with several new methods reported during the preparation of this manuscript (41,42). While most methods are accompanied by a variety of metrics which attempt to illustrate the accuracy of the predictions, it is inherently difficult to evaluate the quality of generative models, as their ultimate goal is to generate entirely novel sequences with no existing counterparts.…”

Section: Resultsmentioning

confidence: 99%

Fast and flexible design of novel proteins using graph neural networks

Strokach¹,

Becerra

Corbi‐Verge

et al. 2019

Preprint

View full text Add to dashboard Cite

Protein structure and function is determined by the arrangement of the linear sequence of amino acids in 3D space. Despite substantial advances, precisely designing sequences that fold into a predetermined shape (the "protein design" problem) remains difficult. We show that a deep graph neural network, ProteinSolver, can solve protein design by phrasing it as a constraint satisfaction problem (CSP). To sidestep the considerable issue of optimizing the network architecture, we first develop a network that is accurately able to solve the related and straightforward problem of Sudoku puzzles. Recognizing that each protein design CSP has many solutions, we train this network on millions of real protein sequences corresponding to thousands of protein structures. We show that our method rapidly designs novel protein sequences and perform a variety of in silico and in vitro validations suggesting that our designed proteins adopt the predetermined structures.One Sentence Summary: A neural network optimized using Sudoku puzzles designs protein sequences that adopt predetermined structures.

show abstract

“…The generative approaches to de novo protein structure design so far described in the literature, rule- or model-based, either focus exclusively on helical structures ( 31 – 33 ), are not geared toward atomic-detail modeling and design ( 34 ), or sacrifice fine-grained structural control for structural diversity ( 35 ). Machine-learning–based generative models show considerable promise ( 35 , 36 ), but have not yet been applied to the direct generation of full atomic structures with specific features of interest, as we do here for scaffolds containing a varied geometry of binding pockets. We hope the experimental data generated in this work will aid the development of models that more efficiently produce protein structures with finer control over atomic detail and greater diversity.…”

Section: Discussionmentioning

confidence: 99%

An enumerative algorithm for de novo design of proteins with diverse pocket structures

Basanta

Bick

Bera

et al. 2020

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

To create new enzymes and biosensors from scratch, precise control over the structure of small-molecule binding sites is of paramount importance, but systematically designing arbitrary protein pocket shapes and sizes remains an outstanding challenge. Using the NTF2-like structural superfamily as a model system, we developed an enumerative algorithm for creating a virtually unlimited number of de novo proteins supporting diverse pocket structures. The enumerative algorithm was tested and refined through feedback from two rounds of large-scale experimental testing, involving in total the assembly of synthetic genes encoding 7,896 designs and assessment of their stability on yeast cell surface, detailed biophysical characterization of 64 designs, and crystal structures of 5 designs. The refined algorithm generates proteins that remain folded at high temperatures and exhibit more pocket diversity than naturally occurring NTF2-like proteins. We expect this approach to transform the design of small-molecule sensors and enzymes by enabling the creation of binding and active site geometries much more optimal for specific design challenges than is accessible by repurposing the limited number of naturally occurring NTF2-like proteins.

show abstract

Protein Sequence Design with a Learned Potential

Cited by 32 publications

References 100 publications

Ig-VAE: Generative Modeling of Protein Structure by Direct 3D Coordinate Generation

Ig-VAE: Generative Modeling of Protein Structure by Direct 3D Coordinate Generation

Fast and flexible design of novel proteins using graph neural networks

An enumerative algorithm for de novo design of proteins with diverse pocket structures

Contact Info

Product

Resources

About