Fast and Flexible Protein Design Using Deep Graph Neural Networks.

By Alexey Strokach, David Becerra, Carles Corbi-Verge, Albert Perez-Riba, Philip M. Kim. 2020

242 citations recorded by the source corpus.

Protein structure and function is determined by the arrangement of the linear sequence of amino acids in 3D space. We show that a deep graph neural network, ProteinSolver, can precisely design sequences that fold into a predetermined shape by phrasing this challenge as a constraint satisfaction problem (CSP), akin to Sudoku puzzles. We trained ProteinSolver on over 70,000,000 real protein sequences corresponding to over 80,000 structures. We show that our method rapidly designs new protein sequences and benchmark them in silico using energy-based scores, molecular dynamics, and structure prediction methods. As a proof-of-principle validation, we use ProteinSolver to generate sequences that match the structure of serum albumin, then synthesize the top-scoring design and validate it in vitro using circular dichroism. ProteinSolver is freely available at http://design.proteinsolver.org and https://gitlab.com/ostrokach/proteinsolver. A record of this paper's transparent peer review process is included in the Supplemental Information.

Subfields: Molecular Biology, Graph Learning, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Graph Learning

In Computational Biology & Bioinformatics

Citations in the corpus

Robust deep learning based protein sequence design using ProteinMPNN (2022, positive): “Recently deep learning approaches have shown considerable promise in rapidly generating plausible amino acid sequences given monomeric protein backbones without need for compute intensive explicit consideration of sidechain rotameric states (1-6).”
Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models (2022, background): “Machine learning has also made an impact on sequence design both in the case of conditioning on structural information [3, 21], and without [17, 9, 37, 38, 16, 18, 31, 20].”
De novo protein design by deep network hallucination (2020, background): “…backbones without consideration of sequence 6 , and to identify amino acid sequences that either fit well onto specified backbone structures 7–10 or are conditioned on low-dimensional fold representations 11 ; models tailored to generate sequences and/or structures for specific protein…”
ProGen: Language Modeling for Protein Generation (2020, methodology): “Recent generative modeling work [34, 22] has shown promising directions such as Ingraham et al.”
Learning inverse folding from millions of predicted structures (2022, methodology): “Recently a new class of deep learning based approaches has been proposed, using generative models to predict sequences for structures (Ingraham et al., 2019; Strokach et al., 2020; Anand-Achim et al., 2021; Jing et al., 2021b), generate backbone structures (Anand & Huang, 2018; Eguchi et al., 2020),”
Protein sequence design with a learned potential (2022, background): “4 because of the high redundancy (33) and high CC(1/2) value (82%).”
Learning from Protein Structure with Geometric Vector Perceptrons (2020, background): “These methods vary in their representation of geometry: while some, such as ProteinSolver and GraphQA, represent edges as a function of their length, others, such as Structured Transformer, indirectly encode the 3D geometry of the proximity graph in terms of relative orientations and other scalar fe”
Utilizing graph machine learning within drug discovery and development (2021, background): “[106] leveraged a deep GNN to tackle protein design as a constraint satisfaction problem.”
Using AlphaFold for Rapid and Accurate Fixed Backbone Protein Design (2021, background): “…variational autoencoders (Greener et al., 2018; Hawkins-Hooker et al., 2021), deep exploration networks (Linder et al., 2020), graph neural networks (Strokach et al., 2020), recurrent neural networks (Alley et al., 2019) and autoregressive models (Shin et al., 2021; Trinquier et al., 2021).”
Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures (2022, background): “Fix-backbone design is a common setting in the area of protein design [21, 20, 6, 46, 47].”
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB (2022, methodology): “Another related work is ProteinSolver (Strokach et al., 2020), but it was mainly developed for scenarios where partial sequences are known and does not report results on standard datasets.”
AlphaDesign: A de novo protein design framework based on AlphaFold (2021, background): “[68] have framed fixed-backbone design as a constraint satisfaction problem and have trained their network as a constraint solver.”
Recent advances in de novo protein design: Principles, methods, and applications (2021, background): “A number of generative models were developed for sequence design, including generative adversarial networks (104), variational autoencoders (105, 106), and graph-based (107, 108) models.”
Efficient generative modeling of protein sequences using simple autoregressive models (2021, methodology): “via a VAE [26] or a Graph Neural Network [51], or by inverting structural prediction models [4, 21, 37, 40].”
Protein Representation Learning by Geometric Structure Pretraining (2022, background): “…on learning representations of the protein structures, which then can be used for a variety of tasks such as protein design (Ingraham et al., 2019; Strokach et al., 2020; Cao et al., 2021; Jing et al., 2021), structure classiﬁcation (Hermosilla et al., 2021), model quality assessment (Baldassarre…”