Fast and flexible design of novel proteins using graph neural networks

By Alexey Strokach, David Becerra, Carles Corbi-Verge, Albert Perez-Riba, Philip M. Kim. 2019

17 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. 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.

Subfields: Cellular and Molecular Neuroscience, Electrical and Electronic Engineering, Molecular Biology

How researchers see this paper

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

In Cellular and Molecular Neuroscience

Kevin Kaichuang Yang

In Electrical and Electronic Engineering

In Molecular Biology

Citations in the corpus

Learning from Protein Structure with Geometric Vector Perceptrons (2020, neutral): “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”
Protein sequence design with a learned potential (2020, unknown): “Other deep learning approaches have been developed for sequence design or rotamer packing [ 90, 91, 92, 93, 94, 95], but most of these methods’ designs have not been comprehensively validated by a range of biochemical metrics or by folding in silico or in vitro .”
Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts (2020, background): “Besides drug repurposing, many have been devoted to drug discovery [89], [91]–[93] and protein structure prediction [94]–[96] for combating against the COVID-19 pandemic.”
Deep Learning in Protein Structural Modeling and Design (2020, background): “They were able to validate designed sequences in silico and demonstrate that some designs folded to their target structures in vitro.(213) An ambitious design goal is to generate new structureswithout specifying the target structure.”
Masked Inverse Folding with Sequence Transfer for Protein Representation Learning (2023, background): “Deep learning-based inverse folding is usually parametrized as a graph neural network (GNN) (Ingra-ham et al., 2019; Strokach et al., 2020; Jin et al., 2021; Jing et al., 2020; Hsu et al., 2022; Dauparas et al., 2022; Shi et al., 2022) or SE(3)-equivariant transformer (McPartlon et al., 2022) that…”