• Corpus ID: 238583214

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design

@article{Jin2021IterativeRG,
  title={Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design},
  author={Wengong Jin and Jeremy Wohlwend and Regina Barzilay and T. Jaakkola},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.04624}
}
Antibodies are versatile proteins that bind to pathogens like viruses and stimulate the adaptive immune system. The specificity of antibody binding is determined by complementarity-determining regions (CDRs) at the tips of these Y-shaped proteins. In this paper, we propose a generative model to automatically design the CDRs of antibodies with enhanced binding specificity or neutralization capabilities. Previous generative approaches formulate protein design as a structure-conditioned sequence… 

Figures and Tables from this paper

Benchmarking deep generative models for diverse antibody sequence design
TLDR
Three recently proposed deep generative frameworks for protein design are considered: (AR) the sequence-based autoregressive generative model, (GVP) the precise structure-based graph neural network, and Fold2Seq that leverages a fuzzy and scale-free representation of a three-dimensional fold, while enforcing structure-to-sequence consistency.
A 3D Generative Model for Structure-Based Drug Design
We study a fundamental problem in structure-based drug design — generating molecules that bind to specific protein binding sites. While we have witnessed the great success of deep generative models
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
TLDR
A novel pairwise-independent SE(3)-equivariant graph matching network is designed to predict the rotation and translation to place one of the proteins at the right docked position relative to the second protein.

References

SHOWING 1-10 OF 50 REFERENCES
Antibody Complementarity Determining Region Design Using High-Capacity Machine Learning
TLDR
A machine learning method is presented that can design human Immunoglobulin G (IgG) antibodies with target affinities that are superior to candidates from phage display panning experiments within a limited design budget and shows that data from disparate antibody campaigns can be combined by machine learning to improve antibody specificity.
Fast and flexible design of novel proteins using graph neural networks
TLDR
A deep graph neural network, ProteinSolver, can solve protein design by phrasing it as a constraint satisfaction problem (CSP), and develops a network that is accurately able to solve the related and straightforward problem of Sudoku puzzles.
Protein Design and Variant Prediction Using Autoregressive Generative Models
TLDR
This work introduces a deep generative model adapted from natural language processing for prediction and design of diverse functional sequences without the need for alignments and successfully design and test a diverse 105-nanobody library that shows better expression than a 1000-fold larger synthetic library.
Antibody design using LSTM based deep generative model from phage display library for affinity maturation
TLDR
A long short term memory network—a widely used deep generative model—based sequence generation and prioritization procedure to efficiently discover antibody sequences with higher affinity is employed to affinity maturation of antibodies against kynurenine.
In silico proof of principle of machine learning-based antibody design at unconstrained scale
TLDR
This work establishes a priori feasibility and the theoretical foundation of high-throughput ML-based mAb design and shows increased generation quality of low-N-based machine learning models via transfer learning.
RosettaAntibodyDesign (RAbD): A general framework for computational antibody design
TLDR
This work rigorously benchmarked RAbD on a set of 60 diverse antibody–antigen complexes, using two design strategies—optimizing total Rosetta energy and optimizing interface energy alone and utilized two novel metrics for measuring success in computational protein design.
Accurate prediction of protein structures and interactions using a 3-track neural network
TLDR
A three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure.
Design of proteins presenting discontinuous functional sites using deep learning
TLDR
This work uses the trRosetta residual neural network, which maps input sequences to predicted inter-residue distances and orientations, to compute a loss function which simultaneously rewards recapitulation of a desired structural motif and the ideality of the surrounding scaffold, and generates diverse structures harboring the desired binding interface by optimizing this loss function by gradient descent.
Unified rational protein engineering with sequence-based deep representation learning
TLDR
Deep learning is applied to unlabeled amino-acid sequences to distill the fundamental features of a protein into a statistical representation that is semantically rich and structurally, evolutionarily and biophysically grounded and broadly applicable to unseen regions of sequence space.
OptCDR: a general computational method for the design of antibody complementarity determining regions for targeted epitope binding.
TLDR
The results demonstrate that OptCDR can efficiently generate diverse antibody libraries of a pre-specified size with promising antigen affinity potential as exemplified by computationally derived binding metrics.
...
1
2
3
4
5
...