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

Jin, Wengong; Wohlwend, Jeremy; Barzilay, Regina; Jaakkola, Tommi S.

doi:10.48550/arxiv.2110.04624

Cited by 24 publications

(56 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the longer run, there are also many promising developments in BayesOpt methodology that are yet to be explored for sequence design, such as non-myopic acquisition functions (Jiang et al, 2020), multi-fidelity acquisition functions to determine the type of experimental assay and number of replications (Kandasamy et al, 2017;Wu et al, 2019), rigorous treatment of optimization constraints (Eriksson et al, 2019), and the coordination of many parallel drug development campaigns by optimizing risk measures across a whole compound portfolio (Cakmak et al, 2020). BayesOpt with multi-modal inputs is a particularly exciting direction, allowing scientists to combine many different sources of experimental data, including 3D structure and raw instrumental output (Jin et al, 2021). BayesOpt itself can also be developed for better adaptivity to misspecification, miscalibration, and distribution shift, all of which are important in drug design problems.…”

Section: Discussionmentioning

confidence: 99%

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Stanton¹,

Maddox²,

Gruver³

et al. 2022

Preprint

View full text Add to dashboard Cite

Bayesian optimization is a gold standard for query-efficient continuous optimization. However, its adoption for drug and antibody sequence design has been hindered by the discrete, highdimensional nature of the decision variables. We develop a new approach (LaMBO) which jointly trains a denoising autoencoder with a discriminative multi-task Gaussian process head, enabling gradient-based optimization of multi-objective acquisition functions in the latent space of the autoencoder. These acquisition functions allow LaMBO to balance the explore-exploit trade-off over multiple design rounds, and to balance objective tradeoffs by optimizing sequences at many different points on the Pareto frontier. We evaluate LaMBO on a small-molecule task based on the ZINC dataset and introduce a new large-molecule task targeting fluorescent proteins. In our experiments, LaMBO outperforms genetic optimizers and does not require a large pretraining corpus, demonstrating that Bayesian optimization is practical and effective for biological sequence design.

show abstract

Section: Discussionmentioning

confidence: 99%

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Stanton¹,

Maddox²,

Gruver³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, it is also relevant for de novo design of binding proteins (e.g. antibodies (Jin et al, 2021)) or for use cases when protein docking models are just a component of significantly larger end-to-end architectures targeting more involved biological scenarios, for example representing a drug's mechanism of action or modeling cellular processes with a single machine learning model as opposed to a multi-pipeline architecture.…”

Section: Methodsmentioning

confidence: 99%

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

Ganea¹,

Huang²,

Bunne³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Protein complex formation is a central problem in biology, being involved in most of the cell's processes, and essential for applications, e.g. drug design or protein engineering. We tackle rigid body protein-protein docking, i.e., computationally predicting the 3D structure of a protein-protein complex from the individual unbound structures, assuming no conformational change within the proteins happens during binding. We design a novel pairwise-independent SE(3)-equivariant graph matching network to predict the rotation and translation to place one of the proteins at the right docked position relative to the second protein. We mathematically guarantee a basic principle: the predicted complex is always identical regardless of the initial locations and orientations of the two structures. Our model, named EQUIDOCK, approximates the binding pockets and predicts the docking poses using keypoint matching and alignment, achieved through optimal transport and a differentiable Kabsch algorithm. Empirically, we achieve significant running time improvements and often outperform existing docking software despite not relying on heavy candidate sampling, structure refinement, or templates.

show abstract

“…(Ingraham et al, 2019;Koga et al, 2012;Cao et al, 2021) additionally includes the information of a backbone structure. Recently (Jin et al, 2021) proposed an iterative refinement approach to redesign the 3D structure and sequence of antibodies for improving properties such as neutralising score. The generative modelling paradigm can increase the efficient design of antibodies by prioritising the next candidates to be tested experimentally.…”

Section: Generative Models For Sampling New Antibody Candidatesmentioning

confidence: 99%

“…In this work, however, we use the three most relevant scores identified for CDRH3 region (Raybould et al, 2019;Jin et al, 2021)…”

Section: Cdrh3 Developability Constraintsmentioning

confidence: 99%

AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation

Khan¹,

Cowen-Rivers²,

Deik³

et al. 2022

Preprint

View full text Add to dashboard Cite

Antibodies are canonically Y-shaped multimeric proteins capable of highly specific molecular recognition. The CDRH3 region located at the tip of variable chains of an antibody dominates antigen-binding specificity. Therefore, it is a priority to design optimal antigen-specific CDRH3 regions to develop therapeutic antibodies to combat harmful pathogens. However, the combinatorial nature of CDRH3 sequence space makes it impossible to search for an optimal binding sequence exhaustively and efficiently, especially not experimentally. Here, we present AntBO: a Combinatorial Bayesian Optimisation framework enabling efficient in silico design of the CDRH3 region. Ideally, antibodies should bind to their target antigen and be free from any harmful outcomes. Therefore, we introduce the CDRH3 trust region that restricts the search to sequences with feasible developability scores. To benchmark AntBO, we use the Absolut! software suite as a black-box oracle because it can score the target specificity and affinity of designed antibodies in silico in an unconstrained fashion (Robert et al., 2021a). The results across 188 antigens demonstrate the benefit of AntBO in designing CDRH3 regions with diverse biophysical properties. In under 200 protein designs, AntBO can suggest antibody sequences that outperform the best binding sequence drawn from 6.9 million experimentally obtained CDRH3s and a commonly used genetic algorithm baseline. Additionally, AntBO finds very-high affinity CDRH3 sequences in only 38 * Equal contribution

show abstract

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

Cited by 24 publications

References 32 publications

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking

AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation

Contact Info

Product

Resources

About