research-article

Antibody Complementarity Determining Regions (CDRs) design using Constrained Energy Model

Authors:

Jimeng SunAuthors Info & Claims

KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Pages 389 - 399

https://doi.org/10.1145/3534678.3539285

Published: 14 August 2022 Publication History

Abstract

In recent years, therapeutic antibodies have become one of the fastest-growing classes of drugs and have been approved for the treatment of a wide range of indications, from cancer to autoimmune diseases. Complementarity-determining regions (CDRs) are part of the variable chains in antibodies and determine specific antibody-antigen binding. Some explorations use in silicon methods to design antibody CDR loops. However, the existing methods faced the challenges of maintaining the specific geometry shape of the CDR loops. This paper proposes a Constrained Energy Model (CEM) to address this issue. Specifically, we design a constrained manifold to characterize the geometry constraints of the CDR loops. Then we design the energy model in the constrained manifold and only depict the energy landscape of the manifold instead of the whole space in the vanilla energy model. The geometry shape of the generated CDR loops is automatically preserved. Theoretical analysis shows that learning on the constrained manifold requires less sample complexity than the unconstrained method. CEM's superiority is validated via thorough empirical studies, achieving consistent and significant improvement with up to 33.4% relative reduction in terms of 3D geometry error (Root Mean Square Deviation, RMSD) and 8.4% relative reduction in terms of amino acid sequence metric (perplexity) compared to the best baseline method. The code is publicly available at https://github.com/futianfan/energy_model4antibody_design

Supplemental Material

MP4 File

antibody design with energy model

Download
17.46 MB

References

[1]

Rahmad Akbar et al. 2021. In silico proof of principle of machine learning-based antibody design at unconstrained scale. BioRXiV (2021).

[2]

Jose Juan Almagro Armenteros et al. 2020. Language modelling for biological sequences--curated datasets and baselines. BioRxiv (2020).

[3]

Idan Attias, Aryeh Kontorovich, and Yishay Mansour. 2019. Improved generalization bounds for robust learning. In Algorithmic Learning Theory. PMLR.

[4]

Marcus Brubaker et al. 2012. A family of MCMC methods on implicitly defined manifolds. In AISTATS.

[5]

Yue Cao et al. 2021. Fold2Seq: A Joint Sequence (1D)-Fold (3D) Embedding-based Generative Model for Protein Design. In ICML.

[6]

Tong Che et al. 2020. Your GAN is secretly an energy-based model and you should use discriminator driven latent sampling. arXiv (2020).

[7]

Zak Costello et al. 2019. How to hallucinate functional proteins. arXiv (2019).

[8]

Chen Dan et al. 2018. The sample complexity of semi-supervised learning with nonparametric mixture models. NeurIPS (2018).

[9]

Yuanqi Du et al. 2022. MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design. arXiv preprint arXiv:2203.14500 (2022).

[10]

James Dunbar et al. 2014. SAbDab: the structural antibody database. Nucleic acids research (2014).

[11]

T Fu et al. 2020. CORE: Molecule Optimization using Copy and Refine. AAAI (2020).

[12]

T Fu et al. 2020. MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization. AAAI (2020).

[13]

T Fu et al. 2022. Differentiable Scaffolding Tree for Molecular Optimization. ICLR (2022).

[14]

WGao et al. 2020. Deep learning in protein modeling and design. Patterns (2020).

[15]

Monireh Golpour et al. 2021. The Perspective of Therapeutic Antibody Marketing in Iran: Trend and Estimation by 2025. Advances in pharma. sci. (2021).

[16]

Ian Goodfellow et al. 2020. Generative adversarial networks. (2020).

[17]

Fredrik Gustafsson et al. 2020. Energy-based models for deep probabilistic regression. In ECCV.

[18]

SQ Han et al. 2022. ADBench: Anomaly Detection Benchmark. arXiv (2022).

[19]

Kexin Huang et al. 2021. Therapeutics data Commons: machine learning datasets and tasks for therapeutics. NeurIPS Track Datasets and Benchmarks (2021).

[20]

John Ingraham et al. 2019. Generative Models for Graph-Based Protein Design. NeurIPS (2019).

[21]

Wengong Jin et al. 2022. Iterative refinement graph neural network for antibody sequence-structure co-design. ICLR (2022).

[22]

Wolfgang Kabsch. 1976. A solution for the best rotation to relate two sets of vectors. International Union of Crystallography (1976).

[23]

Mostafa Karimi et al. 2020. De novo protein design for novel folds using Wasserstein generative adversarial network. J. Chem. Info. & Model. (2020).

[24]

Diederik P Kingma et al. 2013. Auto-encoding variational bayes. arXiv (2013).

[25]

Chang Liu et al. 2016. Stochastic gradient geodesic mcmc methods. NeurIPS (2016).

[26]

Ge Liu et al. 2020. Antibody complementarity determining region design using high-capacity machine learning. Bioinformatics (2020).

[27]

Meng Liu et al. 2021. GraphEBM: Molecular graph generation with energy-based models. arXiv (2021).

[28]

Xiaofeng Liu et al. 2017. Computational design of an epitope-specific Keap1 binding antibody using hotspot residues grafting and CDR loop swapping. Sci. Rep. (2017).

[29]

Ruei-Min Lu et al. 2020. Development of therapeutic antibodies for the treatment of diseases. Journal of biomedical science (2020).

[30]

Shitong Luo et al. 2021. 3D Generative Model for Structure-Based Drug Design. NeurIPS (2021).

[31]

Robert M MacCallum et al. 1996. Antibody-antigen interactions: contact analysis and binding site topography. Journal of molecular biology (1996).

[32]

Hariharan Narayanan et al. 2009. Sample Complexity of Learning Smooth Cuts on a Manifold. In COLT.

[33]

Harini Narayanan et al. 2021. Machine learning for biologics: opportunities for protein engineering, developability, and formulation. Trends. Pharma. Sci. (2021).

[34]

Aaron Nelson et al. 2009. Development trends for therapeutic antibody fragments. Nature Bio. (2009).

[35]

Jaroslaw Nowak et al. 2016. Length-independent structural similarities enrich the antibody CDR canonical class model. In MAbs. Taylor & Francis.

[36]

RJ Pantazes et al. 2010. OptCDR: a general computational method for the design of antibody CDR for targeted epitope binding. Protein Engineering (2010).

[37]

Yifei Qi et al. 2020. DenseCPD: improving the accuracy of neural-network-based protein sequence design with DenseNet. J. chem. info. & model. (2020).

[38]

Prajit Ramachandran et al. 2017. Searching for activation functions. arXiv (2017).

[39]

Cristian Regep et al. 2017. The H3 loop of antibodies shows unique structural characteristics. Proteins: Structure, Function, and Bioinformatics (2017).

[40]

Donatas Repecka et al. 2021. Expanding functional protein sequence spaces using generative adversarial networks. Nature Machine Intelligence (2021).

[41]

D Rezende et al. 2015. Variational inference with normalizing flows. In ICML.

[42]

Koichiro Saka et al. 2021. Antibody design using LSTM based deep generative model from phage display library for affinity maturation. Scientific reports (2021).

[43]

Victor Satorras et al. 2021. E(n) equivariant graph neural networks. ICML (2021).

[44]

Victor Satorras et al. 2021. E(n) equivariant normalizing flows. arXiv (2021).

[45]

Inbal Sela-Culang, Vered Kunik, and Yanay Ofran. 2013. The structural basis of antibody-antigen recognition. Frontiers in immunology (2013).

[46]

Chence Shi et al. 2020. GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation. In ICLR.

[47]

Sam Sinai et al. 2017. Variational auto-encoding of protein sequences. NeurIPS Machine Learning in Computational Biology (MLCB) workshop (2017).

[48]

Robyn L Stanfield and Ian A Wilson. 2014. Antibody structure. Microbiology spectrum 2, 2 (2014), 2--2.

[49]

Alexey Strokach et al. 2020. Fast and flexible protein design using deep graph neural networks. Cell Systems (2020).

[50]

Vladimir Vapnik. 1999. The nature of statistical learning theory. Springer science.

Digital Library

[51]

Larry Wasserman. 2004. All of statistics: a concise course in statistical inference.

[52]

Max Welling and Yee W Teh. 2011. Bayesian learning via stochastic gradient Langevin dynamics. In ICML.

[53]

Jiaxuan You et al. 2018. Graphrnn: Generating realistic graphs with deep autoregressive models. In ICML.

[54]

Chengxi Zang et al. 2020. MoFlow: an invertible flow model for generating molecular graphs. In SIGKDD.

[55]

Yang Zhang. 2008. I-TASSER server for protein 3D structure prediction. BMC bioinformatics (2008).

[56]

Yuan Zhang et al. 2020. ProDCoNN: Protein design using a convolutional neural network. Proteins: Structure, Function, and Bioinformatics (2020).

[57]

Yue Zhao et al. 2021. Pyhealth: A python library for health predictive models. arXiv (2021).

Cited By

Lu YChen THao NVan Rechem CChen JFu T(2024)Uncertainty Quantification and Interpretability for Clinical Trial Approval PredictionHealth Data Science10.34133/hds.01264Online publication date: 15-Apr-2024
https://doi.org/10.34133/hds.0126
Melnyk IChenthamarakshan VChen PDas PDhurandhar APadhi IDas DKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Reprogramming pretrained language models for antibody sequence infillingProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619423(24398-24419)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619423
Gao KWu LZhu JPeng TXia YHe LXie SQin TLiu HHe KLiu TSingh ASun YAkoglu LGunopulos DYan XKumar ROzcan FYe J(2023)Pre-training Antibody Language Models for Antigen-Specific Computational Antibody DesignProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599468(506-517)Online publication date: 6-Aug-2023
https://dl.acm.org/doi/10.1145/3580305.3599468

Index Terms

Antibody Complementarity Determining Regions (CDRs) design using Constrained Energy Model
1. Computing methodologies
  1. Artificial intelligence
    1. Search methodologies
      1. Continuous space search

Recommendations

SIPF: Sampling Method for Inverse Protein Folding
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Protein engineering has important applications in drug discovery. Among others, inverse protein folding is a fundamental task in protein design, which aims at generating protein's amino acid sequence given a 3D graph structure. However, most existing ...
Roles of the respective loops at complementarity determining region on the antigen-antibody recognition

Display Omitted źThe direct hydrogen bond with the shortest distance is principally observed in the heavy chain.źTyr in the heavy chain (especially at H2 and H3) primarily contributes to the binding free energy.źThe appearances of Asn and Gln are large ...
Antibody complementarity-determining region design using AlphaFold2 and DDG predictor
Abstract
The constraints imposed by natural antibody affinity maturation often culminate in antibodies with suboptimal binding affinities, thereby limiting their therapeutic efficacy. As such, the augmentation of antibody binding affinity is pivotal for ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 2022

5033 pages

ISBN:9781450393850

DOI:10.1145/3534678

General Chairs:
Aidong Zhang
University of Virginia
,
Huzefa Rangwala
Amazon/George Mason University

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 August 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

NSF

Conference

KDD '22

Sponsor:

KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 14 - 18, 2022

Washington DC, USA

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Upcoming Conference

KDD '25

Sponsor:
sigkdd
sigkdd

The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining

August 3 - 7, 2025

Toronto , ON , Canada

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
639
Total Downloads

Downloads (Last 12 months)89
Downloads (Last 6 weeks)8

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Lu YChen THao NVan Rechem CChen JFu T(2024)Uncertainty Quantification and Interpretability for Clinical Trial Approval PredictionHealth Data Science10.34133/hds.01264Online publication date: 15-Apr-2024
https://doi.org/10.34133/hds.0126
Melnyk IChenthamarakshan VChen PDas PDhurandhar APadhi IDas DKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Reprogramming pretrained language models for antibody sequence infillingProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619423(24398-24419)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619423
Gao KWu LZhu JPeng TXia YHe LXie SQin TLiu HHe KLiu TSingh ASun YAkoglu LGunopulos DYan XKumar ROzcan FYe J(2023)Pre-training Antibody Language Models for Antigen-Specific Computational Antibody DesignProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599468(506-517)Online publication date: 6-Aug-2023
https://dl.acm.org/doi/10.1145/3580305.3599468

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten