In silico proof of principle of machine learning-based antibody design at unconstrained scale

Akbar, Rahmad; Robert, Philippe A.; Weber, Cédric R.; Widrich, Michael; Frank, Robert; Pavlović, Milena; Scheffer, Lonneke; Chernigovskaya, Maria; Snapkov, Igor; Slabodkin, Andrei; Mehta, Brij Bhushan; Miho, Enkelejda; Lund-Johansen, Fridtjof; Andersen, Jan Terje; Hochreiter, Sepp; Haff, Ingrid Hobæk; Klambauer, Günter; Sandve, Geir Kjetil; Greiff, Victor

doi:10.1080/19420862.2022.2031482

Cited by 66 publications

(64 citation statements)

References 75 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The VAE [ 53 ], introduced by Friedensohn, was better at identifying convergent sequences than clonotyping by grouping antigen-specific sequences across multiple features. However, further investigations on ground truth data are needed for an unbiased ranking of ML-based antibody bioinformatics approaches [ 13 , 54 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Wilman¹,

Wróbel²,

Bielska³

et al. 2022

Briefings in Bioinformatics

Self Cite

View full text Add to dashboard Cite

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

show abstract

Section: Discussionmentioning

confidence: 99%

“…To address the issue of ‘learnability’ of the Ab-Ag recognition, Akbar et al. tested this concept in silico by simulated Ab–Ag binding data [ 54 ]. They trained the LSTM-RNN on CDRH3 that were apriori computationally associated with developability data [ 13 ].…”

Section: Embedding the Ab-ag Space: Prediction Of Antibody–antigen Bi...mentioning

confidence: 99%

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Wilman¹,

Wróbel²,

Bielska³

et al. 2022

Briefings in Bioinformatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…More specifically, 1D sequential data of 70,000,000 structures (higher amount of data by three orders of magnitude compared to SoA were used to feed the transfer learning model which reflects proper biological complexity in order to design the conformational (3D) epitope-specific antibodies, while the deep learning computer mAb design at high-throughput was validated by experiments for its ability to accelerate antibody discovery. A key functionality of in silico generative frameworks was that since training is completed, the model can be utilized as on-demand as a large-scale tool for the development of virtual representations of antigen-specific and immune receptor sequences [ 128 ].…”

Section: Selection Of Nanomaterials Tailored For Improvements In Qual...mentioning

confidence: 99%

Digital Innovation Enabled Nanomaterial Manufacturing; Machine Learning Strategies and Green Perspectives

Konstantopoulos

Koumoulos²,

Charitidis

2022

Nanomaterials

View full text Add to dashboard Cite

Machine learning has been an emerging scientific field serving the modern multidisciplinary needs in the Materials Science and Manufacturing sector. The taxonomy and mapping of nanomaterial properties based on data analytics is going to ensure safe and green manufacturing with consciousness raised on effective resource management. The utilization of predictive modelling tools empowered with artificial intelligence (AI) has proposed novel paths in materials discovery and optimization, while it can further stimulate the cutting-edge and data-driven design of a tailored behavioral profile of nanomaterials to serve the special needs of application environments. The previous knowledge of the physics and mathematical representation of material behaviors, as well as the utilization of already generated testing data, received specific attention by scientists. However, the exploration of available information is not always manageable, and machine intelligence can efficiently (computational resources, time) meet this challenge via high-throughput multidimensional search exploration capabilities. Moreover, the modelling of bio-chemical interactions with the environment and living organisms has been demonstrated to connect chemical structure with acute or tolerable effects upon exposure. Thus, in this review, a summary of recent computational developments is provided with the aim to cover excelling research and present challenges towards unbiased, decentralized, and data-driven decision-making, in relation to increased impact in the field of advanced nanomaterials manufacturing and nanoinformatics, and to indicate the steps required to realize rapid, safe, and circular-by-design nanomaterials.

show abstract

“…Recently, various deep generative models are developed to design both sequences and structures of antibodies [41, 3, 23]. In comparison to conventional algorithms, deep generative models could capture higher order interactions among amino acids on antibodies and antigens directly from data [2].…”

Section: Introductionmentioning

confidence: 99%

“…(b) The orientations of amino acids (represented by triangles) determine their side-chain orientations, which are key to inter-aminoacid interactions. (c) The task in this work is to design CDRs for a given antigen structure and an antibody framework.Recently, various deep generative models are developed to design both sequences and structures of antibodies[41,3,23]. In comparison to conventional algorithms, deep generative models could capture higher order interactions among amino acids on antibodies and antigens directly from data[2].…”

mentioning

confidence: 99%

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Luo

Peng

et al. 2022

Preprint

123

View full text Add to dashboard Cite

Antibodies are immune system proteins that protect the host by binding to specific antigens such as viruses and bacteria. The binding between antibodies and antigens are mainly determined by the complementarity-determining regions (CDR) on the antibodies. In this work, we develop a deep generative model that jointly models sequences and structures of CDRs based on diffusion processes and equivariant neural networks. Our method is the first deep learning-based method that can explicitly target specific antigen structures and generate antibodies at atomic resolution. The model is a ''Swiss Army Knife'' which is capable of sequence-structure co-design, sequence design for given backbone structures, and antibody optimization. For antibody optimization, we propose a special sampling scheme that first perturbs the given antibody and then denoises it. As the number of available antibody structures is relatively scarce, we curate a new dataset that contains antibody-like proteins as a complement to the original antibody dataset for training. We conduct extensive experiments to evaluate the quality of both sequences and structures of designed antibodies. We find that our model could yield highly competitive results in terms of binding affinity measured by biophysical energy functions and other protein design metrics.

show abstract

In silico proof of principle of machine learning-based antibody design at unconstrained scale

Cited by 66 publications

References 75 publications

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Digital Innovation Enabled Nanomaterial Manufacturing; Machine Learning Strategies and Green Perspectives

Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein Structures

Contact Info

Product

Resources

About