Computational and artificial intelligence-based methods for antibody development

Trends in Pharmacological Sciences, Год журнала: 2023, Номер 44(3), С. 175 - 189

Опубликована: Янв. 18, 2023

Due to their high target specificity and binding affinity, therapeutic antibodies are currently the largest class of biotherapeutics. The traditional largely empirical antibody development process is, while mature robust, cumbersome has significant limitations. Substantial recent advances in computational artificial intelligence (AI) technologies now starting overcome many these limitations increasingly integrated into pipelines. Here, we provide an overview AI methods relevant for development, including databases, predictors properties structure, design with emphasis on machine learning (ML) models, complementarity-determining region (CDR) loops, structural components critical binding.

Язык: Английский

---

Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens

Journal of Chemical Theory and Computation, Год журнала: 2023, Номер 19(16), С. 5315 - 5333

Опубликована: Авг. 1, 2023

The design of new biomolecules able to harness immune mechanisms for the treatment diseases is a prime challenge computational and simulative approaches. For instance, in recent years, antibodies have emerged as an important class therapeutics against spectrum pathologies. In cancer, immune-inspired approaches are witnessing surge thanks better understanding tumor-associated antigens their engagement or evasion from human system. Here, we provide summary main state-of-the-art that used antigens, parallel, review key methodologies epitope identification both B- T-cell mediated responses. A special focus devoted description structure- physics-based models, privileged over purely sequence-based We discuss implications novel methods engineering with tailored immunological properties possible therapeutic uses. Finally, highlight extraordinary challenges opportunities presented by integration emerging Artificial Intelligence technologies prediction epitopes, antibodies.

Язык: Английский

---

Approaches to expand the conventional toolbox for discovery and selection of antibodies with drug-like physicochemical properties

mAbs, Год журнала: 2023, Номер 15(1)

Опубликована: Янв. 11, 2023

Antibody drugs should exhibit not only high-binding affinity for their target antigens but also favorable physicochemical drug-like properties. Such biophysical properties are essential the successful development of antibody drug products. The traditional approaches used in require significant experimentation to produce, optimize, and characterize many candidates. Therefore, it is attractive integrate new methods that can optimize process selecting antibodies with both desired target-binding Here, we summarize a selection techniques complement conventional toolbox de-risk development. These be integrated at different stages reduce frequency liabilities libraries during initial discovery co-optimize multiple features early-stage engineering maturation. Moreover, highlight computational predict physical degradation pathways relevant long-term storage in-use stability need extensive experimentation.

Язык: Английский

---

Rationally seeded computational protein design of ɑ-helical barrels

Nature Chemical Biology, Год журнала: 2024, Номер 20(8), С. 991 - 999

Опубликована: Июнь 20, 2024

Abstract Computational protein design is advancing rapidly. Here we describe efficient routes starting from validated parallel and antiparallel peptide assemblies to two families of α-helical barrel proteins with central channels that bind small molecules. designs are seeded by the sequences structures defined de novo oligomeric barrel-forming peptides, adjacent helices connected loop building. For targets helices, short loops sufficient. However, require longer connectors; namely, an outer layer helix–turn–helix–turn–helix motifs packed onto barrels. Throughout these computational pipelines, residues define open states barrels maintained. This minimizes sequence sampling, accelerating process. each six targets, just synthetic genes made for expression in Escherichia coli . On average, 70% express give soluble monomeric fully characterized, including high-resolution most match models high accuracy.

Язык: Английский

---

Affinity maturation of antibody fragments: A review encompassing the development from random approaches to computational rational optimization

International Journal of Biological Macromolecules, Год журнала: 2023, Номер 247, С. 125733 - 125733

Опубликована: Июль 7, 2023

Routinely screened antibody fragments usually require further in vitro maturation to achieve the desired biophysical properties. Blind strategies can produce improved ligands by introducing random mutations into original sequences and selecting resulting clones under more stringent conditions. Rational approaches exploit an alternative perspective that aims first at identifying specific residues potentially involved control of mechanisms, such as affinity or stability, then evaluate what could improve those characteristics. The understanding antigen-antibody interactions is instrumental develop this process reliability which, consequently, strongly depends on quality completeness structural information. Recently, methods based deep learning critically speed accuracy model building are promising tools for accelerating docking step. Here, we review features available bioinformatic instruments analyze reports illustrating result obtained with their application optimize fragments, nanobodies particular. Finally, emerging trends open questions summarized.

Язык: Английский

---

How can we discover developable antibody-based biotherapeutics?

Frontiers in Molecular Biosciences, Год журнала: 2023, Номер 10

Опубликована: Авг. 7, 2023

Antibody-based biotherapeutics have emerged as a successful class of pharmaceuticals despite significant challenges and risks to their discovery development. This review discusses the most frequently encountered hurdles in research development (R&D) antibody-based proposes conceptual framework called biopharmaceutical informatics. Our vision advocates for syncretic use computation experimentation at every stage biologic drug discovery, considering developability (manufacturability, safety, efficacy, pharmacology) potential candidates from earliest stages phase. The computational advances recent years allow more precise formulation disease concepts, rapid identification, validation targets suitable therapeutic intervention that can agonize or antagonize them. Furthermore, methods

Язык: Английский

---

Applying artificial intelligence to accelerate and de-risk antibody discovery

Frontiers in Drug Discovery, Год журнала: 2024, Номер 4

Опубликована: Март 5, 2024

As in all sectors of science and industry, artificial intelligence (AI) is meant to have a high impact the discovery antibodies coming years. Antibody was traditionally conducted through succession experimental steps: animal immunization, screening relevant clones, vitro testing, affinity maturation, vivo testing models, then different steps humanization maturation generating candidate that will be tested clinical trials. This scheme suffers from flaws, rendering whole process very risky, with an attrition rate over 95%. The rise silico methods, among which AI, has been gradually proven reliably guide more robust processes. They are now capable covering process. Amongst players this new field, company MAbSilico proposes pipeline allowing design antibody sequences few days, already humanized optimized for developability, considerably de-risking accelerating

Язык: Английский

---

Structural modeling of antibody variable regions using deep learning—progress and perspectives on drug discovery

Frontiers in Molecular Biosciences, Год журнала: 2023, Номер 10

Опубликована: Июль 7, 2023

AlphaFold2 has hallmarked a generational improvement in protein structure prediction. In particular, advances antibody prediction have provided highly translatable impact on drug discovery. Though laid the groundwork for all proteins, antibody-specific applications require adjustments tailored to these molecules, which resulted handful of deep learning predictors. Herein, we review recent and relate them their role advancing biologics

Язык: Английский

---

Nanobody engineering: computational modelling and design for biomedical and therapeutic applications

FEBS Open Bio, Год журнала: 2024, Номер 15(2), С. 236 - 253

Опубликована: Июнь 19, 2024

Nanobodies, the smallest functional antibody fragment derived from camelid heavy-chain-only antibodies, have emerged as powerful tools for diverse biomedical applications. In this comprehensive review, we discuss structural characteristics, properties, and computational approaches driving design optimisation of synthetic nanobodies. We explore their unique antigen-binding domains, highlighting critical role complementarity-determining regions in target recognition specificity. This review further underscores advantages nanobodies over conventional antibodies a biosynthesis perspective, including small size, stability, solubility, which make them ideal candidates economical antigen capture diagnostics, therapeutics, biosensing. recent advancements methods nanobody modelling, epitope prediction, affinity maturation, shedding light on intricate mechanisms conformational dynamics. Finally, examine direct example how strategies were implemented improving nanobody-based immunosensor, known Quenchbody. Through combining experimental findings insights, elucidates transformative impact biotechnology research, offering roadmap future applications healthcare diagnostics.

Язык: Английский

---

Computational protein design

Nature Reviews Methods Primers, Год журнала: 2025, Номер 5(1)

Опубликована: Фев. 27, 2025

---