The Application of Machine Learning on Antibody Discovery and Optimization DOI Creative Commons

Jiayao Zheng,

Yu Wang, Liang Qin

et al.

Molecules, Journal Year: 2024, Volume and Issue: 29(24), P. 5923 - 5923

Published: Dec. 16, 2024

Antibodies play critical roles in modern medicine, serving as diagnostics and therapeutics for various diseases due to their ability specifically bind target antigens. Traditional antibody discovery optimization methods are time-consuming resource-intensive, though they have successfully generated antibodies diagnosing treating diseases. The advancements protein data, computational hardware, machine learning (ML) models the opportunity disrupt research. Machine demonstrated abilities design. These enable rapid silico design of candidates within a few days, achieving approximately 60% reduction time 50% cost compared traditional methods. This review focuses on latest learning-based developments. We briefly discuss limitations then explore methodologies. also focus future research directions, including developing Antibody Design AI Agents data foundries, alongside ethical regulatory considerations essential adopting learning-driven designs.

Language: Английский

Next-Generation Therapeutic Antibodies for Cancer Treatment: Advancements, Applications, and Challenges DOI
A. Raja,

Abhishek Kasana,

Vaishali Verma

et al.

Molecular Biotechnology, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 2, 2024

Language: Английский

Citations

5
DyAb: sequence-based antibody design and property prediction in a low-data regime DOI Creative Commons
Joshua Lin, Jennifer L. Hofmann, Andrew Leaver‐Fay

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 2, 2025

ABSTRACT Protein therapeutic design and property prediction are frequently hampered by data scarcity. Here we propose a new model, DyAb, that addresses these issues leveraging pair-wise representation to predict differences in protein properties, rather than absolute values. DyAb is built on top of pre-trained language model achieves Spearman rank correlation up 0.85 binding affinity across molecules targeting three different antigens (EGFR, IL-6, an internal target), given as few 100 training data. We employ two contexts: ranking score combinations known mutations, combined with genetic algorithm generate sequences. Our method consistently generates novel antibody candidates high rates, including designs improve the lead molecule more ten-fold. represents powerful tool for engineering properties low regimes common early-stage drug development.

Language: Английский

Citations

0
How to think about designing smart antibodies in the age of genAI: integrating biology, technology, and experience DOI Creative Commons
Andrew Buchanan, Eric M. Bennett,

Rebecca Croasdale-Wood

et al.

mAbs, Journal Year: 2025, Volume and Issue: 17(1)

Published: April 10, 2025

Antibody discovery has been successful in designing and progressing molecules to the clinic market based on largely empirical methods human experience. The field is now transitioning from classical monospecific antibodies innovative smart biologics that employ diverse mechanisms of action, such as targeting, antagonism, agonism, target-independent function. This evolution being assisted, augmented, potentially disrupted by artificial intelligence machine learning (AI/ML) technologies. perspective focused bringing clarity strategy thinking required when antibody drug candidates how emerging AI/ML strategies can address real-world challenges continue improve performance.

Language: Английский

Citations

0
Machine Learning for Predicting the Drug-to-Antibody Ratio (DAR) in the Synthesis of Antibody–Drug Conjugates (ADCs) DOI
Luca Angiolini, Fabrizio Manetti, Ottavia Spiga

et al.

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

The pharmaceutical industry faces challenges in developing efficient and cost-effective drug delivery systems. Among various applications, antibody-drug conjugates (ADCs) stand out by combining cytotoxic or bioactive agents with monoclonal antibodies (mAbs) for targeted therapies. However, bioconjugation methods can produce different outcomes, including no bioconjugation, depending on the mAb, amino acid residues, linker-payload (LP) system used. In this work, we developed a machine learning (ML) algorithm capable of predicting allowing design best LP systems, conditions development ADCs. particular, exploited potential XGBoost drug-to-antibody ratio (DAR) synthesis Our model demonstrated high predictive accuracy, R2 scores 0.85 0.95 lysine cysteine data sets, respectively. integration ML algorithms into processes ADC offers promising approach to streamlining development.

Language: Английский

Citations

0
AIntibody: an experimentally validated in silico antibody discovery design challenge DOI Creative Commons
M. Frank Erasmus, Laura P. Spector, Fortunato Ferrara

et al.

Nature Biotechnology, Journal Year: 2024, Volume and Issue: 42(11), P. 1637 - 1642

Published: Nov. 1, 2024

Language: Английский

Citations

2
Functional and epitope specific monoclonal antibody discovery directly from immune sera using cryoEM DOI Creative Commons
James A. Ferguson, Sai Sundar Rajan Raghavan, Garazi Peña Alzua

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 9, 2024

Abstract Antibodies are crucial therapeutics, comprising a significant portion of approved drugs due to their safety and clinical efficacy. Traditional antibody discovery methods labor-intensive, limiting scalability high-throughput analysis. Here, we improved upon our streamlined approach combining structural analysis bioinformatics infer heavy light chain sequences from electron potential maps serum-derived polyclonal antibodies (pAbs) bound antigens. Using ModelAngelo, an automated structure-building tool, accelerated pAb sequence determination identified matches in B cell repertoires via ModelAngelo derived Hidden Markov Models (HMMs) associated with structures. Benchmarking against results non-human primate HIV vaccine trial, pipeline reduced time weeks under day higher precision. Validation murine immune sera influenza vaccination revealed multiple protective antibodies. This workflow enhances discovery, enabling faster, more accurate mapping responses broad applications development therapeutic discovery.

Language: Английский

Citations

2
Reading the repertoire: Progress in adaptive immune receptor analysis using machine learning DOI Creative Commons

Timothy J O'Donnell,

Chakravarthi Kanduri, Giulio Isacchini

et al.

Cell Systems, Journal Year: 2024, Volume and Issue: 15(12), P. 1168 - 1189

Published: Dec. 1, 2024

Language: Английский

Citations

2
The Application of Machine Learning on Antibody Discovery and Optimization DOI Creative Commons

Jiayao Zheng,

Yu Wang, Liang Qin

et al.

Molecules, Journal Year: 2024, Volume and Issue: 29(24), P. 5923 - 5923

Published: Dec. 16, 2024

Antibodies play critical roles in modern medicine, serving as diagnostics and therapeutics for various diseases due to their ability specifically bind target antigens. Traditional antibody discovery optimization methods are time-consuming resource-intensive, though they have successfully generated antibodies diagnosing treating diseases. The advancements protein data, computational hardware, machine learning (ML) models the opportunity disrupt research. Machine demonstrated abilities design. These enable rapid silico design of candidates within a few days, achieving approximately 60% reduction time 50% cost compared traditional methods. This review focuses on latest learning-based developments. We briefly discuss limitations then explore methodologies. also focus future research directions, including developing Antibody Design AI Agents data foundries, alongside ethical regulatory considerations essential adopting learning-driven designs.

Language: Английский

Citations

0