EconPapers    
Economics at your fingertips  
 

An antigen-specific protein language model guides CDR optimization for antibody design

Faisal Bin Ashraf, Karen Paco, Sanaz Zebardast, Zihao Zhang, Ryan Mooney, Christian J Dávila Ojeda, Mariana Paco Mendivil, Rashid M Alam, Eva Chen, Iraneus Ogu, Jordan A Lay, Tristan Y Yang, Fernando L Barroso da Silva, Malkiat Johal, Ilya Tolstorukov, Matthew H Sazinsky, Animesh Ray and Stefano Lonardi

PLOS Computational Biology, 2026, vol. 22, issue 11, 1-30

Abstract: The capacity of an antibody to recognize and bind an antigen with high specificity and strength (i.e., its binding affinity) is a key determinant in the design and optimization of neutralizing antibodies against pathogenic targets. Here we introduce Ab-Affinity, a fine-tuned protein language model (PLM) that predicts the binding affinity of an antibody against a target peptide within the SARS-CoV-2 spike protein. Cross-validation results shows that that Ab-Affinity outperforms other PLM-based affinity predictors when evaluated on a held-out validation and independent test sets. When integrated with a genetic algorithm and simulated annealing for sequence diversification and fitness optimization, Ab-Affinity enables the generation of candidate antibodies exhibiting over 100-fold improvement in predicted binding affinity relative to its parental (natural) antibody. More broadly, antibodies designed with Ab-Affinity attain higher predicted binding affinities than those produced by alternative mutational strategies, yielding synthetic antibodies with favorable predicted biophysical characteristics. Molecular docking and molecular dynamics simulations for the strongest synthetic candidates indicate enhanced interactions and increased stability with the target peptide epitope within the spike protein. Experimental validation in vitro for a top-ranked candidate reveals an apparent increase in binding relative to its parental antibody. All model weights, source code, and analysis pipelines are publicly released to allow full reproducibility.Author summary: Antibodies are essential components of the adaptive immune system and are increasingly being developed and deployed as therapeutic modalities. The rational design of novel antibodies capable of effectively recognizing and neutralizing specific pathogens is computationally challenging, owing to the immensely large combinatorial space of possible antibody sequences. In this work, we introduce a computational framework that leverages machine learning to systematically explore antibody sequence space and to identify variants predicted to exhibit enhanced binding affinity toward a predefined viral target. By fine-tuning a protein language model and coupling it with an optimization algorithm, our approach enables the in silico generation of synthetic antibody sequences with improved binding properties — supported by molecular docking, molecular dynamics simulations, and experimental in vitro validation — relative to the corresponding naturally occurring antibody.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014924 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 14924&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1014924

DOI: 10.1371/journal.pcbi.1014924

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().

 
Page updated 2026-11-15
Handle: RePEc:plo:pcbi00:1014924