Ashraf, F. B. | Search bioRxiv

bioRxiv2025

Fine-tuned Protein Language Model Identifies Antigen-specific B Cell Receptors from Immune Repertoires

Scalable identification of antigen-specific antibodies from whole immune repertoire V(D)J sequences is a central challenge in biomedical engineering. We show that protein language models (PLMs) fine-tuned on antibody heavy-chain sequences can directly predict antigen specificity from unselected immune repertoires. We assessed our model, Antigen Specificity Predictor (ASPred), against SARS-CoV-2, influenza, and HIV-AIDS antigens, observing comparable predictive performance. In the whole immune repertoire V(D)J sequences of mice immunized with the SARS-CoV-2 spike proteins receptor-binding domain (RBD), ASPred identified antibody sequences specific to RBD. Several candidate sequences were validated, including one as a heavy chain-only nanobody with 20.7 nM dissociation constant. Molecular dynamics simulations supported the predicted interactions at coarse-grained and atomic levels. Benchmarking against Barcode-Enabled Antigen Mapping (BEAM) of B cell receptor sequence data had highly significant overlaps with ASPred predictions, suggesting scalability. The predicted SARS-CoV-2 binders differed substantially from training sequences, demonstrating generalization beyond sequence memorization. Together, we establish that heavy chain antibody sequences encode sufficient information for PLMs to infer specificity, offering a scalable framework for antibody discovery with broad applications.

bioinformatics↗

bioRxiv2024

A Large Language Model Guides the Affinity Maturation of Variant Antibodies Generated by Combinatorial Optimization

The ability of an antibody to bind an antigen with high specificity and strength (i.e., its binding affinity) are critical properties in the design of neutralizing antibodies. Recent technical advances in AI and a surge of experimental data on antigen-antibody interaction are driving innovations in the design and optimization of antibodies via affinity maturation. Here we introduce Ab-Affinity, a novel large language model which can accurately predict the binding affinity of specific antibodies against a target peptide within the SARS-CoV-2 spike protein. When used in conjunction with a genetic algorithm and simulated annealing, Ab-Affinity can generate novel antibodies with more than a 160-fold increase in predicted binding affinity compared to those obtained experimentally. Our experimental results show that the synthetic antibodies produced by Ab-Affinity have strong predicted biophysical properties. Molecular docking and molecular dynamics simulation of binding interactions of the best synthetic antibodies show enhanced interactions and stability on the target peptide epitope. In general, antibodies generated by Ab-Affinity are superior to those obtained with other existing computational methods.

molecular biology↗