Biology subjects

Sazinsky, M. H.

Publications and source records attributed to Sazinsky, M. H..

2 recordsLinked to original sources

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↗

bioRxiv2020

CryoEM structure of the Vibrio cholerae Type IV competence pilus secretin PilQ

Natural transformation is the process by which bacteria take up genetic material from their environment and integrate it into their genome by homologous recombination. It represents one mode of horizontal gene transfer and contributes to the spread of traits like antibiotic resistance. In Vibrio cholerae, the Type IV competence pilus is thought to facilitate natural transformation by extending from the cell surface, binding to exogenous DNA, and retracting to thread this DNA through the outer membrane secretin, PilQ. A lack of structural information has hindered our understanding of this process, however. Here, we solved the first ever high-resolution structure of a Type IV competence pilus secretin. A functional tagged allele of VcPilQ purified from native V. cholerae cells was used to determine the cryoEM structure of the PilQ secretin in amphipol to [~]2.7 [A]. This structure highlights for the first time key differences in the architecture of the Type IV competence pilus secretin from the Type II and Type III Secretin System secretins. Based on our cryoEM structure, we designed a series of mutants to interrogate the mechanism of PilQ. These experiments provide insight into the channel that DNA likely traverses to promote the spread of antibiotic resistance via horizontal gene transfer by natural transformation. We prove that it is possible to reduce pilus biogenesis and natural transformation by sealing the gate, suggesting VcPilQ as a new drug target.

biophysics↗