Maillere, B. | Search bioRxiv

bioRxiv2026

Machine Learning-Guided Engineering of High-Affinity Cross-Reactive Antibodies with Minimal Mutations

Antibodies raised against human targets often fail to recognize their animal orthologs, limiting preclinical evaluation in relevant models. We developed a Deep Mutational Scanning (DMS)-coupled deep learning strategy to engineer potent cross-reactive antibodies with minimal sequence divergence. Starting from C4, a fully human anti-PD-L1 antibody with weak recognition of murine PD-L1, DMS identified substitutions that improved binding to both human and mouse antigens. Conventional recombination of beneficial mutations generated highly cross-reactive antibodies but required 13 to 15 substitutions. To reduce this mutational burden, a deep learning model trained on DMS-derived sequence-binding data was used to identify minimal mutation combinations predicted to retain high affinity. This approach yielded variants carrying only 4 to 5 substitutions, with in vitro and cellular binding properties comparable to highly mutated antibodies. Epitope mapping, structural modeling and in vivo assessment further confirmed that these engineered antibodies retained PD-1/PD-L1 blockade and demonstrated therapeutic activity in a mouse tumor model.

molecular biology↗

bioRxiv2021

Deep Mutational Engineering of broadly-neutralizing and picomolar affinity nanobodies to accommodate SARS-CoV-1 & 2 antigenic polymorphism

We report in this study the molecular engineering of nanobodies that bind with picomolar affinity to both SARS-CoV-1 and SARS-CoV-2 Receptor Binding Domains (RBD) and are highly neutralizing. We applied Deep Mutational Engineering to VHH72, a nanobody initially specific for SARS-CoV-1 RBD with little cross-reactivity to SARS-CoV-2 antigen. We first identified all the individual VHH substitutions that increase binding to SARS-CoV-2 RBD and then screened highly focused combinatorial libraries to isolate engineered nanobodies with improved properties. The corresponding VHH-Fc molecules show high affinities for SARS-CoV-2 antigens from various emerging variants and SARS-CoV-1, block the interaction between ACE2 and RBD and neutralize the virus with high efficiency. Its rare specificity across sarbecovirus relies on its peculiar epitope outside the immunodominant regions. The engineered nanobodies share a common motif of three amino acids, which contribute to the broad specificity of recognition. These nanobodies appears as promising therapeutic candidates to fight SARS-CoV-2 infection.

biochemistry↗

bioRxiv2019

HLA class II polymorphism influences the immune response to protective antigen and susceptibility to Bacillus anthracis

The causative agent of anthrax, Bacillus anthracis, evades the host immune response and establishes infection through the production of binary exotoxins composed of Protective Antigen (PA) and one of two subunits, lethal factor (LF) or edema factor (EF). The majority of vaccination strategies have focused upon the antibody response to the PA subunit. We have used a panel of humanised HLA class II transgenic mouse strains to define HLA-DR-restricted and HLA-DQ-restricted CD4+ T cell responses to the immunodominant epitopes of PA. This was correlated with the binding affinities of epitopes to HLA class II molecules, as well as the responses of two human cohorts: individuals vaccinated with the Anthrax Vaccine Precipitated (AVP) vaccine (which contains PA and trace amounts of LF), and patients recovering from cutaneous anthrax infections. The infected and vaccinated cohorts expressing different HLA types were found to make CD4+ T cell responses to multiple and diverse epitopes of PA. The effects of HLA polymorphism were explored using transgenic mouse lines, which demonstrated differential susceptibility, indicating that HLA-DR1 and HLA-DQ8 alleles conferred protective immunity relative to HLA-DR15, HLA-DR4 and HLA-DQ6. The HLA transgenics enabled a reductionist approach, allowing us to better define CD4+ T cell epitopes. Appreciating the effects of HLA polymorphism on the variability of responses to natural infection and vaccination will be vital in planning protective strategies against anthrax. Author SummaryThe bacterium responsible for causing the disease anthrax, Bacillus anthracis, produces a binary toxin composed of Protective Antigen (PA) and either Lethal Factor (LF) or Edema Factor (EF). Previous vaccination strategies have focused upon the antibody response to the PA subunit. However, within the field of bacterial immunity, there is a growing appreciation of the importance of the adaptive immune response, specifically led by CD4+ T cells. We identified long-term CD4+ T cell responses to PA epitopes following cutaneous human anthrax infection and vaccination, indicating that this toxin component is a principle B. anthracis antigen. To characterise the impact of polymorphism in HLA class II alleles at DR and DQ loci, we used transgenic mice to map the immunodominant epitopes from PA. This was correlated with survival in the transgenic lines following live anthrax challenge. We were able to demonstrate the differential impact of HLA class II alleles upon the CD4+ T cell immunodominant epitopes which shaped the immune hierarchy and therefore susceptibility to anthrax infection.

immunology↗