DeImmu-MPNN: Reducing Immunogenicity in De Novo Protein Design
4 affiliations
- 1Center for Protein Assemblies
- 2Technical University of Munich
- 3School of Science
- 4Constructor University
Abstract
De novo-designed proteins lack an evolutionary history of immune tolerance, making antidrug antibody (ADA) responses a barrier to their clinical translation. ProteinMPNN is widely used to design sequences for a given protein backbone, but it does not account for immune tolerance, which is important for therapeutic applications. The ADA response to injected proteins is driven principally by MHC class II presentation of protein-derived peptides to CD4+ T-helper cells. We fine-tuned ProteinMPNN using direct preference optimization to reduce ADA-relevant class II epitopes across a six-allele HLA-DRB1 panel, while also reducing class I epitopes. The resulting model, DeImmu-MPNN, reduces NetMHCIIpan-predicted MHC class II presentation by 41.4% relative to the baseline model, bringing predicted presentation to the level of length-matched human proteins, and NetMHCpan-predicted MHC class I presentation by 33.0% on the same designs, for 2.1 points of sequence recovery and no detectable structural cost. The reduction transfers without retraining to unseen DRB1 alleles, the DRB3/4/5 paralogs, and HLA-DQ. It generalizes to 11 published de novo binder complexes, with mean reductions of 50.4% for class II and 30.2% for class I and no systematic predicted cost to interface confidence. DeImmu-MPNN provides a framework for incorporating immune presentation into protein sequence design and may dramatically facilitate the design of proteins with reduced immunogenicity.
Related
- Design of multi-epitope vaccine based on G2c genotype PEDV antigen and its immunogenicity and protective effect in piglets.
- In Silico Design and Immunogenicity Studies of Two Multi-Epitope Vaccines against Klebsiella pneumoniae.
- In Silico Design and Immunogenicity Evaluation of a Multiepitope Vaccine Candidate Against Leishmania tropica in BALB/c Mice.
- Potato Protein Peptides as a Serum-Reducing Supplement for MDCK Cell Culture Medium.
- Rapid Translation of the Early Coding Region Promotes Premature Transcription Termination, Reducing Protein Expression in Escherichia coli
BibTeX
@misc{halbwedl2026deimmumpnn,
title = {{DeImmu-MPNN: Reducing Immunogenicity in De Novo Protein Design}},
author = {Niklas Halbwedl and Sebastian Springer and Martin Zacharias},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15010686/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010686/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - DeImmu-MPNN: Reducing Immunogenicity in De Novo Protein Design
AU - Niklas Halbwedl
AU - Sebastian Springer
AU - Martin Zacharias
PY - 2026
DA - 2026/10/19
PB - ChemRxiv
DO - 10.26434/chemrxiv.15010686/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010686/v1
AB - De novo-designed proteins lack an evolutionary history of immune tolerance, making antidrug antibody (ADA) responses a barrier to their clinical translation. ProteinMPNN is widely used to design sequences for a given protein backbone, but it does not account for immune tolerance, which is important for therapeutic applications. The ADA response to injected proteins is driven principally by MHC class II presentation of protein-derived peptides to CD4+ T-helper cells. We fine-tuned ProteinMPNN using direct preference optimization to reduce ADA-relevant class II epitopes across a six-allele HLA-DRB1 panel, while also reducing class I epitopes. The resulting model, DeImmu-MPNN, reduces NetMHCIIpan-predicted MHC class II presentation by 41.4% relative to the baseline model, bringing predicted presentation to the level of length-matched human proteins, and NetMHCpan-predicted MHC class I presentation by 33.0% on the same designs, for 2.1 points of sequence recovery and no detectable structural cost. The reduction transfers without retraining to unseen DRB1 alleles, the DRB3/4/5 paralogs, and HLA-DQ. It generalizes to 11 published de novo binder complexes, with mean reductions of 50.4% for class II and 30.2% for class I and no systematic predicted cost to interface confidence. DeImmu-MPNN provides a framework for incorporating immune presentation into protein sequence design and may dramatically facilitate the design of proteins with reduced immunogenicity.
ER -