PMGen: from peptide-MHC structure prediction to peptide generation
Bioinformatics · 01.06.2026 · 42 (6)
DOI: 10.1093/bioinformatics/btag381 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.06.2026. Verfasst von Amir H Asgary und 8 weiteren Autor:innen. Beteiligte Einrichtung: Quantitative and Computational Biology Group, Max Planck Institute for Multidisciplinary Sciences, Göttingen 37077, Germany. Hauptthemen laut MEDLINE: Peptides, Major Histocompatibility Complex, Software, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation, the Max Planck Society, European Research Council.
Abstract (Originalsprache)
Motivation Accurate structural modeling of peptide–major histocompatibility complex (pMHC) complexes is essential for structure-driven immunotherapy design, yet current prediction tools suffer from narrow class coverage, restricted peptide lengths, insufficient accuracy, and a lack of built-in structure-aware peptide sampling. Consequently, most mimotope and altered peptide ligand designs rely solely on sequence substitution, leaving spatial and biophysical insights from pMHC structures largely unexploited. Results We introduce peptide–MHC generator (PMGen), an integrated framework for structure prediction and structure-guided design of variable-length peptides across MHC Class I and II. PMGen enforces anchor constraints within AlphaFold2 through two complementary strategies, initial guess and template engineering, achieving state-of-the-art structural fidelity without model fine-tuning. On a comprehensive benchmark, PMGen outperforms all existing methods, yielding median peptide-core Cα RMSDs of 0.62 Å for MHC-I and 0.33 Å for MHC-II. We show that PMGen can recover incorrectly predicted anchor positions and that AlphaFold pLDDT scores enable sequence-independent binding-core identification. Applied to a published neoantigen/wild-type pair, PMGen accurately captures mutation-induced conformational changes. Beyond structure prediction, we show that ProteinMPNN sampling on PMGen-predicted backbones yields higher affinity peptides while preserving the parental 3D conformation. Using PMGen to generate 63 817 high-confidence pMHC structures as training data, we further improve ProteinMPNN’s peptide sequence recovery from 0.14 to 0.64 on a test set of 85 unseen MHC-I alleles, highlighting the value of accurate predicted structures for downstream machine learning tasks. Availability and implementation PMGen is freely available at https://github.com/soedinglab/PMGen, with an interactive Colab notebook at https://colab.research.google.com/github/soedinglab/PMGen/blob/master/colab.ipynb.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Quantitative and Computational Biology Group, Max Planck Institute for Multidisciplinary Sciences, Göttingen 37077, Germany.
- Institute of Immunobiology, Kantonsspital St. Gallen, St. Gallen 9007, Switzerland.
- Centre for Inflammation Biology and Cancer Immunology (CIBCI) & Peter Gorer Department of Immunobiology, King's College London, London SE1 1UL, United Kingdom.
- Research Group of Molecular Immunology The Francis Crick Institute, London NW1 1AT, United Kingdom.
- Max Planck Institute for Multidisciplinary Sciences, Göttingen 37077, Germany.
ORCID-Profile: Amir H Asgary, Johannes Söding
Förderung
- Swiss National Science Foundation
- the Max Planck Society
- European Research Council
- Cancer Research UK
- CRUK City of London Centre
- MPI-NAT Collaboration
Zitieren
APA
Asgary, A. H., Aleyasin, A., Mehl, J. A., Fallah, S. S., Aintablian, H., Ludewig, B., Mishto, M., Liepe, J., & Söding, J. (2026). PMGen: from peptide-MHC structure prediction to peptide generation. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag381
Vancouver
Asgary AH, Aleyasin A, Mehl JA, Fallah SS, Aintablian H, Ludewig B, et al. PMGen: from peptide-MHC structure prediction to peptide generation. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag381
BibTeX
@article{Asgary2026,
author = {Asgary, Amir H and Aleyasin, Amirreza and Mehl, Jonas A and Fallah, Salman S and Aintablian, Hasmig and Ludewig, Burkhard and Mishto, Michele and Liepe, Juliane and Söding, Johannes},
title = {PMGen: from peptide-MHC structure prediction to peptide generation},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {6},
doi = {10.1093/bioinformatics/btag381}
}
EUVIMED