EUVIMEDEUVIMED entdecken
Open Access

Repertoire-scale antibody structural prediction informs therapeutic design

Zhe Sang iD, Yufei Xiang iD, Wei Huang iD, Paul R Sargunas iD, Yong Joon Jeffery Kim iD, Zirui Feng, Derek J Taylor iD, Yi Shi iD

Science Advances · 2026

DOI: 10.1126/sciadv.aef7163 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2026. Verfasst von Zhe Sang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Center for Protein Engineering and Therapeutics, Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA. Hauptthemen laut MEDLINE: Single-Domain Antibodies, Drug Design, Antigen-Antibody Complex. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 83 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NCATS NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present AF3-TurboAb, a scalable framework that makes a repertoire-scale antibody-antigen complex structural decoding routine for antibody engineering. By eliminating preprocessing bottlenecks, AF3-TurboAb enables end-to-end complex modeling in 0.5 minutes per seed on a single GPU while preserving near-experimental interface fidelity, as validated on ~1000 posttraining Protein Data Bank (PDB) benchmarks and 12 experimentally determined cryo–electron microscopy nanobody-antigen structures. Applying this capability to 275,371 immunization-derived antigen-specific nanobodies produced 28,013 high-confidence complex predictions, substantially expanding the structural landscape of antibody recognition. The resulting atlas reveals hundreds of previously unmapped epitopes, extensive coverage of solvent-exposed surfaces, and recurrent affinity hotspots enriched in aromatic and charged residues. Despite wide sequence diversity, we observe structural convergence at shared epitopes and consistent physicochemical and geometric features that complement and extend existing PDB entries. We demonstrate translational utility by (i) designing durable (escape-proof), multiepitope neutralizers against highly evolved viruses, (ii) identifying cross-species and glycoform-specific binders to a cancer checkpoint, and (iii) enabling near-real-time in silico binder triage. The models and metadata will be shared for community use, establishing repertoire-scale structural decoding as a practical design modality that transforms the scale and speed of structure-guided antibody engineering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Domain AntibodiesDrug DesignAntigen-Antibody ComplexEpitopesHumansModels, MolecularProtein ConformationCryoelectron MicroscopyProtein EngineeringDatabases, Protein

Substanzen

EpitopesSingle-Domain AntibodiesAntigen-Antibody Complex

Autor:innen und Institutionen

  • Center for Protein Engineering and Therapeutics, Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
  • Department of Pharmacology, Case Western Reserve University, Cleveland, OH, USA.

ORCID-Profile: Zhe Sang, Yufei Xiang, Wei Huang, Paul R Sargunas, Yong Joon Jeffery Kim, Derek J Taylor, Yi Shi

Förderung

  • NIGMS NIH HHS
  • NCATS NIH HHS
  • National Institutes of Health
  • Clinical and Translational Science Awards

Zitieren

APA

Sang, Z., Xiang, Y., Huang, W., Sargunas, P. R., Kim, Y. J. J., Feng, Z., Taylor, D. J., & Shi, Y. (2026). Repertoire-scale antibody structural prediction informs therapeutic design. Science Advances. https://doi.org/10.1126/sciadv.aef7163

Vancouver

Sang Z, Xiang Y, Huang W, Sargunas PR, Kim YJJ, Feng Z, et al. Repertoire-scale antibody structural prediction informs therapeutic design. Science Advances. 2026. doi:10.1126/sciadv.aef7163

BibTeX
@article{Sang2026,
  author = {Sang, Zhe and Xiang, Yufei and Huang, Wei and Sargunas, Paul R and Kim, Yong Joon Jeffery and Feng, Zirui and Taylor, Derek J and Shi, Yi},
  title = {Repertoire-scale antibody structural prediction informs therapeutic design},
  journal = {Science Advances},
  year = {2026},
  doi = {10.1126/sciadv.aef7163}
}
Kostenlos starten →