EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Confidence scoring for deep learning-predicted antibody–antigen complexes: AntiConf as a precision-driven metric

Serbülent Ünsal, Benjamin Holland, Inci Sardag, Emel Timucin iD

Briefings in Bioinformatics · 01.03.2026 · 27 (2)

DOI: 10.1093/bib/bbag137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 28.03.2026. Verfasst von Serbülent Ünsal und 3 weiteren Autor:innen. Beteiligte Einrichtung: Antiverse, Antiverse ltd., sbarc/spark, Maindy Road, CF24 4HQ Cardiff, United Kingdom. Hauptthemen laut MEDLINE: Deep Learning, Antigen-Antibody Complex. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate determination of antibody–antigen (Ab–Ag) complex structures is critical for therapeutic development. While deep learning-based methods, beginning with AlphaFold2 (AF2), have revolutionized multimer predictions, the optimal strategies for Ab–Ag modeling, and the reliability of their confidence scores remain active areas of research. This study evaluates the performance of AF2, Boltz-1, Boltz-1x, Boltz-2, Chai-1, Protenix, Protenix-1, OpenFold3, and ESMFold, on a curated dataset of 200 Ab–Ag complexes. Among the nine methods tested, Protenix-1 emerged as the top performer, with Chai-1 consistently ranking second across multiple success metrics, closely followed by AF2. We observed diverse effects of recycling iterations, with AF2, Chai-1, and Protenix variants benefiting from increased cycles, unlike Boltz variants. We analyzed various model confidence scores, noting high precision from pDockQ2 and high recall from predicted Template-Modeling (pTM) score. By integrating these two scores, we developed antibody confidence (AntiConf), a novel metric that achieves superior performance for all methods in terms of precision and recall. These strengths make AntiConf a valuable post score for both computational predictions and downstream experimental workflows, reflecting its potential to improve Ab–Ag complex predictions by AF2 and AF3 architectures. Altogether, this study addresses current limitations in deep learning-based Ab–Ag complex prediction, showcasing the potential of AntiConf for future assessment studies, and providing a guideline for improving the accuracy of Ab–Ag complex prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAntigen-Antibody ComplexHumansComputational BiologyAlgorithmsModels, Molecular

Stichwörter der Autor:innen

AF3-based implementationsAlphafold2antibody–antigen complexesmodel confidence scoresmultimer prediction

Substanzen

Antigen-Antibody Complex

Autor:innen und Institutionen

  • Antiverse, Antiverse ltd., sbarc/spark, Maindy Road, CF24 4HQ Cardiff, United Kingdom.
  • Faculty of Medicine, Karadeniz Technical University, Kanuni Campus, 61080 Trabzon, Turkey.
  • Department of Molecular Biology and Genetics, Bogazici University, North Campus, 34342 Istanbul, Turkey.
  • Department of Molecular Biology and Genetics, Gebze Technical University, Cumhuriyet 2254 St., Gebze, 41400 Kocaeli, Turkey.

ORCID-Profile: Emel Timucin

Zitieren

APA

Ünsal, S., Holland, B., Sardag, I., & Timucin, E. (2026). Confidence scoring for deep learning-predicted antibody–antigen complexes: AntiConf as a precision-driven metric. Briefings in Bioinformatics, 27(2). https://doi.org/10.1093/bib/bbag137

Vancouver

Ünsal S, Holland B, Sardag I, Timucin E. Confidence scoring for deep learning-predicted antibody–antigen complexes: AntiConf as a precision-driven metric. Briefings in Bioinformatics. 2026;27(2). doi:10.1093/bib/bbag137

BibTeX
@article{nsal2026,
  author = {Ünsal, Serbülent and Holland, Benjamin and Sardag, Inci and Timucin, Emel},
  title = {Confidence scoring for deep learning-predicted antibody–antigen complexes: AntiConf as a precision-driven metric},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {2},
  doi = {10.1093/bib/bbag137}
}
Kostenlos starten →