Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 37 min ago
Peer-reviewedCC BYBioinformatics (Oxford, England)

ParaEM: antigen-aware sequence-based paratope prediction with expectation-maximization.

  • Taegyu Kim1
  • Changyun Cho2
  • Inuk Jung3
  • Sun Kim1,2,4,5
5 affiliations
  1. 1Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul 08826, Republic of Korea.
  2. 2AIGENDRUG Co., Ltd, Seoul 08758, South Korea.
  3. 3School of Computer Science and Engineering, Kyungpook National University, Daegu 41566, Republic of Korea.
  4. 4Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Republic of Korea.
  5. 5Department of Computer Science and Engineering, Seoul National University, Seoul 08826, Republic of Korea.
Read full textPDFDOICite

Abstract

Motivation

Accurate identification of antibody paratopes-the residues contacting the antigen-is vital for understanding antibody-antigen recognition, antibody engineering, and vaccine design. However, structure-based predictors require antibody structural inputs, which are often obtained from experimentally determined antibody-antigen complexes in benchmark settings but are generally unavailable for new sequences. Conversely, sequence-based predictors scale efficiently but remain largely antigen-agnostic, limiting their use of pair-specific antigen context.Results

We introduce ParaEM, an antigen-aware sequence-based paratope predictor that operates directly on antibody and antigen sequences. ParaEM leverages pretrained ESM3 embeddings to encode both sequences, augmenting antibody residues with trainable, complementarity-determining regions (CDR)-informed embeddings to introduce a biologically informed inductive bias. It models interactions via a residue-level compatibility scorer that defines latent antigen-anchor distributions. During training, a generalized Expectation-Maximization (EM) framework alternates between estimating label-conditioned posterior responsibilities (E-step) and performing gradient-based parameter updates (M-step). Evaluated across three established benchmarks, ParaEM outperforms existing sequence-based baselines in AUC-PR and achieves performance competitive with structure-based predictors without requiring explicit three-dimensional structural inputs. Ablation studies show consistent improvements from generalized EM optimization and an additional gain from CDR-informed embeddings. Antibody-side and antigen-information controls further show that antibody sequence carries substantial predictive signal, while the matching antigen provides additional predictive information. Together, these results support ParaEM as a scalable framework for incorporating matching-antigen context into sequence-based paratope prediction.Availability and implementation

ParaEM is available at https://github.com/kimtaegyuu/ParaEM. An archival snapshot of the software corresponding to this study is available on Zenodo at DOI: 10.5281/zenodo.22157100.

Related

  1. KAT-Net: a hyperbolic routing framework for joint lysine acylation site prediction with shared sequence–structure representations
    Briefings in bioinformaticsPeer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMC
  2. Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
    Chanoknun Phunnasorn, Narupat Hongdilokkul, Wasakorn Laesanklang +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
  3. AbLWR: a context-aware listwise ranking framework for antibody-antigen binding affinity prediction via positive-unlabeled learning
    Fan Xu, Zhi-An Huang, Haohuai He +6
    BioinformaticsPeer-reviewedCC BY 4.0Full text1 citedMolecular biology & gene regulationPMC
  4. XChrom: A Cross-Cell Chromatin Accessibility Prediction Model Integrating Genomic Sequence and Cellular Context.
    Yuanyuan Miao, Xuan Liang, Wenwen Zhang +3
    Advanced science (Weinheim, Baden-Wurttemberg, Germany)Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
  5. TAPERSS-MoCa: A Physics-Based Monte Carlo Framework for 3D RNA Structure Prediction from Sequence
    Mariam Ibrahim, Ivan Issac Riveros, Nanayakkara P.N.R. Kumarachchi +1
    ChemRxivPreprintCC BYFull textMolecular biology & gene regulationChemRxiv

Cite

BibTeXRIS
BibTeX
@article{kim2026paraem,
  title = {{ParaEM: antigen-aware sequence-based paratope prediction with expectation-maximization.}},
  author = {Taegyu Kim and Changyun Cho and Inuk Jung and Sun Kim},
  journal = {Bioinformatics (Oxford, England)},
  year = {2026},
  month = oct,
  doi = {10.1093/bioinformatics/btag739},
  url = {https://europepmc.org/article/MED/42834434},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - ParaEM: antigen-aware sequence-based paratope prediction with expectation-maximization.
AU  - Taegyu Kim
AU  - Changyun Cho
AU  - Inuk Jung
AU  - Sun Kim
PY  - 2026
DA  - 2026/10/01
JO  - Bioinformatics (Oxford, England)
DO  - 10.1093/bioinformatics/btag739
UR  - https://europepmc.org/article/MED/42834434
AB  - Motivation  Accurate identification of antibody paratopes-the residues contacting the antigen-is vital for understanding antibody-antigen recognition, antibody engineering, and vaccine design. However, structure-based predictors require antibody structural inputs, which are often obtained from experimentally determined antibody-antigen complexes in benchmark settings but are generally unavailable for new sequences. Conversely, sequence-based predictors scale efficiently but remain largely antigen-agnostic, limiting their use of pair-specific antigen context.Results  We introduce ParaEM, an antigen-aware sequence-based paratope predictor that operates directly on antibody and antigen sequences. ParaEM leverages pretrained ESM3 embeddings to encode both sequences, augmenting antibody residues with trainable, complementarity-determining regions (CDR)-informed embeddings to introduce a biologically informed inductive bias. It models interactions via a residue-level compatibility scorer that defines latent antigen-anchor distributions. During training, a generalized Expectation-Maximization (EM) framework alternates between estimating label-conditioned posterior responsibilities (E-step) and performing gradient-based parameter updates (M-step). Evaluated across three established benchmarks, ParaEM outperforms existing sequence-based baselines in AUC-PR and achieves performance competitive with structure-based predictors without requiring explicit three-dimensional structural inputs. Ablation studies show consistent improvements from generalized EM optimization and an additional gain from CDR-informed embeddings. Antibody-side and antigen-information controls further show that antibody sequence carries substantial predictive signal, while the matching antigen provides additional predictive information. Together, these results support ParaEM as a scalable framework for incorporating matching-antigen context into sequence-based paratope prediction.Availability and implementation  ParaEM is available at https://github.com/kimtaegyuu/ParaEM. An archival snapshot of the software corresponding to this study is available on Zenodo at DOI: 10.5281/zenodo.22157100.
SN  - 1367-4803
SN  - 1367-4811
ER  -