EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning

• URL: http://arxiv.org/abs/2606.04154v1
• Date: Tue, 02 Jun 2026 19:20:25 GMT
• Title: EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
• Abstract summary: EpiFormer is a general-variant-decoder framework for antibody prediction.<n>It improves over the previous best method by over 40% in F1 score on standard benchmarks.<n>EpiFormer discovers known biological principles as emergent behaviors of end-to-end training.
• Score: 5.747428107106341
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Antibodies neutralize foreign antigens by binding to specific surface regions called epitopes. Computational epitope prediction is critical for understanding immune recognition and guiding antibody engineering. However, existing methods face three fundamental challenges: antibody-aware models encode each chain independently and combine them only at a late stage, failing to capture co-dependent structural features that define binding interfaces, whereas severe class imbalance and scarcity of known antibody-antigen complexes render standard training objectives ineffective. We propose EpiFormer, a general encoder-decoder framework that addresses these challenges jointly. Our key design principle is interleaved cross-attention within GNN encoding layers, enabling bidirectional antigen-antibody information flow throughout representation learning rather than only at the output. This early-fusion principle is backbone-agnostic, providing consistent gains across GNN architectures from simple GCNs to equivariant models. We further show that sparsity-aware objectives are effective when paired with early-fusion architectures for the epitope prediction task. EpiFormer improves over the previous best method by over 40% in F1 score on standard benchmarks, demonstrating generalizability and cross-dataset transferability. Notably, EpiFormer discovers known biological principles as emergent behaviors of end-to-end training, where the learned cross-attention gates favor antigen-to-antibody information flow, consistent with the asymmetric roles of the two chains at the binding interface, and the model's preference for geometric over evolutionary features aligns with the established finding that epitope residues are not evolutionarily conserved. The source code is available at: https://github.com/mansoor181/epiformer.git

Related papers

• Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense [80.28330585803133]
  Graph neural networks (GNNs) are widely deployed on computation data, yet they can leak sensitive or proprietary information about the training graph adjacency.<n>This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN.<n>We propose MC-GRA (+), which reconstructs the adjacency by optimizing a surrogate adjacency whose GNN-induced representations align with those of the target model.<n>On the defense side, we propose MC-GPB (+), which suppresses adjacency-dependent information throughout the representation chain
  arXiv  Detail & Related papers  (2026-06-06T09:29:27Z)
• AgForce Enables Antigen-conditioned Generative Antibody Design [3.2018287682779003]
  We propose a novel encoder-decoder architecture called AgForce.<n>It uses a graph neural network (GNN) as the encoder and specialized decoders for sequence-structure co-design.<n>It achieves the best binding quality and sequence recovery simultaneously on the CHIMERA-Bench dataset.
  arXiv  Detail & Related papers  (2026-05-20T18:16:52Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• Bidirectional Representations Augmented Autoregressive Biological Sequence Generation:Application in De Novo Peptide Sequencing [51.12821379640881]
  Autoregressive (AR) models offer holistic, bidirectional representations but face challenges with generative coherence and scalability.<n>We propose a hybrid framework enhancing AR generation by dynamically integrating rich contextual information from non-autoregressive mechanisms.<n>A novel cross-decoder attention module enables the AR decoder to iteratively query and integrate these bidirectional features.
  arXiv  Detail & Related papers  (2025-10-09T12:52:55Z)
• ABConformer: Physics-inspired Sliding Attention for Antibody-Antigen Interface Prediction [3.947298454012977]
  We present ABCONFORMER, a model based on the Conformer backbone that captures both local and global features of a biosequence.<n>ABCONFORMER can accurately predict paratopes and antigens given the antibody and sequence, and predict pan-epitopes on the antigen without antibody information.
  arXiv  Detail & Related papers  (2025-09-27T11:12:04Z)
• BConformeR: A Conformer Based on Mutual Sampling for Unified Prediction of Continuous and Discontinuous Antibody Binding Sites [3.947298454012977]
  In this work, we propose a conformer-based model trained on antigen sequences derived from 1,080 antigen-antibody complexes.<n>CNN enhances the prediction of linears, and the Transformer module improves the prediction of conformationals.<n> Experimental results show that our model outperforms existing baselines in terms of PCC, ROC-AUC, PR-AUC, and F1 scores on both linear and conformationals.
  arXiv  Detail & Related papers  (2025-08-16T12:31:39Z)
• BURN: Backdoor Unlearning via Adversarial Boundary Analysis [73.14147934175604]
  Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality.<n>We propose Backdoor Unlearning via adversaRial bouNdary analysis (BURN), a novel defense framework that integrates false correlation decoupling, progressive data refinement, and model purification.
  arXiv  Detail & Related papers  (2025-07-14T17:13:06Z)
• AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction [12.433560411515575]
  We introduce a filtered antibody-antigen complex structure dataset, AsEP. AsEP is the largest of its kind and provides clustered groups. We propose a novel method, WALLE, which leverages both protein language models and structural modeling from graph neural networks.
  arXiv  Detail & Related papers  (2024-07-25T16:43:56Z)
• Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks [50.87615167799367]
  We certify Graph Neural Networks (GNNs) against poisoning attacks, including backdoors, targeting the node features of a given graph.<n>Our framework provides fundamental insights into the role of graph structure and its connectivity on the worst-case behavior of convolution-based and PageRank-based GNNs.
  arXiv  Detail & Related papers  (2024-07-15T16:12:51Z)
• BeeTLe: A Framework for Linear B-Cell Epitope Prediction and Classification [0.43512163406551996]
  This paper presents a new deep learning-based framework for linear B-cell prediction as well as antibody type-specific classification. We propose an amino acid encoding method based on eigen decomposition to help the model learn the representations of antibodies. Experimental results on data curated from the largest public database demonstrate the validity of the proposed methods.
  arXiv  Detail & Related papers  (2023-09-05T09:18:29Z)
• xTrimoABFold: De novo Antibody Structure Prediction without MSA [77.47606749555686]
  We develop a novel model named xTrimoABFold to predict antibody structure from antibody sequence. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame-aligned point loss.
  arXiv  Detail & Related papers  (2022-11-30T09:26:08Z)
• Reprogramming Pretrained Language Models for Antibody Sequence Infilling [72.13295049594585]
  Computational design of antibodies involves generating novel and diverse sequences, while maintaining structural consistency. Recent deep learning models have shown impressive results, however the limited number of known antibody sequence/structure pairs frequently leads to degraded performance. In our work we address this challenge by leveraging Model Reprogramming (MR), which repurposes pretrained models on a source language to adapt to the tasks that are in a different language and have scarce data.
  arXiv  Detail & Related papers  (2022-10-05T20:44:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.