pith. sign in

arxiv: 2606.04154 · v1 · pith:ZWSNQYOJnew · submitted 2026-06-02 · 🧬 q-bio.QM · cs.LG

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

Mansoor Ahmed , Huirong Chai , Haoxin Wang , Hemanth Venkateswara , Murray Patterson This is my paper

Pith reviewed 2026-06-28 07:10 UTC · model grok-4.3

classification 🧬 q-bio.QM cs.LG
keywords epitope predictionantigen-antibody interactionsgeometric deep learninggraph neural networkscross-attentionprotein structure predictionimmune system modelingantibody engineering
0
0 comments X

The pith

EpiFormer predicts antibody binding sites on antigens by interleaving cross-attention inside GNN layers to exchange structural information bidirectionally from the first layer onward.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents EpiFormer as a way to predict epitopes, the surface patches on antigens where antibodies attach, by modeling the two molecules together throughout the learning process. Prior approaches encode each chain on its own and merge the results only at the final step, which misses the joint geometric features that actually define the binding interface, and they also suffer from extreme data imbalance. EpiFormer inserts cross-attention steps inside every graph neural network layer so antigen and antibody representations continuously update each other. When this early-fusion design is paired with sparsity-aware training losses, the method records more than 40 percent higher F1 scores on standard benchmarks and recovers expected biological patterns, such as stronger flow from antigen to antibody and greater reliance on geometry than on evolutionary conservation, as automatic outcomes of training. A reader would care because better epitope prediction could speed up the design of therapeutic antibodies and vaccines without needing exhaustive experimental mapping of every complex.

Core claim

EpiFormer is a general encoder-decoder framework whose central mechanism is interleaved cross-attention placed inside GNN encoding layers. This design produces bidirectional antigen-antibody information flow at every stage of representation learning instead of only at the output. The same early-fusion principle works across different GNN backbones and becomes especially effective when combined with sparsity-aware objectives. On standard benchmarks the resulting model exceeds the previous best method by more than 40 percent in F1 score, shows cross-dataset transfer, and produces attention patterns and feature preferences that match known biology without any explicit supervision on those prope

What carries the argument

Interleaved cross-attention within GNN encoding layers, which enables continuous bidirectional exchange of structural features between antigen and antibody throughout representation learning rather than only at the final output.

If this is right

  • The early-fusion principle delivers consistent gains when swapped into GNN architectures ranging from simple GCNs to equivariant models.
  • Sparsity-aware training objectives become effective only when paired with architectures that perform antigen-antibody fusion early rather than late.
  • Learned cross-attention weights spontaneously favor antigen-to-antibody information flow, reproducing the asymmetric roles of the two chains at real binding interfaces.
  • The model assigns higher importance to geometric features than to evolutionary sequence conservation, matching the established observation that epitope residues are not conserved across related antigens.
  • The same architecture exhibits measurable cross-dataset transferability on epitope prediction tasks.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The interleaved cross-attention pattern could be tested on other protein-protein interface tasks, such as predicting binding sites between enzymes and substrates, to see whether the same early-fusion benefit appears without task-specific redesign.
  • If the model truly down-weights evolutionary features in favor of geometry, future versions could be trained on single structures alone and still reach comparable accuracy, removing the need for large multiple-sequence alignments.
  • Applying the architecture to complexes involving entirely novel pathogen antigens not seen in any training distribution would provide a direct test of whether the learned geometric representations transfer beyond the benchmark distribution.
  • The discovery that biological asymmetry emerges from end-to-end training suggests that similar attention-based GNNs might surface other interface rules, such as preferred secondary-structure motifs at binding sites, that were not explicitly encoded.

Load-bearing premise

The standard benchmarks used for evaluation are representative of real-world antigen-antibody complexes and the model will generalize to unseen sequences and structures outside the training distribution.

What would settle it

Evaluating the trained model on a new collection of antigen-antibody complexes drawn from a different experimental source or containing sequences and folds absent from the original training data yields F1 scores no higher than the previous best method.

Figures

Figures reproduced from arXiv: 2606.04154 by Haoxin Wang, Hemanth Venkateswara, Huirong Chai, Mansoor Ahmed, Murray Patterson.

Figure 1
Figure 1. Figure 1: Overview of EpiFormer. (a) Parallel EGNN-R encoders with interleaved cross-attention. (b) Bidirectional cross-attention decoder producing the interaction map. (c) Encoder block schematic (“⊕" = addition). (d) Multi-head cross-attention between antigen and antibody residues. Encoder. EpiFormer contains two parallel encoders with no shared parameters, one dedicated to the antigen chain and the other to the a… view at source ↗
Figure 2
Figure 2. Figure 2: F1 sensitivity to seven loss hyperparameters across both splits. Most weights show flat [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: (a) Ground-truth contact map, pairwise distance map, and predicted interaction matrix for [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Learned cross-attention gate values (α) across encoder blocks for four initialization values (αinit ∈ {0.0, 0.05, 0.2, 0.4}). (a) Antigen gate. (b) Antibody gate. The antibody gate consistently exceeds the antigen gate, reflecting the asymmetric roles of the two chains. 5 Conclusion We presented EpiFormer, a general encoder-decoder framework for antibody-aware epitope prediction that addresses late fusion,… view at source ↗
Figure 5
Figure 5. Figure 5: Size distributions of antigen surface residues, antibody CDR residues, epitope residues, and [PITH_FULL_IMAGE:figures/full_fig_p013_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: (a) Node and edge features encoding position, distance, direction, angle, and orientation [PITH_FULL_IMAGE:figures/full_fig_p020_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: (a) Layer-wise silhouette scores showing progressive class separability from encoder to [PITH_FULL_IMAGE:figures/full_fig_p022_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: t-SNE visualization of antigen residue embeddings from the final encoder layer, colored by [PITH_FULL_IMAGE:figures/full_fig_p023_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Test set performance across four interleaved-MHCA gate initialization values ( [PITH_FULL_IMAGE:figures/full_fig_p026_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Encoder AG→AB cross-attention heatmaps for complex 6xq0_1P. Rows: αinit ∈ {0.0, 0.05, 0.2, 0.4}; columns: encoder blocks 0–3. Ground-truth epitope (red) and paratope (cyan) residues are overlaid. 26 [PITH_FULL_IMAGE:figures/full_fig_p026_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Decoder cross-attention and predicted interaction maps vs. ground-truth contacts for [PITH_FULL_IMAGE:figures/full_fig_p027_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Per-block coordinate displacement magnitude across EGNN-R encoder blocks 1–3 [PITH_FULL_IMAGE:figures/full_fig_p028_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Per-complex metric distributions (AUROC, AUPRC, F1, MCC, Precision, Recall) stratified [PITH_FULL_IMAGE:figures/full_fig_p028_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Per-complex metric distributions (AUROC, AUPRC, F1, MCC, Precision, Recall) stratified [PITH_FULL_IMAGE:figures/full_fig_p029_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Per-complex metric distributions on the epitope-ratio test set (170 complexes) for Epi [PITH_FULL_IMAGE:figures/full_fig_p030_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Distribution shift between AsEP and three external benchmarks across (a) antigen size, (b) [PITH_FULL_IMAGE:figures/full_fig_p030_16.png] view at source ↗
read the original 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

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The manuscript introduces EpiFormer, a general encoder-decoder framework for epitope prediction that employs interleaved cross-attention within GNN encoding layers to enable early bidirectional fusion of antigen and antibody information. It pairs this architecture with sparsity-aware training objectives to handle class imbalance and claims an improvement of over 40% in F1 score relative to the previous best method on standard benchmarks, along with cross-dataset transferability and the emergence of biologically plausible behaviors (asymmetric antigen-to-antibody attention flow and preference for geometric over evolutionary features) from end-to-end training. Source code is provided.

Significance. If the performance claims hold under rigorous evaluation, the work would advance computational immunology by demonstrating that early-fusion cross-attention architectures can substantially outperform late-fusion baselines for antigen-antibody interface prediction. The backbone-agnostic design and the alignment of learned attention patterns with established biological asymmetries constitute additional strengths. Reproducibility is supported by the linked GitHub repository.

major comments (1)
  1. [Abstract] The central performance claim (over 40% F1 improvement) is load-bearing yet unsupported by any concrete information on benchmark datasets, baseline re-implementations, train/test splits, or statistical significance testing. Without these details the magnitude and robustness of the reported gain cannot be assessed.
minor comments (1)
  1. [Abstract] The abstract refers to 'standard benchmarks' without naming the datasets or citing the prior papers that established them.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their careful review and for highlighting the need for greater transparency around the central performance claim. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] The central performance claim (over 40% F1 improvement) is load-bearing yet unsupported by any concrete information on benchmark datasets, baseline re-implementations, train/test splits, or statistical significance testing. Without these details the magnitude and robustness of the reported gain cannot be assessed.

    Authors: The manuscript reports these details in the Methods (dataset curation, preprocessing, and train/test split protocol) and Results (baseline re-implementations under identical splits, F1 scores with standard deviations across five random seeds, and paired t-test p-values) sections, together with explicit dataset identifiers and cross-dataset transfer experiments. The abstract condenses the finding for brevity. To improve self-containment of the claim, we will revise the abstract to include a concise statement of the evaluation protocol and benchmarks used. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper presents an empirical geometric deep learning model (EpiFormer) for epitope prediction. Its central claims rest on end-to-end training of a GNN with interleaved cross-attention and sparsity-aware losses, followed by benchmark evaluation reporting F1 improvements. No equations, derivations, or first-principles results are described that reduce any reported prediction or performance metric to a quantity defined by the model itself. No self-citation chains, uniqueness theorems, or ansatzes are invoked as load-bearing justifications. The architecture and objectives are standard ML design choices evaluated on external data, making the derivation chain self-contained against benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on standard machine-learning assumptions that benchmark datasets are representative and that end-to-end training on limited positive examples will yield generalizable representations; no additional free parameters, axioms, or invented entities are specified in the abstract.

pith-pipeline@v0.9.1-grok · 5827 in / 1092 out tokens · 27414 ms · 2026-06-28T07:10:14.406258+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

232 extracted references · 25 canonical work pages

  1. [1]

    biorxiv , title =

    Chen, Xingyao and Dougherty, Thomas and Hong, Chan and Schibler, Rachel and Zhao, Yi and Sadeghi, Reza and Matasci, Naim and Wu, Yi-Chieh and Kerman, Ian , year =. biorxiv , title =

  2. [2]

    Prediction of Antibody-Antigen Binding via Machine Learning: Development of Data Sets and Evaluation of Methods

    Ye, Chao and Hu, Wenxing and Gaeta, Bruno. Prediction of Antibody-Antigen Binding via Machine Learning: Development of Data Sets and Evaluation of Methods. JMIR Bioinform Biotech. 2022. doi:10.2196/29404

    work page doi:10.2196/29404 2022

  3. [3]

    and Friedensohn, Simon and Weber, C

    Mason, Derek M. and Friedensohn, Simon and Weber, C. Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning , journal=. 2021 , month=. doi:10.1038/s41551-021-00699-9 , url=

    work page doi:10.1038/s41551-021-00699-9 2021

  4. [4]

    MAbs , volume=

    Discovery-stage identification of drug-like antibodies using emerging experimental and computational methods , author=. MAbs , volume=. 2021 , organization=

    2021

  5. [5]

    Antibody stability: A key to performance - Analysis, influences and improvement , journal =

    Hui Ma and Ciarán Ó’Fágáin and Richard O’Kennedy , keywords =. Antibody stability: A key to performance - Analysis, influences and improvement , journal =. 2020 , issn =. doi:https://doi.org/10.1016/j.biochi.2020.08.019 , url =

    work page doi:10.1016/j.biochi.2020.08.019 2020

  6. [6]

    doi:https://doi.org/10.1111/cbdd.13388 , url =

    Muhammed, Muhammed Tilahun and Aki-Yalcin, Esin , title =. doi:https://doi.org/10.1111/cbdd.13388 , url =. https://onlinelibrary.wiley.com/doi/pdf/10.1111/cbdd.13388 , year =

    work page doi:10.1111/cbdd.13388

  7. [7]

    Journal of Biomedical Science , year=

    Lu, Ruei-Min and Hwang, Yu-Chyi and Liu, I-Ju and Lee, Chi-Chiu and Tsai, Han-Zen and Li, Hsin-Jung and Wu, Han-Chung , title=. Journal of Biomedical Science , year=. doi:10.1186/s12929-019-0592-z , url=

    work page doi:10.1186/s12929-019-0592-z

  8. [8]

    Grange, R. D. and Thompson, J. P. and Lambert, D. G. , title = ". BJA: British Journal of Anaesthesia , volume =. 2014 , month =. doi:10.1093/bja/aet293 , url =

    work page doi:10.1093/bja/aet293 2014

  9. [9]

    Frontiers in Immunology , VOLUME=

    Huang, Yan and Zhang, Ziding and Zhou, Yuan , TITLE=. Frontiers in Immunology , VOLUME=. 2022 , URL=. doi:10.3389/fimmu.2022.1053617 , ISSN=

    work page doi:10.3389/fimmu.2022.1053617 2022

  10. [10]

    PLOS ONE , publisher =

    Assisted Design of Antibody and Protein Therapeutics (ADAPT) , year =. PLOS ONE , publisher =. doi:10.1371/journal.pone.0181490 , author =

    work page doi:10.1371/journal.pone.0181490

  11. [11]

    and Ascher, David B

    Pires, Douglas E.V. and Ascher, David B. , title = ". Nucleic Acids Research , volume =. 2016 , month =. doi:10.1093/nar/gkw458 , url =

    work page doi:10.1093/nar/gkw458 2016

  12. [12]

    Khamis and Walid Gomaa and Walaa F

    Mohamed A. Khamis and Walid Gomaa and Walaa F. Ahmed , keywords =. Machine learning in computational docking , journal =. 2015 , issn =. doi:https://doi.org/10.1016/j.artmed.2015.02.002 , url =

    work page doi:10.1016/j.artmed.2015.02.002 2015

  13. [13]

    and Andersen, Jan Terje and Greiff, Victor , title=

    Akbar, Rahmad and Bashour, Habib and Rawat, Puneet and Robert, Philippe A. and Andersen, Jan Terje and Greiff, Victor , title=. mAbs , year=. doi:10.1080/19420862.2021.2008790 , url=

    work page doi:10.1080/19420862.2021.2008790 2021

  14. [14]

    and Lehmann, Paul V

    Ras-Carmona, Alvaro and Lehmann, Alexander A. and Lehmann, Paul V. and Reche, Pedro A. , title=. Scientific Reports , year=. doi:10.1038/s41598-022-18021-1 , url=

    work page doi:10.1038/s41598-022-18021-1

  15. [15]

    BMC Genomics , year=

    Ren, Jing and Song, Jiangning and Ellis, John and Li, Jinyan , title=. BMC Genomics , year=. doi:10.1186/s12864-017-3493-0 , url=

    work page doi:10.1186/s12864-017-3493-0

  16. [16]

    BepFAMN : A Method for Linear B-Cell Epitope Predictions Based on Fuzzy-ARTMAP Artificial Neural Network

    La Marca, Anthony F and Lopes, Robson da S and Lotufo, Anna Diva P and Bartholomeu, Daniella C and Minussi, Carlos R. BepFAMN : A Method for Linear B-Cell Epitope Predictions Based on Fuzzy-ARTMAP Artificial Neural Network. Sensors (Basel)

  17. [17]

    Bioinformatics , volume =

    Liberis, Edgar and Veličković, Petar and Sormanni, Pietro and Vendruscolo, Michele and Liò, Pietro , title = ". Bioinformatics , volume =. 2018 , month =. doi:10.1093/bioinformatics/bty305 , url =

    work page doi:10.1093/bioinformatics/bty305 2018

  18. [18]

    Bioinformatics , volume=

    Paragraph—antibody paratope prediction using graph neural networks with minimal feature vectors , author=. Bioinformatics , volume=. 2023 , publisher=

    2023

  19. [19]

    2025 , doi =

    Ahmed, Mansoor and Ali, Sarwan and Jan, Avais and Khan, Imdad Ullah and Patterson, Murray , title =. 2025 , doi =

    2025

  20. [20]

    Antibodies , volume=

    In silico methods in antibody design , author=. Antibodies , volume=. 2018 , publisher=

    2018

  21. [21]

    PloS one , volume=

    OptMAVEn--a new framework for the de novo design of antibody variable region models targeting specific antigen epitopes , author=. PloS one , volume=. 2014 , publisher=

    2014

  22. [22]

    Attentive Cross-Modal Paratope Prediction , journal =

    Deac, Andreea and Veli. Attentive Cross-Modal Paratope Prediction , journal =. 2019 , doi =

    2019

  23. [23]

    Nucleic acids research , year=

    Chailyan, Anna and Tramontano, Anna and Marcatili, Paolo , title=. Nucleic acids research , year=. doi:10.1093/nar/gkr806 , url=

    work page doi:10.1093/nar/gkr806

  24. [24]

    and Johnson, David S

    Lim, Yoong Wearn and Adler, Adam S. and Johnson, David S. , title=. mAbs , year=. doi:10.1080/19420862.2022.2069075 , url=

    work page doi:10.1080/19420862.2022.2069075 2022

  25. [25]

    Briefings in bioinformatics , volume=

    AntiFormer: graph enhanced large language model for binding affinity prediction , author=. Briefings in bioinformatics , volume=. 2024 , publisher=

    2024

  26. [26]

    Bioinformatics , volume=

    CSM-AB: Graph-based antibody--antigen binding affinity prediction and docking scoring function , author=. Bioinformatics , volume=. 2022 , publisher=

    2022

  27. [27]

    Structure , volume=

    ANTIPASTI: interpretable prediction of antibody binding affinity exploiting Normal Modes and Deep Learning , author=. Structure , volume=. 2024 , publisher=

    2024

  28. [28]

    Nature Machine Intelligence , volume=

    A topology-based network tree for the prediction of protein--protein binding affinity changes following mutation , author=. Nature Machine Intelligence , volume=. 2020 , publisher=

    2020

  29. [29]

    Journal of Computational Biology , volume=

    Reads2vec: Efficient embedding of raw high-throughput sequencing reads data , author=. Journal of Computational Biology , volume=. 2023 , publisher=

    2023

  30. [30]

    Algorithms , volume=

    Robust representation and efficient feature selection allows for effective clustering of sars-cov-2 variants , author=. Algorithms , volume=. 2021 , publisher=

    2021

  31. [31]

    Bioinformatics Research and Applications: 17th International Symposium, ISBRA 2021, Shenzhen, China, November 26--28, 2021, Proceedings 17 , pages=

    A k-mer based approach for sars-cov-2 variant identification , author=. Bioinformatics Research and Applications: 17th International Symposium, ISBRA 2021, Shenzhen, China, November 26--28, 2021, Proceedings 17 , pages=. 2021 , organization=

    2021

  32. [32]

    Biology , volume=

    Exploring the Potential of GANs in Biological Sequence Analysis , author=. Biology , volume=. 2023 , publisher=

    2023

  33. [33]

    International Workshop on Deep Learning in Medical Image Analysis , pages=

    Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations , author=. International Workshop on Deep Learning in Medical Image Analysis , pages=. 2017 , organization=

    2017

  34. [34]

    International conference on machine learning , pages=

    A simple framework for contrastive learning of visual representations , author=. International conference on machine learning , pages=. 2020 , organization=

    2020

  35. [35]

    Neural networks , volume=

    Sigmoid-weighted linear units for neural network function approximation in reinforcement learning , author=. Neural networks , volume=. 2018 , publisher=

    2018

  36. [36]

    arXiv preprint arXiv:1903.02428 , year=

    Fast graph representation learning with PyTorch Geometric , author=. arXiv preprint arXiv:1903.02428 , year=

    Pith/arXiv arXiv 1903

  37. [37]

    Molecular systems biology , volume=

    Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega , author=. Molecular systems biology , volume=. 2011 , publisher=

    2011

  38. [38]

    Bioinformatics , volume=

    DLAB: deep learning methods for structure-based virtual screening of antibodies , author=. Bioinformatics , volume=. 2022 , publisher=

    2022

  39. [39]

    Bioinformatics , volume =

    Myung, Yoochan and Pires, Douglas E V and Ascher, David B , title = ". Bioinformatics , volume =. 2021 , month =. doi:10.1093/bioinformatics/btab762 , url =

    work page doi:10.1093/bioinformatics/btab762 2021

  40. [40]

    Machine learning prediction of Antibody-Antigen binding: dataset, method and testing , journal=

    Ye, Chao and Hu, Wenxing and Gaëta, Bruno , year =. Machine learning prediction of Antibody-Antigen binding: dataset, method and testing , journal=

  41. [41]

    Bioinformatics , volume =

    Jain, Tushar and Boland, Todd and Lilov, Asparouh and Burnina, Irina and Brown, Michael and Xu, Yingda and Vásquez, Maximiliano , title = ". Bioinformatics , volume =. 2017 , month =. doi:10.1093/bioinformatics/btx519 , url =

    work page doi:10.1093/bioinformatics/btx519 2017

  42. [42]

    Frontiers in Microbiology , VOLUME=

    Kang, Tae Hyun and Seong, Baik Lin , TITLE=. Frontiers in Microbiology , VOLUME=. 2020 , URL=. doi:10.3389/fmicb.2020.01927 , ISSN=

    work page doi:10.3389/fmicb.2020.01927 2020

  43. [43]

    Antibody apparent solubility prediction from sequence by transfer learning , journal =

    Jiangyan Feng and Min Jiang and James Shih and Qing Chai , keywords =. Antibody apparent solubility prediction from sequence by transfer learning , journal =. 2022 , issn =. doi:https://doi.org/10.1016/j.isci.2022.105173 , url =

    work page doi:10.1016/j.isci.2022.105173 2022

  44. [44]

    Alejandro and Charonis, Spyros and Curtis, Robin and Warwicker, Jim , title =

    Hebditch, Max and Carballo-Amador, M. Alejandro and Charonis, Spyros and Curtis, Robin and Warwicker, Jim , title =. 2017 , journal =. doi:10.1093/bioinformatics/btx345 , url =

    work page doi:10.1093/bioinformatics/btx345 2017

  45. [45]

    Computational and artificial intelligence-based methods for antibody development

    Kim, Jisun and McFee, Matthew and Fang, Qiao and Abdin, Osama and Kim, Philip M. Computational and artificial intelligence-based methods for antibody development. Trends Pharmacol Sci

  46. [46]

    Frontiers in immunology , volume=

    DiscoTope-3.0: improved B-cell epitope prediction using inverse folding latent representations , author=. Frontiers in immunology , volume=. 2024 , publisher=

    2024

  47. [47]

    Antibody Therapeutics , volume =

    Zhang, Weijie and Wang, Hao and Feng, Nan and Li, Yifeng and Gu, Jijie and Wang, Zhuozhi , title = ". Antibody Therapeutics , volume =. 2022 , month =. doi:10.1093/abt/tbac029 , url =

    work page doi:10.1093/abt/tbac029 2022

  48. [48]

    1996 , issn =

    Computational methods for biomolecular docking , journal =. 1996 , issn =. doi:https://doi.org/10.1016/S0959-440X(96)80061-3 , url =

    work page doi:10.1016/s0959-440x(96)80061-3 1996

  49. [49]

    Protein structure prediction

    Deng, Haiyou and Jia, Ya and Zhang, Yang. Protein structure prediction. Int. J. Mod. Phys. B

  50. [50]

    MAbs , volume=

    Antibodies to watch in 2019 , author=. MAbs , volume=. 2019 , organization=

    2019

  51. [51]

    MAbs , volume=

    Phage display and hybridoma generation of antibodies to human CXCR2 yields antibodies with distinct mechanisms and epitopes , author=. MAbs , volume=. 2014 , organization=

    2014

  52. [52]

    Immunology today , volume=

    Antibodies in diagnostics--from immunoassays to protein chips , author=. Immunology today , volume=. 2000 , publisher=

    2000

  53. [53]

    Nature , volume=

    Highly accurate protein structure prediction with AlphaFold , author=. Nature , volume=. 2021 , publisher=

    2021

  54. [54]

    Education, the Responsible and Ethical Use of ChatGPT Towards Lifelong Learning (February 11, 2023) , year=

    Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning , author=. Education, the Responsible and Ethical Use of ChatGPT Towards Lifelong Learning (February 11, 2023) , year=

    2023

  55. [55]

    and Vendruscolo, Michele

    Sormanni, Pietro and Aprile, Francesco A. and Vendruscolo, Michele. Third generation antibody discovery methods: in silico rational design. Chem. Soc. Rev. 2018. doi:10.1039/C8CS00523K

    work page doi:10.1039/c8cs00523k 2018

  56. [56]

    Nucleic acids research , volume=

    PyIgClassify: a database of antibody CDR structural classifications , author=. Nucleic acids research , volume=. 2015 , publisher=

    2015

  57. [57]

    Current Opinion in Structural Biology , volume=

    Advances in computational structure-based antibody design , author=. Current Opinion in Structural Biology , volume=. 2022 , publisher=

    2022

  58. [58]

    Bioinformatics , volume =

    Dai, Bowen and Bailey-Kellogg, Chris , title = ". Bioinformatics , volume =. 2021 , month =

    2021

  59. [59]

    Scientific reports , volume=

    Automation of absolute protein-ligand binding free energy calculations for docking refinement and compound evaluation , author=. Scientific reports , volume=. 2021 , publisher=

    2021

  60. [60]

    bioRxiv , pages=

    Advancing Protein-DNA Binding Site Prediction: Integrating Sequence Models and Machine Learning Classifiers , author=. bioRxiv , pages=. 2023 , publisher=

    2023

  61. [61]

    Current opinion in virology , volume=

    Antibody specific epitope prediction—emergence of a new paradigm , author=. Current opinion in virology , volume=. 2015 , publisher=

    2015

  62. [62]

    2024 , publisher=

    Wang, Chuan and Wang, Jiangyuan and Song, Wenjun and Luo, Guanzheng and Jiang, Taijiao , journal=. 2024 , publisher=

    2024

  63. [63]

    epitope1D: accurate taxonomy-aware

    Silva, Bruna and Ascher, David and Pires, Douglas , journal=. epitope1D: accurate taxonomy-aware. 2023 , publisher=

    2023

  64. [64]

    Bioinformatics , volume=

    Learning context-aware structural representations to predict antigen and antibody binding interfaces , author=. Bioinformatics , volume=. 2020 , publisher=

    2020

  65. [65]

    Liu, Chunan and Denzler, Lilian and Chen, Yihong and Martin, Andrew and Paige, Brooks , journal=

  66. [66]

    A structure-based

    Lu, Shuai and Li, Yuguang and Ma, Qiang and Nan, Xiaofei and Zhang, Shoutao , journal=. A structure-based. 2022 , publisher=

    2022

  67. [67]

    Scientific Reports , volume=

    Prediction of protein--protein interaction using graph neural networks , author=. Scientific Reports , volume=. 2022 , publisher=

    2022

  68. [68]

    Frontiers in immunology , volume=

    SEMA: Antigen B-cell conformational epitope prediction using deep transfer learning , author=. Frontiers in immunology , volume=. 2022 , publisher=

    2022

  69. [69]

    Nucleic Acids Research , volume=

    SEPPA-mAb: spatial epitope prediction of protein antigens for mAbs , author=. Nucleic Acids Research , volume=. 2023 , publisher=

    2023

  70. [70]

    Briefings in bioinformatics , volume=

    Critical review of conformational B-cell epitope prediction methods , author=. Briefings in bioinformatics , volume=. 2023 , publisher=

    2023

  71. [71]

    Nature protocols , volume=

    The ClusPro AbEMap web server for the prediction of antibody epitopes , author=. Nature protocols , volume=. 2023 , publisher=

    2023

  72. [72]

    Journal of Biological Chemistry , volume=

    Cloning and characterization of deoxymugineic acid synthase genes from graminaceous plants , author=. Journal of Biological Chemistry , volume=. 2006 , publisher=

    2006

  73. [73]

    coli , author=

    Small ubiquitin-like modifier protein 3 enhances the solubilization of human bone morphogenetic protein 2 in E. coli , author=. Applied biochemistry and biotechnology , volume=. 2018 , publisher=

    2018

  74. [74]

    Journal of Experimental Botany , volume=

    Paralogs and mutants show that one DMA synthase functions in iron homeostasis in rice , author=. Journal of Experimental Botany , volume=. 2017 , publisher=

    2017

  75. [75]

    , author=

    Effects of MDL 19205 (piroximone), a new cardiotonic agent, on electrophysiological, mechanical, and intracellular ionic characteristics of sheep cardiac tissues. , author=. Journal of cardiovascular pharmacology , volume=

  76. [76]

    Nature communications , volume=

    Histone H4 lysine 20 mono-methylation directly facilitates chromatin openness and promotes transcription of housekeeping genes , author=. Nature communications , volume=. 2021 , publisher=

    2021

  77. [77]

    Nature communications , volume=

    Histone H4K20 methylation mediated chromatin compaction threshold ensures genome integrity by limiting DNA replication licensing , author=. Nature communications , volume=. 2018 , publisher=

    2018

  78. [78]

    Plant molecular biology , volume=

    Iron deficiency regulated OsOPT7 is essential for iron homeostasis in rice , author=. Plant molecular biology , volume=. 2015 , publisher=

    2015

  79. [79]

    Nucleic Acids Research , volume=

    Topokaryotyping demonstrates single cell variability and stress dependent variations in nuclear envelope associated domains , author=. Nucleic Acids Research , volume=. 2018 , publisher=

    2018

  80. [80]

    in vivo biotinylation

    PUB-NChIP—“in vivo biotinylation” approach to study chromatin in proximity to a protein of interest , author=. Genome research , volume=. 2013 , publisher=

    2013

Showing first 80 references.