Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Matters Arising
  • Published:

Reply to: The pitfalls of negative data bias for the T-cell epitope specificity challenge

Nature Machine Intelligence volume 5, pages 1063–1065 (2023)Cite this article

Subjects

The Original Article was published on 05 October 2023

replying to C. Dens et al. Nature Machine Intelligence https://doi.org/10.1038/s42256-023-00727-0 (2023)

In their Matters Arising, Dens et al. highlighted the negative data sampling issue in T-cell epitope specificity prediction1. The negative sampling issue is of general importance in biological data modelling, since biological experiments intend to record positive results and ignore the negative results. We appreciate the efforts from Meysman and colleagues to raise this point for T-cell epitope specificity modelling, as it is known that the choice of negative data sampling strategy influences the prediction results2,3. Therefore, a negative data sampling strategy should be carefully selected, which is what we noticed and emphasized in our original work on PanPep4. There are two commonly used negative sampling strategies: reshuffling based on positive pairs (the first strategy) and randomly drawing from background repertories (the second strategy), and we selected the second for PanPep, as explained in in the original paper4. In reply to Dens et al.1 we would like to further clarify and provide a comprehensive discussion of our negative sampling strategy in peptide–TCR binding prediction from a perspective of positive and unlabelled data learning (PU learning) together with causal language. We advocate more attention to this issue in peptide–TCR binding prediction.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: The confounder illustration from a causal perspective.

Data availability

All data that we used in this manuscript can be found on GitHub (https://github.com/bm2-lab/PanPep) and Zenodo15 (https://doi.org/10.5281/zenodo.7544387).

Code availability

PanPep is available on GitHub (https://github.com/bm2-lab/PanPep) and Zenodo (https://doi.org/10.5281/zenodo.7544387), together with a usage documentation.

References

  1. Dens, C., Laukens, K., Bittremieux, W. & Meysman, P. The pitfalls of negative data bias for the T-cell epitope specificity challenge. Nat. Mach. Intell. https://doi.org/10.1038/s42256-023-00727-0 (2023).

  2. Hudson, D., Fernandes, R. A., Basham, M., Ogg, G. & Koohy, H. Can we predict T cell specificity with digital biology and machine learning? Nat. Rev. Immunol. 23, 511–521 (2023).

  3. Jiang, Y., Huo, M. & Cheng Li, S. TEINet: a deep learning framework for prediction of TCR–epitope binding specificity. Brief. Bioinform. 24, bbad086 (2023).

    Article  Google Scholar 

  4. Gao, Y. et al. Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition. Nat. Mach. Intell. 5, 236–249 (2023).

  5. Pavlović, M. et al. Improving generalization of machine learning-identified biomarkers with causal modeling: an investigation into immune receptor diagnostics. Preprint at https://doi.org/10.48550/arXiv.2204.09291 (2023).

  6. Elkan, C. & Noto, K. Learning classifiers from only positive and unlabeled data. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’08 213–220 (Association for Computing Machinery, 2008).

  7. Ren, J., Liu, Q., Ellis, J. & Li, J. Positive-unlabeled learning for the prediction of conformational B-cell epitopes. BMC Bioinf. 16, S12 (2015).

    Article  Google Scholar 

  8. Hameed, P. N., Verspoor, K., Kusljic, S. & Halgamuge, S. Positive-unlabeled learning for inferring drug interactions based on heterogeneous attributes. BMC Bioinf. 18, 140 (2017).

    Article  Google Scholar 

  9. Lu, T. et al. Deep learning-based prediction of the T cell receptor–antigen binding specificity. Nat. Mach. Intell. 3, 864–875 (2021).

    Article  Google Scholar 

  10. Springer, I., Tickotsky, N. & Louzoun, Y. Contribution of T cell receptor alpha and beta CDR3, MHC typing, V and J genes to peptide binding prediction. Front. Immunol. 12, 664514 (2021).

    Article  Google Scholar 

  11. Luu, A. M., Leistico, J. R., Miller, T., Kim, S. & Song, J. S. Predicting TCR-epitope binding specificity using deep metric learning and multimodal learning. Genes 12, 572 (2021).

    Article  Google Scholar 

  12. Gielis, S. et al. Detection of enriched T cell epitope specificity in full T cell receptor sequence repertoires. Front. Immunol. 10, 2820 (2019).

    Article  Google Scholar 

  13. Pan, S. J. & Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345–1359 (2009).

    Article  Google Scholar 

  14. Wang, M. & Deng, W. Deep visual domain adaptation: a survey. Neurocomputing 312, 135–153 (2018).

    Article  Google Scholar 

  15. Gao, Y., Gao, Y., & Liu, Q. Pan-Peptide Meta learning for T-cell receptor-antigen binding recognition. Zenodo https://doi.org/10.5281/zenodo.7544387 (2023).

Download references

Author information

Author notes

  1. These authors contributed equally: Yicheng Gao, Yuli Gao.

Authors and Affiliations

  1. Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration, Ministry of Education, Orthopaedic Department of Tongji Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai, China

    Yicheng Gao, Yuli Gao, Kejing Dong, Siqi Wu & Qi Liu

  2. Translational Medical Center for Stem Cell Therapy and Institution for Regenerative Medicine, Shanghai East Hospital, Frontier Science Center for Stem Cell Research, Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai, China

    Yicheng Gao, Yuli Gao, Kejing Dong, Siqi Wu & Qi Liu

  3. Research Institute of Intelligent Computing, Hangzhou, China

    Qi Liu

  4. Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai, China

    Qi Liu

Authors
  1. Yicheng Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuli Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kejing Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Siqi Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Q.L., Yicheng Gao and Yuli Gao designed the framework of this work. Yicheng Gao, Yuli Gao, K.D., S.W. performed the analyses. Yicheng Gao, Yuli Gao and Q.L. wrote the manuscript with the help of other authors. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Qi Liu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Geir Kjetil Sandve for his contribution to the peer review of this work. Primary Handling Editor: Liesbeth Venema, in collaboration with the Nature Machine Intelligence team.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 The case of cross-reactivity of TCRs in the zero-dataset.

The histogram depicting the distribution of the number of binding peptides in TCRs in the zero-dataset.

Supplementary information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, Y., Gao, Y., Dong, K. et al. Reply to: The pitfalls of negative data bias for the T-cell epitope specificity challenge. Nat Mach Intell 5, 1063–1065 (2023). https://doi.org/10.1038/s42256-023-00725-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-023-00725-2

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing