Improving generalization of machine learning-identified biomarkers using causal modelling with examples from immune receptor diagnostics | Nature Machine Intelligence
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.

  • Perspective
  • Published:

Improving generalization of machine learning-identified biomarkers using causal modelling with examples from immune receptor diagnostics

Nature Machine Intelligence volume 6, pages 15–24 (2024)Cite this article

Subjects

Abstract

Machine learning is increasingly used to discover diagnostic and prognostic biomarkers from high-dimensional molecular data. However, a variety of factors related to experimental design may affect the ability to learn generalizable and clinically applicable diagnostics. Here we argue that a causal perspective improves the identification of these challenges and formalizes their relation to the robustness and generalization of machine learning-based diagnostics. To make for a concrete discussion, we focus on a specific, recently established high-dimensional biomarker—adaptive immune receptor repertoires (AIRRs). Through simulations, we illustrate how major biological and experimental factors of the AIRR domain may influence the learned biomarkers. In conclusion, we argue that causal modelling improves machine learning-based biomarker robustness by identifying stable relations between variables and guiding the adjustment of the relations and variables that vary between populations.

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

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

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

Fig. 1: Developing an AIRR-based diagnostic.
Fig. 2: Examples of selection bias in causal models.
Fig. 3: The different causal roles HLA can take for different types of immune-related disease.
Fig. 4: Experiments showing immune-state prediction performance under different causal models.
Fig. 5: Batch effects may lead to higher error rates in transcriptomic and AIR settings and might result in classifiers learning spurious signals, especially in the AIR setting.

Similar content being viewed by others

Data availability

All data and results for the analysis presented in the manuscript are openly available on Zenodo at https://zenodo.org/record/7756163 (experiment 1), https://zenodo.org/record/7752837 (experiment 2), https://zenodo.org/record/7752115 (experiment 3, AIRR setting) and https://zenodo.org/record/7727894 (experiment 3, transcriptomic setting).

Code availability

The source code for the experiments is openly available on GitHub at https://github.com/uio-bmi/causalairr.

References

  1. Frazer, K. A., Murray, S. S., Schork, N. J. & Topol, E. J. Human genetic variation and its contribution to complex traits. Nat. Rev. Genet. 10, 241–251 (2009).

    Article  Google Scholar 

  2. Locke, W. J. et al. DNA methylation cancer biomarkers: translation to the clinic. Front. Genet. 10, 1150 (2019).

    Article  Google Scholar 

  3. Byron, S. A., Van Keuren-Jensen, K. R., Engelthaler, D. M., Carpten, J. D. & Craig, D. W. Translating RNA sequencing into clinical diagnostics: opportunities and challenges. Nat. Rev. Genet. 17, 257–271 (2016).

    Article  Google Scholar 

  4. Huang, K., Wu, L. & Yang, Y. Gut microbiota: an emerging biological diagnostic and treatment approach for gastrointestinal diseases. JGH Open 5, 973–975 (2021).

    Article  Google Scholar 

  5. Arnaout, R. A. et al. The future of blood testing is the immunome. Front. Immunol 12, 626793 (2021).

    Article  Google Scholar 

  6. Strimbu, K. & Tavel, J. A. What are biomarkers? Curr. Opin. HIV AIDS 5, 463–466 (2010).

    Article  Google Scholar 

  7. Subbaswamy, A. & Saria, S. From development to deployment: dataset shift, causality and shift-stable models in health AI. Biostatistics 21, 345–352 (2020).

    MathSciNet  Google Scholar 

  8. Castro, D. C., Walker, I. & Glocker, B. Causality matters in medical imaging. Nat. Commun. 11, 3673 (2020).

    Article  Google Scholar 

  9. Whalen, S., Schreiber, J., Noble, W. S. & Pollard, K. S. Navigating the pitfalls of applying machine learning in genomics. Nat. Rev. Genet. 23, 169–181 (2021).

    Article  Google Scholar 

  10. Dockès, J., Varoquaux, G. & Poline, J.-B. Preventing dataset shift from breaking machine-learning biomarkers. GigaScience. 10, giab055 (2021).

    Article  Google Scholar 

  11. Daumé, H. & Marcu, D. Domain adaptation for statistical classifiers. J. Artif. Intell. Res. 26, 101–126 (2006).

    Article  MathSciNet  Google Scholar 

  12. Kouw, W. M. & Loog, M. A review of domain adaptation without target labels. IEEE Trans. Pattern Anal. Mach. Intell. 43, 766–785 (2021).

    Article  Google Scholar 

  13. Wang, J. et al. Generalizing to unseen domains: a survey on domain generalization. IEEE Trans. Knowl. Data Eng. 35, 8052–8072 (2023).

    Google Scholar 

  14. Gulrajani, I. & Lopez-Paz, D. In search of lost domain generalization. Preprint at https://arxiv.org/abs/2007.01434 (2020).

  15. Liu, J. et al. Towards out-of-distribution generalization: a survey. Preprint at https://doi.org/10.48550/arXiv.2108.13624 (2023).

  16. Pearl, J. Causality (Cambridge Univ. Press, 2009); https://doi.org/10.1017/CBO9780511803161

  17. Peters, J., Janzing, D. & Schölkopf, B. Elements of Causal Inference: Foundations and Learning Algorithms (MIT Press, 2017).

  18. Hernán, M. & Robins, J. Causal Inference: What If (Chapman & Hall/CRC, 2020).

    Google Scholar 

  19. Rothenhäusler, D. & Bühlmann, P. Distributionally robust and generalizable inference. Statist. Sci. 38, 527–542 (2023).

    Article  MathSciNet  Google Scholar 

  20. Kaddour, J., Lynch, A., Liu, Q., Kusner, M. J. & Silva, R. Causal machine learning: a survey and open problems. Preprint at https://doi.org/10.48550/arXiv.2206.15475 (2022).

  21. Heinze-Deml, C., Maathuis, M. H. & Meinshausen, N. Causal structure learning. Annu. Rev. Stat. Appl. 5, 371–391 (2018).

    Article  MathSciNet  Google Scholar 

  22. Squires, C. & Uhler, C. Causal structure learning: a combinatorial perspective. Found. Comput. Math. https://doi.org/10.1007/s10208-022-09581-9 (2022).

    Article  Google Scholar 

  23. Peters, J., Bühlmann, P. & Meinshausen, N. Causal inference by using invariant prediction: identification and confidence intervals. J. R. Stat. Soc. B Stat. Methodol. 78, 947–1012 (2016).

    Article  MathSciNet  Google Scholar 

  24. Arjovsky, M., Bottou, L., Gulrajani, I. & Lopez-Paz, D. Invariant risk minimization. Preprint at https://doi.org/10.48550/arXiv.1907.02893 (2020).

  25. Jiang, Y. & Veitch, V. Invariant and transportable representations for anti-causal domain shifts. Adv. Neural Inf. Process Syst. 35, 20782–20794 (2022).

    Google Scholar 

  26. Magliacane, S. et al. Domain adaptation by using causal inference to predict invariant conditional distributions. Adv. Neural Inf. Process Syst. 31, 10846–10856 (2018).

    Google Scholar 

  27. Schölkopf, B. et al. Toward causal representation learning. Proc. IEEE 109, 612–634 (2021).

    Article  Google Scholar 

  28. Cui, P. & Athey, S. Stable learning establishes some common ground between causal inference and machine learning. Nat. Mach. Intell. 4, 110–115 (2022).

    Article  Google Scholar 

  29. Bareinboim, E. & Pearl, J. Causal inference and the data-fusion problem. Proc. Natl Acad. Sci. USA 113, 7345–7352 (2016).

    Article  Google Scholar 

  30. Richens, J. G., Lee, C. M. & Johri, S. Improving the accuracy of medical diagnosis with causal machine learning. Nat. Commun. 11, 3923 (2020).

    Article  Google Scholar 

  31. Prosperi, M. et al. Causal inference and counterfactual prediction in machine learning for actionable healthcare. Nat. Mach. Intell. 2, 369–375 (2020).

    Article  Google Scholar 

  32. Raita, Y., Camargo, C. A., Liang, L. & Hasegawa, K. Big data, data science and causal inference: a primer for clinicians. Front. Med. 8, 678047 (2021).

    Article  Google Scholar 

  33. Schölkopf, B. et al. On causal and anticausal learning. In Proc. 29th International Conference on Machine Learning 459–466 (Omnipress, 2012).

  34. Greiff, V., Yaari, G. & Cowell, L. Mining adaptive immune receptor repertoires for biological and clinical information using machine learning. Curr. Opin. Syst. Biol. https://doi.org/10.1016/j.coisb.2020.10.010 (2020).

    Article  Google Scholar 

  35. Emerson, R. O. et al. Immunosequencing identifies signatures of cytomegalovirus exposure history and HLA-mediated effects on the T cell repertoire. Nat. Genet. 49, 659–665 (2017).

    Article  Google Scholar 

  36. Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G. & King, D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 17, 195 (2019).

    Article  Google Scholar 

  37. Britanova, O. V. et al. Age-related decrease in TCR repertoire diversity measured with deep and normalized sequence profiling. J. Immunol. 192, 2689–2698 (2014).

    Article  Google Scholar 

  38. Schneider-Hohendorf, T. et al. Sex bias in MHC I-associated shaping of the adaptive immune system. Proc. Natl Acad. Sci. USA 115, 2168–2173 (2018).

    Article  Google Scholar 

  39. Slabodkin, A. et al. Individualized VDJ recombination predisposes the available Ig sequence space. Genome Res. 31, 2209–2224 (2021).

    Article  Google Scholar 

  40. Dendrou, C. A., Petersen, J., Rossjohn, J. & Fugger, L. HLA variation and disease. Nat. Rev. Immunol. 18, 325–339 (2018).

    Article  Google Scholar 

  41. Ishigaki, K. et al. HLA autoimmune risk alleles restrict the hypervariable region of T cell receptors. Nat. Genet. 54, 393–402 (2022).

    Article  Google Scholar 

  42. Barennes, P. et al. Benchmarking of T cell receptor repertoire profiling methods reveals large systematic biases. Nat. Biotechnol. 39, 236–245 (2021).

    Article  Google Scholar 

  43. Trück, J. et al. Biological controls for standardization and interpretation of adaptive immune receptor repertoire profiling. eLife 10, e66274 (2021).

    Article  Google Scholar 

  44. Smirnova, A. O. et al. The use of non-functional clonotypes as a natural calibrator for quantitative bias correction in adaptive immune receptor repertoire profiling. eLife 12, e69157 (2023).

    Article  Google Scholar 

  45. Krishna, C., Chowell, D., Gönen, M., Elhanati, Y. & Chan, T. A. Genetic and environmental determinants of human TCR repertoire diversity. Immun. Ageing 17, 26 (2020).

    Article  Google Scholar 

  46. Klein, S. L. & Flanagan, K. L. Sex differences in immune responses. Nat. Rev. Immunol. 16, 626–638 (2016).

    Article  Google Scholar 

  47. Castelo-Branco, C. & Soveral, I. The immune system and aging: a review. Gynecol. Endocrinol. 30, 16–22 (2014).

    Article  Google Scholar 

  48. Hernán, M. A., Hsu, J. & Healy, B. A second chance to get causal inference right: a classification of data science tasks. Chance 32, 42–49 (2019).

    Article  Google Scholar 

  49. Blaas, A., Miller, A., Zappella, L., Jacobsen, J.-H. & Heinze-Deml, C. Considerations for distribution shift robustness in health. In Proc. Machine Learning for Healthcare Workshop (ICLR, 2023).

  50. Leek, J. T. et al. Tackling the widespread and critical impact of batch effects in high-throughput data. Nat. Rev. Genet. 11, 733–739 (2010).

    Article  Google Scholar 

  51. Bonaguro, L. et al. A guide to systems-level immunomics. Nat. Immunol. 23, 1412–1423 (2022).

    Article  Google Scholar 

  52. Bareinboim, E. & Pearl, J. Controlling selection bias in causal inference. In Proc. 15th International Conference on Artificial Intelligence and Statistics Vol. 22 (eds Lawrence, N. et al.), 100–108 (PMLR, 2012).

  53. Correa, J., Tian, J. & Bareinboim, E. Generalized adjustment under confounding and selection biases. In Proc. 32nd AAAI Conference on Artificial Intelligence Vol. 32, 6335–6342 (AAAI, 2018).

  54. Laubach, Z. M., Murray, E. J., Hoke, K. L., Safran, R. J. & Perng, W. A biologist’s guide to model selection and causal inference. Proc. R. Soc. B Biol. Sci. 288, 20202815 (2021).

    Article  Google Scholar 

  55. Hernán, M. A., Hernández-Díaz, S. & Robins, J. M. A structural approach to selection bias. Epidemiology 15, 615–625 (2004).

    Article  Google Scholar 

  56. Zhang, K., Schölkopf, B., Muandet, K. & Wang, Z. Domain adaptation under target and conditional shift. In Proc. International Conference on Machine Learning 28 (eds Dasgupta, S. et al.) 819–827 (PMLR, 2013).

  57. Garg, S., Wu, Y., Balakrishnan, S. & Lipton, Z. C. A unified view of label shift estimation. Adv. Neural Inf. Proc. Syst. 33, 3290–3300 (2020).

    Google Scholar 

  58. Pearl, J. & Bareinboim, E. External validity: from Do-calculus to transportability across populations. Stat. Sci. 29, 579–595 (2014).

    Article  MathSciNet  Google Scholar 

  59. Degtiar, I. & Rose, S. A review of generalizability and transportability. Annu. Rev. Stat. Appl. 10, 501–524 (2023).

    Article  MathSciNet  Google Scholar 

  60. Sharon, E. et al. Genetic variation in MHC proteins is associated with T cell receptor expression biases. Nat. Genet. 48, 995–1002 (2016).

    Article  Google Scholar 

  61. Jabri, B. & Sollid, L. M. T cells in Celiac disease. J. Immunol. 198, 3005–3014 (2017).

    Article  Google Scholar 

  62. Schaafsma, E., Fugle, C. M., Wang, X. & Cheng, C. Pan-cancer association of HLA gene expression with cancer prognosis and immunotherapy efficacy. Br. J. Cancer 125, 422–432 (2021).

    Article  Google Scholar 

  63. Rappazzo, C. G. et al. Defining and studying B cell receptor and TCR interactions. J. Immunol. 211, 311–322 (2023).

    Article  Google Scholar 

  64. Hendrycks, D., Lee, K. & Mazeika, M. Using pre-training can improve model robustness and uncertainty. In Proc. 36th International Conference on Machine Learning (eds Chaudhuri, K. et al.) 2712–2721 (PMLR, 2019).

  65. Pradier, M. F. et al. AIRIVA: a deep generative model of adaptive immune repertoires. Preprint at https://doi.org/10.48550/arXiv.2304.13737 (2023).

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

    Article  Google Scholar 

  67. Ostrovsky-Berman, M., Frankel, B., Polak, P. & Yaari, G. Immune2vec: embedding B/T cell receptor sequences in ℝN using natural language processing. Front. Immunol. 12, 680687 (2021).

    Article  Google Scholar 

  68. Fang, Y., Liu, X. & Liu, H. Attention-aware contrastive learning for predicting T cell receptor–antigen binding specificity. Brief. Bioinform. 23, bbac378 (2022).

    Article  Google Scholar 

  69. Gupta, G., Kapila, R., Gupta, K. & Raskar, R. Domain generalization in robust invariant representation. Preprint at https://doi.org/10.48550/arXiv.2304.03431 (2023).

  70. Zhang, J. & Bottou, L. Learning useful representations for shifting tasks and distributions. In Proc. 40th International Conference on Machine Learning (eds Krause, A et al.), 40830–40850 (PMLR, 2023).

  71. Walsh, I. et al. DOME: recommendations for supervised machine learning validation in biology. Nat. Methods 18, 1122–1127 (2021).

    Article  Google Scholar 

  72. Wiles, O. et al. A fine-grained analysis on distribution shift. Preprint at https://arxiv.org/abs/2110.11328 (2021).

  73. Byrd, J. & Lipton, Z. What is the effect of importance weighting in deep learning? In Proc. 36th International Conference on Machine Learning (eds Chaudhuri, K. et al.) 872–881 (PMLR, 2019).

  74. Rubelt, F. et al. Adaptive Immune Receptor Repertoire Community recommendations for sharing immune-repertoire sequencing data. Nat. Immunol. 18, 1274–1278 (2017).

    Article  Google Scholar 

  75. Vander Heiden, J. A. et al. AIRR community standardized representations for annotated immune repertoires. Front. Immunol. 9, 2206 (2018).

    Article  Google Scholar 

  76. Peng, K. et al. Diversity in immunogenomics: the value and the challenge. Nat. Methods 18, 588–591 (2021).

    Article  Google Scholar 

  77. Huang, Y.-N. et al. Ancestral diversity is limited in published T cell receptor sequencing studies. Immunity 54, 2177–2179 (2021).

    Article  Google Scholar 

  78. Registered Reports (Center for Open Science); https://www.cos.io/initiatives/registered-reports

  79. DeWitt, W. S. III et al. Human T cell receptor occurrence patterns encode immune history, genetic background and receptor specificity. eLife 7, e38358 (2018).

    Article  MathSciNet  Google Scholar 

  80. Zaslavsky, M. E. et al. Disease diagnostics using machine learning of immune receptors. Preprint at bioRxiv https://doi.org/10.1101/2022.04.26.489314 (2023).

  81. Langenberg, C., Hingorani, A. D. & Whitty, C. J. M. Biological and functional multimorbidity—from mechanisms to management. Nat. Med. 29, 1649–1657 (2023).

    Article  Google Scholar 

  82. Bongers, S., Forré, P., Peters, J. & Mooij, J. M. Foundations of structural causal models with cycles and latent variables. Ann. Stat. 49, 2885–2915 (2021).

    Article  MathSciNet  Google Scholar 

  83. Chakraborty, B. & Murphy, S. A. Dynamic treatment regimes. Annu. Rev. Stat. Appl. 1, 447–464 (2014).

    Article  Google Scholar 

  84. Bizzarri, M. et al. A call for a better understanding of causation in cell biology. Nat. Rev. Mol. Cell Biol. 20, 261–262 (2019).

    Article  Google Scholar 

  85. Baron, R. M. & Kenny, D. A. The moderator–mediator variable distinction in social psychological research: conceptual, strategic and statistical considerations. J. Pers. Soc. Psychol. 51, 1173–1182 (1986).

    Article  Google Scholar 

  86. Greiff, V., Miho, E., Menzel, U. & Reddy, S. T. Bioinformatic and statistical analysis of adaptive immune repertoires. Trends Immunol. 36, 738–749 (2015).

    Article  Google Scholar 

  87. Nikolich-Žugich, J., Slifka, M. K. & Messaoudi, I. The many important facets of T-cell repertoire diversity. Nat. Rev. Immunol. 4, 123–132 (2004).

    Article  Google Scholar 

  88. Zarnitsyna, V., Evavold, B., Schoettle, L., Blattman, J. & Antia, R. Estimating the diversity, completeness, and cross-reactivity of the T cell repertoire. Front. Immunol. 4, 485 (2013).

    Article  Google Scholar 

  89. Murugan, A., Mora, T., Walczak, A. M. & Callan, C. G. Statistical inference of the generation probability of T-cell receptors from sequence repertoires. Proc. Natl Acad. Sci. USA 109, 16161–16166 (2012).

    Article  Google Scholar 

  90. Tonegawa, S. Somatic generation of antibody diversity. Nature 302, 575–581 (1983).

    Article  Google Scholar 

  91. Weinstein, J. A., Jiang, N., White, R. A., Fisher, D. S. & Quake, S. R. High-throughput sequencing of the zebrafish antibody repertoire. Science 324, 807–810 (2009).

    Article  Google Scholar 

  92. Xu, J. L. & Davis, M. M. Diversity in the CDR3 region of VH is sufficient for most antibody specificities. Immunity 13, 37–45 (2000).

    Article  Google Scholar 

  93. Davis, M. M. & Bjorkman, P. J. T-cell antigen receptor genes and T-cell recognition. Nature 334, 395–402 (1988).

    Article  Google Scholar 

  94. Brown, A. J. et al. Augmenting adaptive immunity: progress and challenges in the quantitative engineering and analysis of adaptive immune receptor repertoires. Mol. Syst. Des. Eng. 4, 701–736 (2019).

    Article  Google Scholar 

  95. Qi, Q. et al. Diversity and clonal selection in the human T-cell repertoire. Proc. Natl Acad. Sci. USA 111, 13139–13144 (2014).

    Article  Google Scholar 

  96. Elhanati, Y. et al. Inferring processes underlying B-cell repertoire diversity. Philos. Trans. R. Soc. Lond. B. Biol. Sci. 370, 20140243 (2015).

    Article  Google Scholar 

  97. Greiff, V. et al. A bioinformatic framework for immune repertoire diversity profiling enables detection of immunological status. Genome Med. 7, 49 (2015).

    Article  Google Scholar 

  98. Elhanati, Y., Sethna, Z., Callan, C. G. Jr, Mora, T. & Walczak, A. M. Predicting the spectrum of TCR repertoire sharing with a data-driven model of recombination. Immunol. Rev. 284, 167–179 (2018).

    Article  Google Scholar 

  99. Varoquaux, G. & Cheplygina, V. Machine learning for medical imaging: methodological failures and recommendations for the future. Npj Digit. Med. 5, 48 (2022).

    Article  Google Scholar 

  100. Ben-David, S. et al. A theory of learning from different domains. Mach. Learn. 79, 151–175 (2010).

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgements

We acknowledge generous support by The Leona M. and Harry B. Helmsley Charitable Trust (grant no. 2019PG-T1D011 to V.G.), the UiO World-Leading Research Community (to V.G. and L.M.S.), the UiO:LifeScience Convergence Environment Immunolingo (to V.G. and G.K.S.), the UiO:LifeScience Convergence Environment RealArt (to G.K.S. and C.K.), EU Horizon 2020 iReceptorplus (grant no. 825821 to V.G. and L.M.S.), a Research Council of Norway FRIPRO project (grant no. 300740 to V.G.), a Norwegian Cancer Society Grant (215817 to V.G.), a Research Council of Norway IKTPLUSS project (grant no. 311341 to V.G. and G.K.S.) and Stiftelsen Kristian Gerhard Jebsen (K.G. Jebsen Coeliac Disease Research Centre, to L.M.S. and G.K.S.).

Author information

Authors and Affiliations

  1. Centre for Bioinformatics, Department of Informatics, University of Oslo, Oslo, Norway

    Milena Pavlović, Ghadi S. Al Hajj, Chakravarthi Kanduri & Geir K. Sandve

  2. K.G. Jebsen Centre for Coeliac Disease Research, Institute of Clinical Medicine, University of Oslo, Oslo, Norway

    Milena Pavlović, Ludvig M. Sollid & Geir K. Sandve

  3. UiO:RealArt Convergence Environment, University of Oslo, Oslo, Norway

    Milena Pavlović, Chakravarthi Kanduri & Geir K. Sandve

  4. Department of Mathematics, University of Oslo, Oslo, Norway

    Johan Pensar

  5. Department of Pharmacy, University of Oslo, Oslo, Norway

    Mollie E. Wood

  6. Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Mollie E. Wood

  7. Department of Immunology, University of Oslo and Oslo University Hospital, Oslo, Norway

    Ludvig M. Sollid & Victor Greiff

Authors
  1. Milena Pavlović
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ghadi S. Al Hajj
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Chakravarthi Kanduri
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Johan Pensar
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Mollie E. Wood
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Ludvig M. Sollid
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Victor Greiff
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Geir K. Sandve
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

M.P., V.G. and G.K.S. conceived the study. M.P., G.S.A.H. and C.K. performed the experiments. J.P., M.E.W., L.M.S., C.K. and G.S.A.H. provided critical feedback. M.P., V.G. and G.K.S. drafted the manuscript. G.K.S. supervised the project. All authors read and approved the final manuscript and are personally accountable for its content.

Corresponding authors

Correspondence to Milena Pavlović or Geir K. Sandve.

Ethics declarations

Competing interests

V.G. declares advisory board positions in aiNET GmbH, Enpicom BV, Absci, Omniscope and Diagonal Therapeutics. V.G. is a consultant for Adaptyv Biosystems, Specifica Inc., Roche/Genentech, immunai and LabGenius. The remaining authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Anna Susmelj and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

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

Supplementary information

Supplementary Information

Supplementary text with details for experiments.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pavlović, M., Al Hajj, G.S., Kanduri, C. et al. Improving generalization of machine learning-identified biomarkers using causal modelling with examples from immune receptor diagnostics. Nat Mach Intell 6, 15–24 (2024). https://doi.org/10.1038/s42256-023-00781-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-023-00781-8

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research