cfDecon: Accurate and Interpretable Methylation-Based Cell Type Deconvolution for Cell-Free DNA (original) (raw)

Abstract

Cell-free DNA (cfDNA) analysis is crucial for noninvasive diagnostics, but computational deconvolution faces data complexity and interpretability challenges. We present cfDecon, a deep-learning framework that uses multichannel autoencoder and iterative refinement to generate condition-aware methylation profiles. Through comprehensive simulations and clinical validations, cfDecon consistently outperforms existing methods and demonstrates superior disease detection capability, offering a promising framework for personalized medicine applications.

Y. Wang and J. Li—These authors make equal contributions.

Similar content being viewed by others

References

  1. Caggiano, C., et al.: Comprehensive cell type decomposition of circulating cell-free DNA with CelFiE. Nat. Commun. 12(1), 2717 (2021)
    Article MathSciNet Google Scholar
  2. Chabon, J.J., et al.: Integrating genomic features for non-invasive early lung cancer detection. Nature 580(7802), 245–251 (2020)
    Article Google Scholar
  3. Chan, K.A., et al.: Noninvasive detection of cancer-associated genome-wide hypomethylation and copy number aberrations by plasma DNA bisulfite sequencing. Proc. Natl. Acad. Sci. 110(47), 18761–18768 (2013)
    Article Google Scholar
  4. De Luca, C., Virtuoso, A., Maggio, N., Papa, M.: Neuro-coagulopathy: blood coagulation factors in central nervous system diseases. Int. J. Mol. Sci. 18(10) (2017). https://doi.org/10.3390/ijms18102128, https://www.mdpi.com/1422-0067/18/10/2128
  5. Kang, S., et al.: CancerLocator: non-invasive cancer diagnosis and tissue-of-origin prediction using methylation profiles of cell-free DNA. Genome Biol. 18, 1–12 (2017)
    Article Google Scholar
  6. Keukeleire, P., Makrodimitris, S., Reinders, M.: Cell type deconvolution of methylated cell-free DNA at the resolution of individual reads. NAR Genom. Bioinform. 5(2), lqad048 (2023)
    Google Scholar
  7. King, P.H.: Skeletal muscle as a molecular and cellular biomarker of disease progression in amyotrophic lateral sclerosis: a narrative review. Neural Regener. Res. 19(4), 747–753 (2024). https://doi.org/10.4103/1673-5374.382226
    Article Google Scholar
  8. Konopka, A., Atkin, J.D.: DNA damage, defective DNA repair, and neurodegeneration in amyotrophic lateral sclerosis. Front. Aging Neurosci. 14 (2022). https://doi.org/10.3389/fnagi.2022.786420
  9. Li, S., et al.: Comprehensive tissue deconvolution of cell-free DNA by deep learning for disease diagnosis and monitoring. Proc. Natl. Acad. Sci. 120(28), e2305236120 (2023)
    Article Google Scholar
  10. Snyder, M.W., Kircher, M., Hill, A.J., Daza, R.M., Shendure, J.: Cell-free DNA comprises an in vivo nucleosome footprint that informs its tissues-of-origin. Cell 164(1), 57–68 (2016)
    Article Google Scholar

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
    Yixuan Wang, Jiayi Li, Xinyuan Liu, Yimin Fan, Irwin King & Yu Li
  2. School of Basic Medical Sciences, Suzhou Medical College, Soochow University, Suzhou, 215123, China
    Jingqi Li, Shen Yang & Yumei Li
  3. School of Biomedical Sciences, The Chinese University of Hong Kong, Hong Kong SAR, China
    Yuhan Huang

Authors

  1. Yixuan Wang
  2. Jiayi Li
  3. Jingqi Li
  4. Shen Yang
  5. Yuhan Huang
  6. Xinyuan Liu
  7. Yimin Fan
  8. Irwin King
  9. Yumei Li
  10. Yu Li

Corresponding authors

Correspondence toYumei Li or Yu Li .

Editor information

Editors and Affiliations

  1. University of California, Los Angeles, CA, USA
    Sriram Sankararaman

Rights and permissions

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Cite this paper

Wang, Y. et al. (2025). cfDecon: Accurate and Interpretable Methylation-Based Cell Type Deconvolution for Cell-Free DNA. In: Sankararaman, S. (eds) Research in Computational Molecular Biology. RECOMB 2025. Lecture Notes in Computer Science(), vol 15647. Springer, Cham. https://doi.org/10.1007/978-3-031-90252-9\_28

Download citation

Keywords

Publish with us