CoChat
Sign Up
Cited by 6Mass Spectrometry Techniques and ApplicationsMetabolomics and Mass Spectrometry StudiesAdvanced Proteomics Techniques and Applications

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Enhancing mass spectrometry imaging accessibility using convolutional autoencoders for deriving hypoxia-associated peptides from tumors

Open access
Bitto, Verena, Hönscheid, Pia, Besso, María José, Sperling, Christian, Kurth, Ina, Baumann, Michael, Brors, Benedikt·2024·npj Systems Biology and Applications
DOI 10.1038/s41540-024-00385-xPMC PMC11130291

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Mass spectrometry imaging (MSI) allows to study cancer’s intratumoral heterogeneity through spatially-resolved peptides, metabolites and lipids. Yet, in biomedical research MSI is rarely used for biomarker discovery. Besides its high dimensionality and multicollinearity, mass spectrometry (MS) technologies typically output mass-to-charge ratio values but not the biochemical compounds of interest. Our framework makes particularly low-abundant signals in MSI more accessible. We utilized convolutional autoencoders to aggregate features associated with tumor hypoxia, a parameter with significant spatial heterogeneity, in cancer xenograft models. We highlight that MSI captures these low-abundant signals and that autoencoders can preserve them in their latent space. The relevance of individual hyperparameters is demonstrated through ablation experiments, and the contribution from original features to latent features is unraveled. Complementing MSI with tandem MS from the same tumor model, multiple hypoxia-associated peptide candidates were derived. Compared to random forests alone, our autoencoder approach yielded more biologically relevant insights for biomarker discovery.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41540-024-00385-x

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 48

  1. Walch, A., Rauser, S., Deininger, S. O. & Höfler, H. MALDI imaging mass spectrometry for direct tissue analysis: a new frontier for molecular histology. Histochem.Cell Biol. 130, 421–434 (2008). · DOI
  2. Jungmann, J. H. & Heeren, R. M. Emerging technologies in mass spectrometry imaging. J. Proteomics 75, 5077–5092 (2012). · DOI
  3. Römpp, A. & Spengler, B. Mass spectrometry imaging with high resolution in mass and space. Histochem. Cell Biol. 139, 759–783 (2013). · DOI
  4. Bressan D., Battistoni G. & Hannon, G. J. The dawn of spatial omics. Science 381, eabq4964 (2023). · DOI
  5. Wang, Y., Miller, D. J. & Clarke, R. Approaches to working in high-dimensional data spaces: gene expression microarrays. Br. J. Cancer 98, 1023–1028 (2008). · DOI
  6. Saeys, Y., Inza, I. & Larrañaga, P. A review of feature selection techniques in bioinformatics. Bioinformatics 23, 2507–2517 (2007). · DOI
  7. Genuer, R., Poggi, J. M. & Tuleau-Malot, C. Variable selection using random forests. Pattern Recognit. Lett. 31, 2225–2236 (2010). · DOI · Paper page
  8. Heidema, A. G. et al. The challenge for genetic epidemiologists: how to analyze large numbers of SNPs in relation to complex diseases. BMC Genet. 7, 1–15 (2006). · DOI
  9. Bank, D., Koenigstein, N. & Giryes, R. Autoencoders. https://doi.org/10.48550/ARXIV.2003.05991 (2020). · DOI
  10. Jones, E. A. et al. Multiple statistical analysis techniques corroborate intratumor heterogeneity in imaging mass spectrometry datasets of myxofibrosarcoma. PLoS ONE 6, e24913 (2011). · DOI
  11. Möginger, U., Marcussen, N. & Jensen, O. N. Histo-molecular differentiation of renal cancer subtypes by mass spectrometry imaging and rapid proteome profiling of formalin-fixed paraffin-embedded tumor tissue sections. Oncotarget 11, 3998–4015 (2020). · DOI
  12. Harris, A. L. Hypoxia — a key regulatory factor in tumour growth. Nat. Rev. Cancer 2, 38–47 (2002). · DOI · Paper page
  13. Chen, Z., Han, F., Du, Y., Shi, H. & Zhou, W. Hypoxic microenvironment in cancer: molecular mechanisms and therapeutic interventions. Signal Transduct.Targeted Ther. 8, 70 (2023). · DOI · Paper page
  14. Toustrup, K. et al. Development of a hypoxia gene expression classifier with predictive impact for hypoxic modification of radiotherapy in head and neck cancer. Cancer Res. 71, 5923–5931 (2011). · DOI
  15. Patil, S. et al. A Novel 2-Metagene signature to identify high-risk HNSCC patients amongst those who are clinically at intermediate risk and are treated with PORT. Cancers 14, 3031 (2022). · DOI
  16. Thomas, S. A., Race, A. M., Steven, R. T., Gilmore, I. S. & Bunch, J. Dimensionality reduction of mass spectrometry imaging data using autoencoders. In: 2016 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE. https://doi.org/10.1109/ssci.2016.7849863 (2016). · DOI
  17. Inglese, P., Alexander, J. L., Mroz, A., Takats, Z. & Glen, R. Variational autoencoders for tissue heterogeneity exploration from (almost) no preprocessed mass spectrometry imaging data. https://doi.org/10.48550/ARXIV.1708.07012 (2017). · DOI
  18. Abdelmoula, W. M. et al. Peak learning of mass spectrometry imaging data using artificial neural networks. Nat. Commun. 12, 5544 (2021). · DOI
  19. Matsuda, K. & Aoyagi, S. Sparse autoencoder–based feature extraction from TOF–SIMS image data of human skin structures. Anal. Bioanal. Chem. 414, 1177–1186 (2022). · DOI
  20. Li, Y., Gan, Z., Zhou, X. & Chen, Z. Accurate classification of Listeria species by MALDI-TOF mass spectrometry incorporating denoising autoencoder and machine learning. J. Microbiol. Methods 192, 106378 (2022). · DOI
  21. Thomas, S. A., Jin, Y., Bunch, J. & Gilmore, I. S. Enhancing classification of mass spectrometry imaging data with deep neural networks. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE. https://doi.org/10.1109/ssci.2017.8285223 (2017). · DOI
  22. Abdelmoula, W. M. et al. massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation. Bioinformatics 38, 2015–2021 (2022). · DOI
  23. Zou, J. et al. A primer on deep learning in genomics. Nat. Genet. 51, 12–18 (2018). · DOI · Paper page
  24. Hoffmann, F. et al. Identification of proteomic markers in head and neck cancer using MALDI–MS imaging, LC–MS/MS, and immunohistochemistry. PROTEOMICS – Clin. Appl. 13, 1700173 (2018). · DOI
  25. Mascini, N. E. et al. Mass spectrometry imaging of the hypoxia marker pimonidazole in a breast tumor model. Anal. Chem. 88, 3107–3114 (2016). · DOI
  26. Maier, S. K. et al. Comprehensive identification of proteins from MALDI imaging. Mol. Cell. Proteomics 12, 2901–2910 (2013). · DOI
  27. Djidja, M. C. et al. Identification of hypoxia-regulated proteins Using MALDI-mass spectrometry imaging combined with quantitative proteomics. J. Proteome Res. 13, 2297–2313 (2014). · DOI
  28. Zhang, Y. A. Better Autoencoder for Image: convolutional Autoencoder. In: Proc. 24th International Conference on Neural Information Processing (ICONIP17-DCEC), Australian National University. https://users.cecs.anu.edu.au/~Tom.Gedeon/conf/ABCs2018/paper/ABCs2018_paper_58.pdf (2018).
  29. Lundberg, S. & Lee, S. I. A Unified Approach to Interpreting Model Predictions. https://doi.org/10.48550/ARXIV. 1705.07874. (2017). · DOI
  30. Aas, K., Jullum, M. & Løland, A. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artif. Intell. 298, 103502 (2021). · DOI
  31. Strobl, C., Boulesteix, A. L., Zeileis, A. & Hothorn, T. Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinform. 8, 1–21 (2007). · DOI
  32. Nicodemus, K. K. & Malley, J. D. Predictor correlation impacts machine learning algorithms: implications for genomic studies. Bioinformatics 25, 1884–1890 (2009). · DOI
  33. Spraggins, J. M. et al. Next-generation technologies for spatial proteomics: Integrating ultra-high speed MALDI-TOF and high mass resolution MALDI FTICR imaging mass spectrometry for protein analysis. PROTEOMICS 16, 1678–1689 (2016). · DOI
  34. Spraggins, J. M. et al. MALDI FTICR IMS of intact proteins: using mass accuracy to link protein images with proteomics data. J. Am. Soc. Mass Spectrom. 26, 974–985 (2015). · DOI
  35. Koi, L. et al. Prognostic biomarkers for the response to the radiosensitizer nimorazole combined with RCTx:a pre-clinical trial in HNSCC xenografts. J. Transl. Med. 21, 576 (2023). · DOI
  36. Ràfols, P. et al. Signal preprocessing, multivariate analysis and software tools for MA(LDI)-TOF mass spectrometry imaging for biological applications. Mass Spectrom. Rev. 37, 281–306 (2016). · DOI
  37. Veselkov, K. et al. BASIS: High-performance bioinformatics platform for processing of large-scale mass spectrometry imaging data in chemically augmented histology. Sci. Rep. 8, 4053 (2018). · DOI
  38. Kingma, D. P. & Welling, M. Auto-Encoding Variational Bayes. https://doi.org/10.48550/ARXIV.1312.6114 (2013). · DOI · Paper page
  39. Shevchenko, A., Tomas, H., Havli, J., Olsen, J. V. & Mann, M. In-gel digestion for mass spectrometric characterization of proteins and proteomes. Nat. Protoc. 1, 2856–2860 (2006). · DOI
  40. Tyanova, S., Temu, T. & Cox, J. The MaxQuant computational platform for mass spectrometry-based shotgun proteomics. Nat. Protoc. 11, 2301–2319 (2016). · DOI
  41. Cox, J. et al. Accurate proteome-wide label-free quantification by delayed normalization and maximal peptide ratio extraction, termed MaxLFQ. Mol. Cell Proteom. 13, 2513–2526 (2014). · DOI · Paper page
  42. Bemis, K. D. et al. Cardinal: an R package for statistical analysis of mass spectrometry-based imaging experiments: Fig. 1. Bioinformatics 31, 2418–2420 (2015). · DOI
  43. Klein, S., Staring, M., Murphy, K., Viergever, M. & Pluim, J. elastix: a Toolbox for intensity-based medical image registration. IEEE Transact. Med. Imaging 29, 196–205 (2010). · DOI · Paper page
  44. Shamonin, D. P. et al. Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease. Front. Neuroinform. 7, 1–15 (2014).
  45. Waskom, M. L. seaborn: statistical data visualization. J. Open Sour. Software 6, 3021 (2021). · DOI · Paper page
  46. Virtanen, P. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261–272 (2020). · DOI · Paper page
  47. Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. B 57, 289–300 (1995). · DOI · Paper page
  48. Perez-Riverol, Y. et al. The PRIDE database resources in 2022: a hub for mass spectrometry-based proteomics evidences. Nucleic Acids Res. 50, D543–D552 (2021). · DOI · Paper page

Metadata

Authors
Bitto, V., Hönscheid, P., Besso, M. J., Sperling, C., Kurth, I., Baumann, M., & Brors, B.
Affiliations
German Cancer Research Center (DE)
Corresponding author
Bitto, Verena
ORCID
Venue
npj Systems Biology and Applications
Publisher
Springer Science and Business Media LLC
Published
2024-05-27
Volume
10
Issue
1
Pages
57-57
ISSN
2056-7189 (ISSN-L)
DOI
10.1038/s41540-024-00385-x
PMC
PMC11130291
OpenAlex
W4399046526
Cited by
6
References
2
Citations by year
2026: 3 · 2025: 3
FWCI
0.75
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Systems Biology and Applications (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
HIDSS4Health – Helmholtz Information and Data Science School for Health
Topics
  • Physical Sciences › Chemistry › Spectroscopy › Mass Spectrometry Techniques and Applications
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Metabolomics and Mass Spectrometry Studies
  • Physical Sciences › Chemistry › Spectroscopy › Advanced Proteomics Techniques and Applications
Keywords
mass spectrometry imaging, convolutional autoencoder, tumor hypoxia, biomarker discovery, intratumoral heterogeneity, tumor xenografts, latent space, tandem mass spectrometry
MeSH terms
Tumor Hypoxia, Animals, Hypoxia, Humans, Neoplasms, Peptides, Mass Spectrometry, Biomarkers, Tumor, Cell Line, Tumor, Mice

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review