Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling

Holmes, E., Wilson, I. D. & Nicholson, J. K. Metabolic phenotyping in health and disease. Cell 134, 714–717 (2008).

Google Scholar 

Nicholson, J. K. Global systems biology, personalized medicine and molecular epidemiology. Mol. Syst. Biol. 2, 52 (2006).

Google Scholar 

Alseekh, S. et al. Mass spectrometry-based metabolomics: a guide for annotation, quantification and best reporting practices. Nat. Methods 18, 747–756 (2021).

Google Scholar 

Julkunen, H. et al. Atlas of plasma NMR biomarkers for health and disease in 118,461 individuals from the UK Biobank. Nat. Commun. 14, 604 (2023).

Google Scholar 

Hu, J. et al. RSPSSL: a novel high-fidelity Raman spectral preprocessing scheme to enhance biomedical applications and chemical resolution visualization. Light Sci. Appl. 13, 52 (2024).

Google Scholar 

He, H. et al. Noise learning of instruments for high-contrast, high-resolution and fast hyperspectral microscopy and nanoscopy. Nat. Commun. 15, 754 (2024).

Google Scholar 

Guo, S., Popp, J. & Bocklitz, T. Chemometric analysis in Raman spectroscopy from experimental design to machine learning–based modeling. Nat. Protoc. 16, 5426–5459 (2021).

Google Scholar 

Felten, J. et al. Vibrational spectroscopic image analysis of biological material using multivariate curve resolution–alternating least squares (MCR-ALS). Nat. Protoc. 10, 217–240 (2015).

Google Scholar 

Bi, X. et al. Molecule-resolvable SERSome for metabolic profiling. Chem https://doi.org/10.1016/j.chempr.2025.102528 (2025).

Su, H. et al. Surface-enhanced Raman spectroscopy study on the structure changes of 4-mercaptophenylboronic acid under different pH conditions. Spectrochim. Acta A Mol. Biomol. Spectrosc. 185, 336–342 (2017).

Google Scholar 

Giese, B. & McNaughton, D. Surface-enhanced Raman spectroscopic study of uracil. The influence of the surface substrate, surface potential, and pH. J. Phys. Chem. B 106, 1461–1470 (2002).

Google Scholar 

Zarei, M. et al. Machine learning analysis of Raman spectra to quantify the organic constituents in complex organic-mineral mixtures. Anal. Chem. 95, 15908–15916 (2023).

Google Scholar 

Koyun, O. C. et al. RamanFormer: a transformer-based quantification approach for raman mixture components. ACS Omega 9, 23241–23251 (2024).

Google Scholar 

Brown, T. et al. Language models are few-shot learners. In Proc. Advances in Neural Information Processing Systems Vol. 33, 1877–1901 (NeurIPS, 2020).

Bi, X., Czajkowsky, D. M., Shao, Z. & Ye, J. Digital colloid-enhanced Raman spectroscopy by single-molecule counting. Nature 628, 771–775 (2024).

Google Scholar 

Luo, Y. et al. Component identification for the SERS spectra of microplastics mixture with convolutional neural network. Sci. Total Environ. 895, 165138 (2023).

Google Scholar 

Bi, X. et al. SERSomes for metabolic phenotyping and prostate cancer diagnosis. Cell Rep. Med. https://doi.org/10.1016/J.XCRM.2024.101579 (2024).

Ye, J. et al. Hypoxanthine is a metabolic biomarker for inducing GSDME-dependent pyroptosis of endothelial cells during ischemic stroke. Theranostics 14, 6071–6087 (2024).

Google Scholar 

Xue, B. Source code for deep spectral component filtering: DSCF_V1 (v1.2). Zenodo https://doi.org/10.5281/zenodo.15013288 (2025).

Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203–211 (2020).

Google Scholar 

Liu, Z. et al. Swin transformer: hierarchical vision transformer using shifted windows. In Proc. IEEE/CVF International Conference on Computer Vision 9992–10002 (IEEE, 2021).

Hughes, C., Gaunt, L., Brown, M., Clarke, N. W. & Gardner, P. Assessment of paraffin removal from prostate FFPE sections using transmission mode FTIR-FPA imaging. Anal. Methods 6, 1028–1035 (2014).

Google Scholar 

Meuse, C. W. & Barker, P. E. Quantitative infrared spectroscopy of formalin-fixed, paraffin-embedded tissue specimens: paraffin wax removal with organic solvents. Appl. Immunohistochem. Mol. Morphol. 17, 547–552 (2009).

Google Scholar 

Nallala, J., Lloyd, G. R. & Stone, N. Evaluation of different tissue de-paraffinization procedures for infrared spectral imaging. Analyst 140, 2369–2375 (2015).

Google Scholar 

De Lima, F. A. et al. Digital de-waxing on FTIR images. Analyst 142, 1358–1370 (2017).

Google Scholar 

Bai, B. et al. Deep learning-enabled virtual histological staining of biological samples. Light Sci. Appl. 12, 57 (2023).

Google Scholar 

Lotfollahi, M., Daeinejad, D., Berisha, S. & Mayerich, D. Digital staining of high-resolution FTIR spectroscopic images. In Proc. 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 973–977 (IEEE, 2018).

Gobinet, C. et al. Automatic identification of paraffin pixels on FTIR images acquired on FFPE human samples. Anal. Chem. 93, 3750–3761 (2021).

Google Scholar 

Bi, X., Fang, Z., Deng, B., Zhou, L. & Ye, J. Ultrahigh Raman-fluorescence dual-enhancement in nanogaps of silver-coated gold nanopetals. Adv. Opt. Mater. 11, 2300188 (2023).

Google Scholar 

Wang, H. P. et al. Recent advances of chemometric calibration methods in modern spectroscopy: algorithms, strategy, and related issues. trends Anal. Chem. 153, 116648 (2022).

Google Scholar 

Zou, Z. et al. A deep learning model for predicting selected organic molecular spectra. Nat. Comput. Sci. 3, 957–964 (2023).

Google Scholar 

Savitzky, A. & Golay, M. J. E. Smoothing and differentiation of data by simplified least squares procedures. Anal. Chem. 36, 1627–1639 (1964).

Google Scholar 

You, L. et al. An exposome atlas of serum reveals the risk of chronic diseases in the Chinese population. Nat. Commun. 15, 2268 (2024).

Google Scholar 

Oh, H. S. H. et al. Organ aging signatures in the plasma proteome track health and disease. Nature 624, 164–172 (2023).

Google Scholar 

Enroth, C. et al. Crystal structures of bovine milk xanthine dehydrogenase and xanthine oxidase: structure-based mechanism of conversion. Proc. Natl Acad. Sci. USA 97, 10723–10728 (2000).

Google Scholar 

Schwedhelm, E. et al. Trimethyllysine, vascular risk factors and outcome in acute ischemic stroke (MARK–STROKE). Amino Acids 53, 555–561 (2021).

Google Scholar 

Farthing, D. E., Farthing, C. A. & Xi, L. Inosine and hypoxanthine as novel biomarkers for cardiac ischemia: from bench to point-of-care. Exp. Biol. Med. 240, 821–831 (2015).

Google Scholar 

Dudka, I. et al. Comprehensive metabolomics analysis of prostate cancer tissue in relation to tumor aggressiveness and TMPRSS2-ERG fusion status. BMC Cancer 20, 437 (2020).

Google Scholar 

Chen, M. M. & Meng, L. H. The double faced role of xanthine oxidoreductase in cancer. Acta Pharmacol. Sin. 43, 1623–1632 (2021).

Google Scholar 

Sreekumar, A. et al. Metabolomic profiles delineate potential role for sarcosine in prostate cancer progression. Nature 457, 910–914 (2009).

Google Scholar 

Clark, D. E. et al. The serine/threonine protein kinase, p90 ribosomal S6 kinase, is an important regulator of prostate cancer cell proliferation. Cancer Res. 65, 3108–3116 (2005).

Google Scholar 

Maitre, M., Klein, C., Patte-Mensah, C. & Mensah-Nyagan, A. G. Tryptophan metabolites modify brain Aβ peptide degradation: a role in Alzheimer’s disease? Prog. Neurobiol. 190, 101800 (2020).

Google Scholar 

Horgan, C. C. et al. High-throughput molecular imaging via deep-learning-enabled Raman spectroscopy. Anal. Chem. 93, 15850–15860 (2021).

Google Scholar 

Ribeiro, M. T., Singh, S. & Guestrin, C. ‘Why should I trust you?’: explaining the predictions of any classifier. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ed. Balaji, K.) 1135–1144 (ACM, 2016).

Radford, A. et al. Language models are unsupervised multitask learners. OpenAI 1, 9 (2019).

Google Scholar 

Liu, B., Yuan, Y., Pan, X., Shen, H-.B. & Jin, C. AttSiOff: a self-attention-based approach on siRNA design with inhibition and off-target effect prediction. Med-X https://doi.org/10.1007/s44258-024-00019-1 (2024).

Leopold, N. & Lendl, B. A new method for fast preparation of highly surface-enhanced raman scattering (SERS) active silver colloids at room temperature by reduction of silver nitrate with hydroxylamine hydrochloride. J. Phys. Chem. B 107, 5723–5727 (2003).

Google Scholar 

Lee, P. C. & Meisel, D. Adsorption and surface-enhanced Raman of dyes on silver and gold sols. J. Phys. Chem. 86, 3391–3395 (1982).

Google Scholar 

Yuan, H. et al. Gold nanostars: surfactant-free synthesis, 3D modelling, and two-photon photoluminescence imaging. Nanotechnology 23, 075102 (2012).

Google Scholar 

Kaur, V., Tanwar, S., Kaur, G. & Sen, T. DNA-origami-based assembly of Au@Ag Nanostar dimer nanoantennas for label-free sensing of pyocyanin. Chem. Phys. Chem. 22, 160–167 (2021).

Google Scholar 

He, K. et al. Masked autoencoders are scalable vision learners. In Proc. IEEE/CVF International Conference on Computer Vision 15979–15988 (IEEE, 2022).

Chau, S. L., Hu, R., London, A., Gonzalez, J. & Sejdinovic, D. RKHS-SHAP: Shapley values for kernel methods. Adv. Neural Inf. Process Syst. 35, 13050–13063 (2022).

Google Scholar 

Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. In Proc. 34th International Conference on Machine Learning Vol. 70 (eds Precup, D. & Teh, Y. W.) 3145–3153 (PMLR, 2017).

Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In Proc. IEEE/CVF International Conference on Computer Vision 618–626 (IEEE, 2017).

Zeiler, M. D. & Fergus, R. Visualizing and understanding convolutional networks. In Proc. European Conference on Computer Vision 818–833 (Springer, 2014).

Lundberg, S. M., Allen, P. G. & Lee, S.-I. A unified approach to interpreting model predictions. In Proc. Advances in Neural Information Processing Systems Vol. 30 (eds Guyon, I. et al.) 4765–4774 (Curran Associates, 2017).

Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. 34th International Conference on Machine Learning (JMLR, 2017).

Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).

Google Scholar 

Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proc. IEEE/CVF International Conference on Computer Vision 2921–2929 (IEEE, 2016).

Xue, B. FTIR of liver tissue. figshare https://doi.org/10.6084/m9.figshare.28107236.v1 (2024).

Xue, B. ComFilE for PCa. figshare https://doi.org/10.6084/m9.figshare.28107395.v1 (2024).

Xue, B. ComFilE for stroke. figshare https://doi.org/10.6084/m9.figshare.28107431.v1 (2024).

Xue, B. ComFilE for AD. figshare https://doi.org/10.6084/m9.figshare.28107578.v1 (2024).

Xue, B. SERS quantification. figshare https://doi.org/10.6084/m9.figshare.28107281.v1 (2024).

Xue, B. SERS nanoparticle background removal (PCa). figshare https://doi.org/10.6084/m9.figshare.28107326.v1 (2024).

Zou, Z. QM9S dataset. figshare https://doi.org/10.6084/m9.figshare.24235333.v3 (2023).