Identification of the Raman Salivary Fingerprint of Parkinson's Disease Through the Spectroscopic- Computational Combinatory Approach

Cristiano Carlomagno, Dario Bertazioli, Alice Gualerzi, Silvia Picciolini, Michele Andrico, Francesca Rodà, Mario Meloni, Paolo Innocente Banfi, Federico Verde, Nicola Ticozzi, Vincenzo Silani, Enza Messina, Marzia Bedoni, Cristiano Carlomagno, Dario Bertazioli, Alice Gualerzi, Silvia Picciolini, Michele Andrico, Francesca Rodà, Mario Meloni, Paolo Innocente Banfi, Federico Verde, Nicola Ticozzi, Vincenzo Silani, Enza Messina, Marzia Bedoni

Abstract

Despite the wide range of proposed biomarkers for Parkinson's disease (PD), there are no specific molecules or signals able to early and uniquely identify the pathology onset, progression and stratification. Saliva is a complex biofluid, containing a wide range of biological molecules shared with blood and cerebrospinal fluid. By means of an optimized Raman spectroscopy procedure, the salivary Raman signature of PD can be characterized and used to create a classification model. Raman analysis was applied to collect the global signal from the saliva of 23 PD patients and related pathological and healthy controls. The acquired spectra were computed using machine and deep learning approaches. The Raman database was used to create a classification model able to discriminate each spectrum to the correct belonging group, with accuracy, specificity, and sensitivity of more than 97% for the single spectra attribution. Similarly, each patient was correctly assigned with discriminatory power of more than 90%. Moreover, the extracted data were significantly correlated with clinical data used nowadays for the PD diagnosis and monitoring. The preliminary data reported highlight the potentialities of the proposed methodology that, once validated in larger cohorts and with multi-centered studies, could represent an innovative minimally invasive and accurate procedure to determine the PD onset, progression and to monitor therapies and rehabilitation efficacy.

Keywords: Parkinson’s disease; Raman spectroscopy; classification model; deep learning; saliva.

Conflict of interest statement

VS received compensation for consulting services and/or speaking activities from AveXis, Cytokinetics, Italfarmaco, and Zambon. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2021 Carlomagno, Bertazioli, Gualerzi, Picciolini, Andrico, Rodà, Meloni, Banfi, Verde, Ticozzi, Silani, Messina and Bedoni.

Figures

FIGURE 1
FIGURE 1
Average Raman signal obtained from the collected CTRL salivary samples (n = 33). Black arrows indicate the identified peaks. The gray band represents the standard deviation.
FIGURE 2
FIGURE 2
Average salivary Raman spectra of the (A) CTRL (n = 33), (B) PD (n = 23), and (C) AD (n = 10) experimental groups. The gray bands represent the associated standard deviations. (D) Overlapped average Raman spectra of the three analyzed groups.
FIGURE 3
FIGURE 3
Subtraction Raman spectra of (A) the average CTRL versus the average PD signals, (B) the average CTRL versus the average AD signals, and (C) the average PD versus the average AD signals.
FIGURE 4
FIGURE 4
(A) Principal component analysis (PCA) in three axis distribution (X = PC1; Z = PC2; Y = PC3), covering the 45.83% of the loadings. Linear discriminant analysis (LDA) and spatial distribution of (B) the Canonical Variables 1 and 2 and (C) box plot of values of the Canonical Variable 1 with the statistical groups including CTRL (n = 33), PD (n = 23), and AD (n = 10). ***p < 0.001, one-way ANOVA test. (D) Receiver operating characteristic (ROC) curve with the relative confidence interval (97–99%).
FIGURE 5
FIGURE 5
Graphic representation of the best 1D-CNN model configuration obtained through the hyper-parameters optimization process.
FIGURE 6
FIGURE 6
Confusion matrices obtained in LOPOCV by the proposed CNN. (A) Spectra-level and (B) patient-level.
FIGURE 7
FIGURE 7
Heat map representing the partial correlation (Pearson’s coefficients) with the relative significance of Canonical Variables 1 and 2 (CV1 and CV2) and Principal Components 1, 2, and 3 (PC1, PC2, and PC3) correlated with levodopa equivalent daily doses (LEDD), Hoehn and Yahr (H&Y) stages and Unified Parkinson’s Disease Rating Scale (UPDRS) motor scales (III). Age, sex, and behavioral parameters were used as control covariates for the partial correlation. *p < 0.05, **p < 0.01, and ***p < 0.001, Pearson’s test.

References

    1. Aarsland D., Bronnick K., Williams-Gray C., Weintraub D., Marder K., Kulisevsky J., et al. (2010). Mild cognitive impairment in Parkinson disease: a multicenter pooled analysis. Neurology 75 1062–1069. 10.1212/wnl.0b013e3181f39d0e
    1. Akiba T., Sano S., Yanase T., Ohta T., Koyama M. (2019). “Optuna,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2623–2631. 10.1145/3292500.3330701
    1. Alakwaa F. M., Chaudhary K., Garmire L. X. (2018). Deep learning accurately predicts estrogen receptor status in breast cancer metabolomics data. J. Proteome Res. 17 337–347. 10.1021/acs.jproteome.7b00595
    1. Albert M. S., DeKosky S. T., Dickson D., Dubois B., Feldman H. H., Fox N. C., et al. (2011). The diagnosis of mild cognitive impairment due to Alzheimer’s disease: recommendations from the national institute on aging-Alzheimer’s association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s Dement. 7 270–279.
    1. Al-Nimer M. S. M., Mshatat S. F., Abdulla H. I. (2014). Saliva α-synuclein and a high extinction coeffi cient protein: A novel approach in assessment biomarkers of parkinson’s disease. N. Am. J. Med. Sci. 6 633–637. 10.4103/1947-2714.147980
    1. Andreou C., Hoonejani M. R., Barmi M. R., Moskovits M., Meinhart C. D. (2013). Rapid detection of drugs of abuse in saliva using surface enhanced raman spectroscopy and microfluidics. ACS Nano. 7 7157–7164. 10.1021/nn402563f
    1. Bäckström D. C., Eriksson Domellöf M., Linder J., Olsson B., Öhrfelt A., Trupp M., et al. (2015). Cerebrospinal fluid patterns and the risk of future dementia in early, incident parkinson disease. JAMA Neurol. 72:1175. 10.1001/jamaneurol.2015.1449
    1. Berg D. (2008). Biomarkers for the early detection of Parkinson’s and Alzheimer’s disease. Neurodegener. Dis. 5 133–136.
    1. Boller F., Mizutani T., Roessmann U., Gambetti P. (1980). Parkinson disease, dementia, and alzheimer disease: clinicopathological correlations. Ann. Neurol. 7 329–335. 10.1002/ana.410070408
    1. Bougea A., Koros C., Stefanis L. (2019). Salivary alpha-synuclein as a biomarker for Parkinson’s disease: a systematic review. J. Neural Transm. 126 1373–1382. 10.1007/s00702-019-02062-4
    1. Braak H., Del Tredici K., Rüb U., de Vos R. A. I., Jansen Steur E. N. H., Braak E. (2003). Staging of brain pathology related to sporadic Parkinson’s disease. Neurobiol. Aging 24 197–211. 10.1016/s0197-4580(02)00065-9
    1. Carlomagno C., Cabinio M., Picciolini S., Gualerzi A., Baglio F., Bedoni M. (2020b). SERS−based biosensor for Alzheimer disease evaluation through the fast analysis of human serum. J. Biophotonics 13:e201960033. 10.1002/jbio.201960033
    1. Carlomagno C., Banfi P. I., Gualerzi A., Picciolini S., Volpato E., Meloni M., et al. (2020a). Human salivary Raman fingerprint as biomarker for the diagnosis of amyotrophic lateral sclerosis. Sci. Rep. 10:10175.
    1. Carlomagno C., Bertazioli D., Gualerzi A., Picciolini S., Banfi P. I., Lax A., et al. (2021a). COVID-19 salivary Raman fingerprint: innovative approach for the detection of current and past SARS-CoV-2 infections. Sci. Rep. 11 :4943.
    1. Carlomagno C., Gualerzi A., Picciolini S., Rodà F., Banfi P. I., Lax A., et al. (2021b). Characterization of the COPD salivary fingerprint through surface enhanced Raman Spectroscopy: a pilot study. Diagnostics 11 :508. 10.3390/diagnostics11030508
    1. Chalimoniuk M., Snoek G. T., Adamczyk A., Małecki A., Strosznajder J. B. (2006). Phosphatidylinositol transfer protein expression altered by aging and parkinson disease. Cell. Mol. Neurobiol. 26 1151–1164. 10.1007/s10571-006-9078-0
    1. Chatzidakis M., Botton G. A. (2019). Towards calibration-invariant spectroscopy using deep learning. Sci. Rep. 9:2126.
    1. Davie C. A. (2008). A review of Parkinson’s disease. Br. Med. Bull. 86 109–127.
    1. Devic I., Hwang H., Edgar J. S., Izutsu K., Presland R., Pan C., et al. (2011). Salivary α-synuclein and DJ-1: potential biomarkers for Parkinson’s disease. Brain 134:e178. 10.1093/brain/awr015
    1. Devitt G., Howard K., Mudher A., Mahajan S. (2018). Raman spectroscopy: an emerging tool in neurodegenerative disease research and diagnosis. ACS Chem. Neurosci. 9 404–420. 10.1021/acschemneuro.7b00413
    1. Díez−Pastor J. F., Jorge−Villar S. E., Arnaiz−González Á, García−Osorio C. I., Díaz−Acha Y., Campeny M., et al. (2020). Machine learning algorithms applied to Raman spectra for the identification of variscite originating from the mining complex of Gavà. J. Raman Spectrosc. 51 1563–1574.
    1. Eraslan G., Avsec Ž, Gagneur J., Theis F. J. (2019). Deep learning: new computational modelling techniques for genomics. Nat. Rev. Genet. 20 389–403. 10.1038/s41576-019-0122-6
    1. Eusebi P., Giannandrea D., Biscetti L., Abraha I., Chiasserini D., Orso M., et al. (2017). Diagnostic utility of cerebrospinal fluid α-synuclein in Parkinson’s disease: a systematic review and meta-analysis. Mov. Disord. 32 1389–1400. 10.1002/mds.27110
    1. Farquharson S., Shende C., Inscore F. E., Maksymiuk P., Gift A. (2005). Analysis of 5-fluorouracil in saliva using surface-enhanced Raman spectroscopy. J. Raman Spectrosc. 36 208–212. 10.1002/jrs.1277
    1. Feng S., Huang S., Lin D., Chen G., Xu Y., Li Y., et al. (2015). Surface-enhanced Raman spectroscopy of saliva proteins for the noninvasive differentiation of benign and malignant breast tumors. Int. J. Nanomedicine 10:537. 10.2147/ijn.s71811
    1. Feurer M., Hutter F. (2019). “Hyperparameter optimization,” in Automated Machine Learning. The Springer Series on Challenges in Machine Learning, eds Hutter F., Kotthoff L., Vanschoren J. (Cham: Springer; ). 10.1007/978-3-030-05318-5_1
    1. Gao L., Tang H., Nie K., Wang L., Zhao J., Gan R., et al. (2015). Cerebrospinal fluid alpha-synuclein as a biomarker for Parkinson’s disease diagnosis: a systematic review and meta-analysis. Int. J. Neurosci. 125 645–654. 10.3109/00207454.2014.961454
    1. Gautam R., Vanga S., Ariese F., Umapathy S. (2015). Review of multidimensional data processing approaches for Raman and infrared spectroscopy. EPJ Tech. Instrum. 2:8.
    1. Gelb D. J., Oliver E., Gilman S. (1999). Diagnostic criteria for parkinson disease. Arch. Neurol. 56:33. 10.1001/archneur.56.1.33
    1. GitHubkeras-team/keras. (2021). Deep Learning for Humans. Available online at: .
    1. Gonchukov S., Sukhinina A., Bakhmutov D., Minaeva S. (2012). Raman spectroscopy of saliva as a perspective method for periodontitis diagnostics. Laser Phys. Lett. 9 73–77. 10.1002/lapl.201110095
    1. Gualerzi A., Picciolini S., Carlomagno C., Terenzi F., Ramat S., Sorbi S., et al. (2019). Raman profiling of circulating extracellular vesicles for the stratification of Parkinson’s patients. Nanomed. Nanotechnol. Biol. Med. 22:102097. 10.1016/j.nano.2019.102097
    1. Guo S., Beleites C., Neugebauer U., Abalde-Cela S., Afseth N. K., Alsamad F., et al. (2020). Comparability of Raman spectroscopic configurations: a large scale cross-laboratory study. Anal. Chem. 92 15745–15756.
    1. Head T., MechCoder, Louppe G., Shcherbatyi I., fcharras, Vinícius Z., et al. (2018). scikit-optimize/scikit-optimize: v0.5rc1. 10.5281/ZENODO.1157320
    1. Ho C.-S., Jean N., Hogan C. A., Blackmon L., Jeffrey S. S., Holodniy M., et al. (2019). Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning. Nat. Commun. 10:4927. 10.1038/s41467-019-12898-9
    1. Huang C.-M. (2004). Comparative proteomic analysis of human whole saliva. Arch. Oral Biol. 49 951–962. 10.1016/j.archoralbio.2004.06.003
    1. Hutter F., Hoos H. H., Leyton-Brown K. (2011). “Sequential model-based optimization for general algorithm configuration,” in Proceedings of the Conference on Learning and Intelligent Optimizatio, 507–523. 10.1007/978-3-642-25566-3_40
    1. In A., Papers B., Vondrakova J., Michl P., Pazdera J., Pink C. R., et al. (2009). Saliva as a diagnostic medium. Biomed. Pap. Med. Fac. Univ. Palacky Olomouc. Czech Repub. 153 103–110.
    1. Kang W.-Y., Yang Q., Jiang X.-F., Chen W., Zhang L.-Y., Wang X.-Y., et al. (2014). Salivary DJ-1 could be an indicator of Parkinson’s disease progression. Front. Aging Neurosci. 6:102.
    1. Kori M., Aydın B., Unal S., Arga K. Y., Kazan D. (2016). Metabolic biomarkers and neurodegeneration: a pathway enrichment analysis of Alzheimer’s disease, Parkinson’s disease, and amyotrophic lateral sclerosis. Omi. A J. Integr. Biol. 20 645–661. 10.1089/omi.2016.0106
    1. Li X., Yang T., Lin J. (2012). Spectral analysis of human saliva for detection of lung cancer using surface-enhanced Raman spectroscopy. J. Biomed. Opt. 17:037003. 10.1117/1.jbo.17.3.037003
    1. Liang Q., Liu H., Zhang T., Jiang Y., Xing H., Zhang A. H. (2015). Metabolomics-based screening of salivary biomarkers for early diagnosis of Alzheimer’s disease. RSC Adv. 5 96074–96079. 10.1039/c5ra19094k
    1. Lindestam Arlehamn C. S., Dhanwani R., Pham J., Kuan R., Frazier A., Rezende Dutra J., et al. (2020). α-Synuclein-specific T cell reactivity is associated with preclinical and early Parkinson’s disease. Nat. Commun. 11:1875.
    1. Liu J., Osadchy M., Ashton L., Foster M., Solomon C. J., Gibson S. J. (2017). Deep convolutional neural networks for Raman spectrum recognition: a unified solution. Analyst 142 4067–4074. 10.1039/c7an01371j
    1. Lleó A., Cavedo E., Parnetti L., Vanderstichele H., Herukka S. K., Andreasen N., et al. (2015). Cerebrospinal fluid biomarkers in trials for Alzheimer and Parkinson diseases. Nat. Rev. Neurol. 11 41–55. 10.1038/nrneurol.2014.232
    1. Lussier F., Thibault V., Charron B., Wallace G. Q., Masson J.-F. (2020). Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering. TrAC Trends Anal. Chem. 124:115796. 10.1016/j.trac.2019.115796
    1. Maass F., Schulz I., Lingor P., Mollenhauer B., Bähr M. (2019). Cerebrospinal fluid biomarker for Parkinson’s disease: an overview. Mol. Cell. Neurosci. 97 60–66. 10.1016/j.mcn.2018.12.005
    1. Maciejczyk M., Zalewska A., Gerreth K. (2020). Salivary redox biomarkers in selected neurodegenerative diseases. J. Clin. Med. 9:497. 10.3390/jcm9020497
    1. Martinez-Horta S., Kulisevsky J. (2019). Mild cognitive impairment in Parkinson’s disease. J. Neural Transm. 126 897–904.
    1. McKhann G. M., Knopman D. S., Chertkow H., Hyman B. T., Jack C. R., Jr., Kawas C. H., et al. (2011). The diagnosis of dementia due to Alzheimer’s disease: recommendations from the national institute on aging−Alzheimer’s association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s Dement. 7 263–269.
    1. Movasaghi Z., Rehman S., Rehman I. U. (2007). Raman spectroscopy of biological tissues. Appl. Spectrosc. Rev. 42 493–541. 10.1080/05704920701551530
    1. Muro C. K., de Souza Fernandes L., Lednev I. K. (2016). Sex determination based on Raman spectroscopy of saliva traces for forensic purposes. Anal. Chem. 88 12489–12493. 10.1021/acs.analchem.6b03988
    1. Parnetti L., Gaetani L., Eusebi P., Paciotti S., Hansson O., El-Agnaf O., et al. (2019). CSF and blood biomarkers for Parkinson’s disease. Lancet Neurol. 18 573–586.
    1. Parnetti L., Paciotti S., Eusebi P., Dardis A., Zampieri S., Chiasserini D., et al. (2017). Cerebrospinal fluid β-glucocerebrosidase activity is reduced in parkinson’s disease patients. Mov. Disord. 32 1423–1431. 10.1002/mds.27136
    1. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., et al. (2011). Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12 2825–2830.
    1. Poewe W., Seppi K., Tanner C. M., Halliday G. M., Brundin P., Volkmann J., et al. (2017). Parkinson disease. Nat. Rev. Dis. Prim. 3:17013.
    1. Postuma R. B., Berg D., Stern M., Poewe W., Olanow C. W., Oertel W., et al. (2015). MDS clinical diagnostic criteria for Parkinson’s disease. Mov. Disord. 30 1591–1601. 10.1002/mds.26424
    1. Qiu S., Xu Y., Huang L., Zheng W., Huang C., Huang S., et al. (2016). Non-invasive detection of nasopharyngeal carcinoma using saliva surface-enhanced Raman spectroscopy. Oncol. Lett. 11 884–890. 10.3892/ol.2015.3969
    1. Radzol A. R. M., Lee K. Y., Mansor W. (2014). “Classification of salivary based NS1 from Raman spectroscopy with support vector machine,” in Proceeding of the 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 1835–1838 (Institute of Electrical and Electronics Engineers Inc.).
    1. Ralbovsky N. M., Halámková L., Wall K., Anderson-Hanley C., Lednev I. K. (2019). Screening for Alzheimer’s disease using saliva: a new approach based on machine learning and Raman Hyperspectroscopy. J. Alzheimer’s Dis. 71 1351–1359. 10.3233/jad-190675
    1. Reed T. T. (2011). Lipid peroxidation and neurodegenerative disease. Free Rad. Biol. Med. 51 1302–1319. 10.1016/j.freeradbiomed.2011.06.027
    1. Rygula A., Majzner K., Marzec K. M., Kaczor A., Pilarczyk M., Baranska M. (2013). Raman spectroscopy of proteins: a review. J. Raman Spectrosc. 44 1061–1076. 10.1002/jrs.4335
    1. Sancho Cantus D., Santiesteban López N., Cuerda Ballester M., Solera Gómez S., de la Rubia Ortí J. E. (2019). Stress in Parkinson’s disease. cortisol and amylase biomarkers. Syst. Rev. Rev. Científica la Soc. Enfermería Neurológica 50 12–22. 10.1016/j.sedeng.2018.09.002
    1. Saracchi E., Fermi S., Brighina L. (2014). Emerging candidate biomarkers for Parkinson’s disease: a review. Aging Dis. 5 27–34.
    1. Shorten C., Khoshgoftaar T. M. (2019). A survey on image data augmentation for deep learning. J. Big. Data 6 :60.
    1. Song W., Kothari V., Velly A. M., Cressatti M., Liberman A., Gornitsky M., et al. (2018). Evaluation of salivary heme oxygenase-1 as a potential biomarker of early Parkinson’s disease. Mov. Disord. 33 583–591. 10.1002/mds.27328
    1. Sveinbjornsdottir S. (2016). The clinical symptoms of Parkinson’s disease. J. Neurochem. 139 318–324.
    1. Van Woert M. H., Mueller P. S. (1971). Glucose, insulin, and free fatty acid metabolism in Parkinson’s disease treated with levodopa. Clin. Pharmacol. Ther. 12 360–367. 10.1002/cpt1971122part2360
    1. Virkler K., Lednev I. K. (2010). Forensic body fluid identification: the Raman spectroscopic signature of saliva. Analyst 135 512–517. 10.1039/b919393f
    1. Whitaker D. A., Hayes K. (2018). A simple algorithm for despiking Raman spectra. Chemom. Intell. Lab. Syst. 179 82–84. 10.1016/j.chemolab.2018.06.009
    1. Zech J. R., Badgeley M. A., Liu M., Costa A. B., Titano J. J., Oermann E. K. (2018). Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med. 15:e1002683. 10.1371/journal.pmed.1002683
    1. Zhang J., Sokal I., Peskind E. R., Quinn J. F., Jankovic J., Kenney C., et al. (2008). Multianalyte profile distinguishes alzheimer and parkinson diseases. Am. J. Clin. Pathol. 129 526–529. 10.1309/w01y0b808emeh12l

Source: PubMed

赞助者和合作者

医疗条件

药物干预

3
订阅