Skip to main content
SpringerLink
Log in

Visible Particle Identification Using Raman Spectroscopy and Machine Learning

  • Research Article
  • Applications of Machine Learning and A.I. in Pharmaceutical Development and Technology
  • Published:
AAPS PharmSciTech Aims and scope Submit manuscript

Abstract

Visible particle identification is a crucial prerequisite step for process improvement and control during the manufacturing of injectable biotherapeutic drug products. Raman spectroscopy is a technology with several advantages for particle identification including high chemical sensitivity, minimal sample manipulation, and applicability to aqueous solutions. However, considerable effort and experience are required to extract and interpret Raman spectral data. In this study, we applied machine learning algorithms to analyze Raman spectral data for visible particle identification in order to minimize expert support and improve data analysis accuracy. We manually prepared ten types of particle standard solutions to simulate the particle types typically observed during manufacturing and established a Raman spectral library with accurate peak assignments for the visible particles. Five classification algorithms were trained using visible particle Raman spectral data. All models had high prediction accuracy of >98% for all types of visible particles. Our results demonstrate that the combination of Raman spectroscopy and machine learning can provide a simple and accurate data analysis approach for visible particle identification.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. CFR 21 Part 211 Current good manufacturing practice for finished pharmaceuticals. Office of the Federal Register. National Archives and Records Administration. 2020. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfcfr/CFRSearch.cfm?CFRPart=211. Accessed 6 Oct 2021.

  2. EU GMP Annex 1 Revision: manufacture of sterile medicinal products (draft). European Commission. 2020. https://www.gmp-compliance.org/files/guidemgr/2020_annex1ps_sterile_medicinal_products_en.pdf. Accessed 6 Oct 2021.

  3. General Chapter: USP. <790> Visible particulates in injections. In: USP-NF. Rockville, MD: USP; May 1, 2016. https://doi.org/10.31003/USPNF_M7197_01_01

  4. Jiskoot W, Randolph TW, Volkin DB, Middaugh CR, Schöneich C, Winter G, et al. Protein instability and immunogenicity: roadblocks to clinical application of injectable protein delivery systems for sustained release. J Pharm Sci. 2012;101(3):946–54. https://doi.org/10.1002/jps.23018.

    Article  CAS  PubMed  Google Scholar 

  5. Jiskoot W, Kijanka G, Randolph TW, Carpenter JF, Koulov AV, Mahler HC, et al. Mouse models for assessing protein immunogenicity: lessons and challenges. J Pharm Sci. 2016;105(5):1567–75.

    Article  CAS  Google Scholar 

  6. General Chapter: USP. <1790> Visual inspection of injections. In: USP-NF. Rockville, MD: USP; May 1, 2022. https://doi.org/10.31003/USPNF_M7198_06_01

  7. ICH. International Conference on Harmonisation of Technical Requirements for Registration of Pharmaceuticals for Human Use. ICH Q10 Pharmaceutical Quality System (PQS). 2009. [accessed 2021 Oct 6]. https://www.fda.gov/media/71553/download

  8. Li GG, Cao S, Jiao N, Wen ZQ. Classification of glass particles in parenteral product vials by visual, microscopic, and spectroscopic methods. PDA J Pharm Sci Technol. 2014;68(4):362–72. https://doi.org/10.5731/pdajpst.2014.00986.

    Article  CAS  PubMed  Google Scholar 

  9. Idris AM, El-Zahhar AA. Indicative properties measurements by SEM, SEM-EDX and XRD for initial homogeneity tests of new certified reference materials. Microchem J. 2019;146:429–33.

    Article  CAS  Google Scholar 

  10. Brückl L, Hahn R, Sergi M, Scheler S. A systematic evaluation of mechanisms, material effects, and protein-dependent differences on friction-related protein particle formation in formulation and filling steps. Int J Pharm. 2016;511(2):931–45.

    Article  Google Scholar 

  11. Nashed-Samuel Y, Torraca G, Liu D, Fujimori K, Zhang Z, Wen ZQ, et al. Identification of an extraneous black particle in a glass syringe: extractables/leachables case study. PDA J Pharm Sci Technol. 2010;64(3):242–8.

    CAS  PubMed  Google Scholar 

  12. Semenova D, Silina YE. The role of nanoanalytics in the development of organic-inorganic nanohybrids-seeing nanomaterials as they are. Nanomaterials (Basel). 2019;9(12):1673. https://doi.org/10.3390/nano9121673.

    Article  CAS  Google Scholar 

  13. Stefaniak EA, Worobiec A, Potgieter-Vermaak S, Alsecz A, Van Grieken R. Molecular and elemental characterisation of mineral particles by means of parallel micro-Raman spectrometry and scanning electron microscopy/energy dispersive X-ray analysis. Spectrochim Acta Part B At Spectrosc. 2006;61(7):824–30.

    Article  Google Scholar 

  14. Bulska E, Wagner B. Quantitative aspects of inductively coupled plasma mass spectrometry. Philos Trans A Math Phys Eng Sci. 2016;374(2079):20150369. https://doi.org/10.1098/rsta.2015.0369.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Benevides JM, Overman SA, Thomas GJ Jr. Raman spectroscopy of proteins. Curr Protoc Protein Sci 2004;Chapter 17. https://doi.org/10.1002/0471140864.ps1708s33

  16. Cao X, Wen ZQ, Vance A, Torraca G. Raman microscopic applications in the biopharmaceutical industry: in situ identification of foreign particulates inside glass containers with aqueous formulated solutions. Appl Spectrosc. 2009;63(7):830–4. https://doi.org/10.1366/000370209788701026.

    Article  CAS  PubMed  Google Scholar 

  17. Caudron E, Tfayli A, Monnier C, Manfait M, Prognon P, Pradeau D. Identification of hematite particles in sealed glass containers for pharmaceutical uses by Raman microspectroscopy. J Pharm Biomed Anal. 2011;54(4):866–8. https://doi.org/10.1016/j.jpba.2010.10.023.

    Article  CAS  PubMed  Google Scholar 

  18. Singh SK, Afonina N, Awwad M, Bechtold-Peters K, Blue JT, Chou D, et al. An industry perspective on the monitoring of subvisible particles as a quality attribute for protein therapeutics. J Pharm Sci. 2010;99(8):3302–21. https://doi.org/10.1002/jps.22097.

    Article  CAS  PubMed  Google Scholar 

  19. Saggu M, Liu J, Patel A. Identification of subvisible particles in biopharmaceutical formulations using Raman spectroscopy provides insight into polysorbate 20 degradation pathway. Pharm Res. 2015;32(9):2877–88. https://doi.org/10.1007/s11095-015-1670-x.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Kostamovaara J, Tenhunen J, Kögler M, Nissinen I, Nissinen J, Keränen P. Fluorescence suppression in Raman spectroscopy using a time-gated CMOS SPAD. Opt. 2013;21(25):31632–45. https://doi.org/10.1364/OE.21.031632.

    Article  CAS  Google Scholar 

  21. Wei D, Chen S, Liu Q. Review of fluorescence suppression techniques in Raman spectroscopy. Appl Spectrosc. 2015;50(5):387–406. https://doi.org/10.1080/05704928.2014.999936.

    Article  Google Scholar 

  22. Berghian-Grosan C, Magdas DA. Raman spectroscopy and machine-learning for edible oils evaluation. Talanta. 2020;218:121176. https://doi.org/10.1016/j.talanta.2020.121176.

    Article  CAS  PubMed  Google Scholar 

  23. Berghian-Grosan C, Magdas DA. Application of Raman spectroscopy and machine learning algorithms for fruit distillates discrimination. Sci Rep. 2020;10(1):21152. https://doi.org/10.1038/s41598-020-78159-8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Mandrell CT, Holland TE, Wheeler JF, Esmaeili S, Amar K, Chowdhury F, et al. Machine learning approach to Raman spectrum analysis of MIA PaCa-2 pancreatic cancer tumor repopulating cells for classification and feature analysis. Life (Basel). 2020;10(9):181. https://doi.org/10.3390/life10090181.

    Article  CAS  Google Scholar 

  25. Zhang L, Li C, Peng D, Yi X, He S, Liu F, et. al. Raman spectroscopy and machine learning for the classification of breast cancers. Spectrochim Acta A Mol Biomol Spectrosc 2022;264:120300. https://doi.org/10.1016/j.saa.2021.120300

  26. Lu W, Chen X, Wang L, Li H, Fu YV. Combination of an artificial intelligence approach and laser tweezers Raman spectroscopy for microbial identification. Anal Chem. 2020;92(9):6288–96. https://doi.org/10.1021/acs.analchem.9b04946.

    Article  CAS  PubMed  Google Scholar 

  27. Le L, Kégl B, Gramfort A, Marini C, Nguyen D, Cherti M, et al. Optimization of classification and regression analysis of four monoclonal antibodies from Raman spectra using collaborative machine learning approach. Talanta. 2018;184:260–5. https://doi.org/10.1016/j.talanta.2018.02.109.

    Article  CAS  PubMed  Google Scholar 

  28. Zhang C, Springall JS, Wang X, Barman I. Rapid, quantitative determination of aggregation and particle formation for antibody drug conjugate therapeutics with label-free Raman spectroscopy. Anal Chim Acta. 2019;1081:138–45. https://doi.org/10.1016/j.aca.2019.07.007.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. Vollrath I, Mathaes R, Sediq AS, Jere D, Jörg S, Huwyler J, et al. Subvisible particulate contamination in cell therapy products - can we distinguish? J Pharm Sci. 2020;109(1):216–9. https://doi.org/10.1016/j.xphs.2019.09.002.

    Article  CAS  PubMed  Google Scholar 

  30. Ringnér M. What is principal component analysis? Nat Biotechnol. 2008;26(3):303–4. https://doi.org/10.1038/nbt0308-303.

    Article  CAS  PubMed  Google Scholar 

  31. Pandya R, Pandya J. C5.0 algorithm to improved decision tree with feature selection and reduced error pruning. Int J Comput Appl. 2015;117:18–21.

    Google Scholar 

  32. Sun J, Zhao H. The application of sparse estimation of covariance matrix to quadratic discriminant analysis. BMC Bioinformatics. 2015;16:48. https://doi.org/10.1186/s12859-014-0443-6.

    Article  PubMed  PubMed Central  Google Scholar 

  33. Lee Y. Support vector machines for classification: a statistical portrait. Methods Mol Biol. 2010;620:347–68. https://doi.org/10.1007/978-1-60761-580-4_11.

    Article  PubMed  Google Scholar 

  34. Abu Alfeilat HA, Hassanat A, Lasassmeh O, Tarawneh AS, Alhasanat MB, Eyal Salman HS, et al. Effects of distance measure choice on K-nearest neighbor classifier performance: a review. Big Data. 2019;7(4):221–48. https://doi.org/10.1089/big.2018.0175.

    Article  PubMed  Google Scholar 

  35. Gul A, Perperoglou A, Khan Z, Mahmoud O, Miftahuddin M, Adler W, et al. Ensemble of a subset of kNN classifiers. Adv Data Anal Classif. 2018;12(4):827–40. https://doi.org/10.1007/s11634-015-0227-5.

    Article  PubMed  Google Scholar 

  36. Wiley JH, Rajai H, Atalla RH. Band assignments in the Raman spectra of celluloses. Carbohydr Res. 1987;160:113–29. https://doi.org/10.1016/0008-6215(87)80306-3.

    Article  CAS  Google Scholar 

  37. Movasaghi Z, Rehman S, Rehman IU. Raman spectroscopy of biological tissues. Appl Spectrosc. 2007;42(5):493–541. https://doi.org/10.1080/05704920701551530.

    Article  CAS  Google Scholar 

  38. Liu H, Yu W. Study of the structure transformation of wool fibers with Raman spectroscopy. J Appl Polym Sci. 2007;103:1–7.

    Article  Google Scholar 

  39. Andreassen E. Infrared and Raman spectroscopy of polypropylene. In: Karger-Kocsis J, editor. Polypropylene, Polym Sci Technol Ser, vol. 2; 1999. p. 320–8. https://doi.org/10.1007/978-94-011-4421-6_46.

    Chapter  Google Scholar 

  40. Jayes L, Hard AP, Séné C, Parker SF, Jayasooriya UA. Vibrational spectroscopic analysis of silicones: a Fourier transform-Raman and inelastic neutron scattering investigation. Anal Chem. 2003;75(4):742–6. https://doi.org/10.1021/ac026012f.

    Article  CAS  PubMed  Google Scholar 

  41. Nallasamy P, Mohan S. Vibrational spectroscopic characterization of form II poly (vinylidene fluoride). Indian J Pure Appl Phys. 2005;43:821–7.

    CAS  Google Scholar 

  42. Lobo H, Bonilla JV (Eds.). Handbook of plastics analysis (1st ed.). CRC Press. 2003;265-266. https://doi.org/10.1201/9780203911983

  43. Abdelrazek EM, Abdelghany AM, Oraby AH, Morsi MA. Effect of inorganic filler in the structural and optical properties of polyether sulfone. Res J Pharm Biol Chem Sci. 2012;3(4):277–93.

    CAS  Google Scholar 

  44. Mihály J, Sterkel S, Ortner H, Kocsis L, Hajba L, Furdyga E, et al. FTIR and FT-Raman spectroscopic study on polymer based high pressure digestion vessels. Croat Chem Acta. 2006;79(3):79.

    Google Scholar 

  45. Han C, Chen M, Rasch R, Yu Y, Zhao B. Structure studies of silicate glasses by raman spectroscopy. In: Reddy RG, Chaubal P, Pistorius PC, Pal U. (eds) Advances in molten slags, fluxes, and salts: Proceedings of the 10th International Conference on Molten Slags, Fluxes and Salts. 2016;p. 175-182 . https://doi.org/10.1007/978-3-319-48769-4_18

  46. Gómez de la Cuesta R, Goodacre R, Ashton L. Monitoring antibody aggregation in early drug development using Raman spectroscopy and perturbation-correlation moving windows. Anal Chem. 2014;86(22):11133–40. https://doi.org/10.1021/ac5038329.

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

This work was supported by the Medical Engineering Fund of Fudan University (yg2021-022), Pioneering Project of Academy for Engineering and Technology of Fudan University (gyy2018-001, gyy2018-002), Shanghai Key Discipline Construction Plan (2020-2022) (Grant No. GWV-10.1-XK01), and National Natural Science Foundation of China (62175034, 62175036).

Author information

Authors and Affiliations

  1. Institute of Biomedical Engineering and Technology, Academy for Engineer and Technology, Fudan University, 220 Handan Road, Shanghai, 200433, China

    Han Sheng, Yinping Zhao, Xiangan Long & Jiong Ma

  2. Shanghai Engineering Research Center of Ultra-precision Optical Manufacturing, Key Laboratory of Micro and Nano Photonic Structures (Ministry of Education), Green Photoelectron Platform, Department of Optical Science and Engineering, Fudan University, 220 Handan Road, Shanghai, 200433, China

    Liwen Chen, Yiyan Fei, Lan Mi & Jiong Ma

  3. Ruidge Biotech Co. Ltd., No. 888, Huanhu West 2nd Road, Lin-Gang Special Area, China (Shanghai) Pilot Free Trade Zone, Shanghai, 200131, China

    Liwen Chen

  4. State Key Laboratory of Applied Optics, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, No. 3888 Dong Nanhu Road, Changchun, Jilin, 130033, China

    Bei Li

  5. Shanghai Engineering Research Center of Industrial Microorganisms, The Multiscale Research Institute of Complex Systems (MRICS), School of Life Sciences, Fudan University, 220 Handan Road, Shanghai, 200433, China

    Jiong Ma

Authors
  1. Han Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yinping Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiangan Long
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Liwen Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yiyan Fei
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lan Mi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jiong Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

• Substantial contributions to the conception or design of the work or the acquisition, analysis, or interpretation of data for the work: Jiong Ma, Lan Mi, Han Sheng, Yinping Zhao, and Xiangan Long

• Drafting the work or revising it critically for important intellectual content: Han Sheng, Yinping Zhao, Xiangan Long, Liwen Chen, Bei Li, and Yiyan Fei

• Final approval of the version to be published: Jiong Ma, and Lan Mi

• Agreement to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved: Han Sheng, Yinping Zhao, Xiangan Long, Liwen Chen, Bei Li, Yiyan Fei, Lan Mi, and Jiong Ma

Corresponding authors

Correspondence to Lan Mi or Jiong Ma.

Ethics declarations

Conflict of Interest

The authors declare no competing interests.

Additional information

Publisher’s Note

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

Supplementary Information

ESM 1

(DOCX 37.7 kb)

ESM 2

(XLSX 3974 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sheng, H., Zhao, Y., Long, X. et al. Visible Particle Identification Using Raman Spectroscopy and Machine Learning. AAPS PharmSciTech 23, 186 (2022). https://doi.org/10.1208/s12249-022-02335-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1208/s12249-022-02335-4

Keywords

Search

Navigation