Posted in | News | Medical Optics

Vaccine Authenticity Verification Using MALDI-MS and Machine Learning

A recent article in NPJ | Vaccines explored the use of matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) combined with machine learning to screen vaccine authenticity. The researchers aimed to address the growing issue of substandard and false vaccines, which pose serious risks to public health. 

Vaccine Authenticity Verification Using MALDI-MS and Machine Learning

Image Credit: luchschenF/Shutterstock.com

They proposed and tested a novel workflow capable of distinguishing authentic vaccines from falsified ones, offering a potential method for monitoring vaccine supply chains.

Background

MALDI-MS is a powerful analytical technique known for its high sensitivity and selectivity, making it ideal for analyzing complex samples. It is widely used in proteomics, metabolomics, and clinical microbiology to identify microorganisms. The technique ionizes molecules from solid or liquid samples using a laser, allowing analysis of their mass-to-charge ratios (m/z).

Combining machine learning with MALDI-MS enhances its ability to classify and identify biomarkers, making it a promising tool for testing vaccine authenticity. This integration allows for rapid and accurate differentiation between authentic and falsified vaccines, even when their chemical compositions are similar. Machine learning models also adapt to evolving data patterns, ensuring the method remains effective against emerging vaccine falsification threats.

About the Research

In this study, the authors developed and validated a MALDI-MS workflow combined with open-source machine learning and statistical analysis to differentiate authentic and falsified vaccines. They used two widely-used MALDI-MS instruments: the Bruker MALDI Biotyper Sirius and the bioMérieux VITEK MS, both commonly found in clinical laboratories worldwide.

The study analyzed four authentic vaccines, including, Nimenrix (Pfizer Ltd), Engerix B (GlaxoSmithKline), Flucelvax Tetra (Seqirus Ltd.), and Ixiaro (Valneva Ltd.), and eight falsified surrogates chosen based on previously reported cases of falsified vaccine.

The workflow involved sample preparation, data acquisition, data processing, and statistical analysis. Vaccine samples were mixed with a matrix solution and spotted onto MALDI target plates. They were then analyzed with the MALDI-MS instruments, and the resulting mass spectra were collected over three overlapping mass ranges (0-900, 700-2500, and 2000-20,000 m/z). This approach captured a comprehensive spectrum of potential biomolecular signatures, providing a robust dataset for analysis.

Data was processed using various software tools, including SpectralWorks AnalyzerPro XD, MALDIquant, and MetaboAnalyst 5.0. The MALDIquant R package was used for essential processing steps, such as baseline correction, peak intensity normalization, and peak identification.

The processed data were then subjected to multivariate statistical analysis and machine learning techniques, including partial least squares-discriminant analysis (PLS-DA). These methods were important in modeling the data and predicting m/z features that could effectively screen vaccine authenticity.

Research Findings

The results demonstrated that this approach effectively distinguished authentic vaccines from falsified ones. The researchers found clear differences between the mass spectral profiles of real vaccines and their counterfeit surrogates. Multivariate data modeling and mass spectra analysis provided further proof that MALDI-MS could be a reliable tool for monitoring vaccine supply chains.

The reproducibility of the MALDI-MS analysis was confirmed by analyzing replicate samples and assessing variability in mass spectral peak intensities. Post-acquisition data processing, including baseline correction, peak intensity normalization, and peak alignment, minimized analytical variability. The PLS-DA models demonstrated that MALDI-MS data could reliably predict vaccine authenticity.

The researchers also identified several mass spectral peaks unique associated with either authentic or falsified vaccines, suggesting they could serve as biomarkers for authenticity testing. These findings suggest that MALDI-MS could be used to develop a comprehensive database of distinguishing mass spectral peaks, enabling real-time screening and verification of vaccine authenticity.

Applications

This research has significant implications for vaccine supply chain monitoring. The proposed method could be integrated into existing MALDI-MS networks in clinical labs worldwide to screen vaccines for authenticity, helping reduce the risk of substandard or falsified vaccines. Its high throughput and low cost make it practical for large-scale screening.

By combining machine learning with MALDI-MS, this approach offers a valuable tool for ensuring vaccine authenticity and safeguarding public health.

Conclusion

The novel workflow effectively screened vaccine authenticity, distinguishing genuine vaccines from counterfeits. This method has the potential to transform vaccine safety checks and improve global supply chain monitoring by leveraging MALDI-MS infrastructure in clinical labs.

Future work should aim to expand the technique to cover a broader range of vaccines and liquid medicines, further enhancing its role in safeguarding pharmaceutical products and public health. This approach represents a significant advancement in addressing vaccine falsification.

Journal Reference

Clarke, R., et al. (2024). Using matrix assisted laser desorption ionisation mass spectrometry combined with machine learning for vaccine authenticity screening. npj Vaccines. DOI: 10.1038/s41541-024-00946-5, https://www.nature.com/articles/s41541-024-00946-5

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Muhammad Osama

Written by

Muhammad Osama

Muhammad Osama is a full-time data analytics consultant and freelance technical writer based in Delhi, India. He specializes in transforming complex technical concepts into accessible content. He has a Bachelor of Technology in Mechanical Engineering with specialization in AI & Robotics from Galgotias University, India, and he has extensive experience in technical content writing, data science and analytics, and artificial intelligence.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Osama, Muhammad. (2024, September 09). Vaccine Authenticity Verification Using MALDI-MS and Machine Learning. AZoOptics. Retrieved on October 08, 2024 from https://www.azooptics.com/News.aspx?newsID=29941.

  • MLA

    Osama, Muhammad. "Vaccine Authenticity Verification Using MALDI-MS and Machine Learning". AZoOptics. 08 October 2024. <https://www.azooptics.com/News.aspx?newsID=29941>.

  • Chicago

    Osama, Muhammad. "Vaccine Authenticity Verification Using MALDI-MS and Machine Learning". AZoOptics. https://www.azooptics.com/News.aspx?newsID=29941. (accessed October 08, 2024).

  • Harvard

    Osama, Muhammad. 2024. Vaccine Authenticity Verification Using MALDI-MS and Machine Learning. AZoOptics, viewed 08 October 2024, https://www.azooptics.com/News.aspx?newsID=29941.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.