Image-based and machine learning-guided multiplexed serology test for SARS-CoV-2

Aug 5, 2026

Upload by Eliana

Pietiäinen and colleagues present a miniaturized, automated microscopy-based serology assay for patient blood samples that uses machine learning-guided image analysis. The platform simultaneously measures IgM, IgA, and IgG responses to multiple SARS-CoV-2 antigens via transfection-expressed targets, enabling low-biosafety operation. Built as a high-throughput, objective workflow, it differentiates vaccine-induced from infection-induced antibody patterns and includes a web resource for quantitative visualization and distribution comparisons.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Motivation

Summary

Introduction

Mini-IFA design and workflow

Machine learning image analysis

Differentiating vaccine vs infection responses

Article Image-based and machine learning-guided multiplexed serology test for SARS-CoV-2 Authors Vilja Pieti¨ainen, Minttu Polso, Ede Migh, ..., Lassi Paavolainen, Peter Horvath, Jussi Hepojoki Correspondence vilja.pietiainen@helsinki.ﬁ (V.P.), [horvath.peter@brc.hu](horvath.peter@brc.hu) (P.H.), jussi.hepojoki@helsinki.ﬁ (J.H.) In brief Pieti¨ainen et al. have developed an automated, miniaturized, microscopybased assay for multiparametric analysis of antibody responses in patient blood samples. Using SARS-CoV-2 antigens, they demonstrate that it is a costeffective, rapid, and reliable serology test with low biosafety level requirements and adaptability to other pathogens. d Combines transfection-based antigens, high-throughput imaging, and machine learning d Rapid and cost effective with low biosafety level requirements d Tested using SARS-CoV-2 antigens but adaptable to other pathogens Pieti¨ainen et al., 2023, Cell Reports Methods 3, 100565 August 28, 2023 ª 2023 The Authors. [https://doi.org/10.1016/j.crmeth.2023.100565](https://doi.org/10.1016/j.crmeth.2023.100565) ll ll OPEN ACCESS Article Image-based and machine learning-guided multiplexed serology test for SARS-CoV-2 Vilja Pieti¨ainen,1,24,* Minttu Polso,1,23 Ede Migh,2,23 Christian Guckelsberger,1,3,4,5,23 Maria Harmati,2 Akos Diosdi,2 Laura Turunen,1 Antti Hassinen,1 Swapnil Potdar,1 Annika Koponen,6,7 Edina Gyukity Sebestyen,2 Ferenc Kovacs,2,8 Andras Kriston,2,8 Reka Hollandi,2 Katalin Burian,9 Gabriella Terhes,9 Adam Visnyovszki,10 Eszter Fodor,11 (Author list continued on next page) 1Institute for Molecular Medicine Finland (FIMM), Helsinki Institute of Life Sciences (HiLIFE), University of Helsinki, Helsinki, Finland 2Laboratory of Microscopic Image Analysis and Machine Learning, Institute of Biochemistry, Biological Research Centre, Szeged, Hungary 3Department of Computer Science, Aalto University, Espoo, Finland 4Finnish Center for Artiﬁcial Intelligence, Espoo, Finland 5School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK 6Minerva Foundation Institute for Medical Research, Helsinki, Finland 7Department of Anatomy, Faculty of Medicine, University of Helsinki, Helsinki, Finland 8Single-Cell Technologies Ltd. , Szeged, Hungary (Afﬁliations continued on next page) MOTIVATION Serological assays are essential for studying and controlling infectious disease outbreaks, such as the current coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) . Immunoﬂuorescence assays relying on cells infected with a given virus provide rapidly available means for demonstrating antibody response against emerging pathogens. However, setting up such assays may require a high-biosafety-level facility for handling the virus. In addition, such assays are often low throughput, and interpretation of the results can be labor intensive and subjective. Here, we describe a mini-immunoﬂuorescence assay (mini-IFA), an automated, high-throughput, microscopy-based serology assay requiring a low-biosafety-level environment. We demonstrate its efﬁcacy using SARS-CoV-2 as a model. SUMMARY We present a miniaturized immunoﬂuorescence assay (mini-IFA) for measuring antibody response in patient blood samples. The method utilizes machine learning-guided image analysis and enables simultaneous measurement of immunoglobulin M (IgM), IgA, and IgG responses against different viral antigens in an automated and high-throughput manner. The assay relies on antigens expressed through transfection, enabling use at a low biosafety level and fast adaptation to emerging pathogens. Using severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) asthe model pathogen, we demonstrate that this method allows differentiation between vaccine-induced and infection-induced antibody responses. Additionally, we established a dedicated web page for quantitative

FAQs

What is the mini-IFA assay described for SARS-CoV-2?

It is a miniaturized immunofluorescence serology assay that uses automated, high-content microscopy with machine learning-guided image analysis to detect antibodies in patient blood samples.

How does the assay achieve multiplexing while requiring low biosafety levels?

It uses transfection-expressed viral antigens instead of infected cells, allowing simultaneous measurement of IgM, IgA, and IgG against different antigens under low-biosafety conditions.

What capability does the study demonstrate using SARS-CoV-2 as a model pathogen?

The method differentiates vaccine-induced from infection-induced antibody responses and provides quantitative visualization of sample-specific results through a dedicated web page.

Aug 5, 2026

Upload by Eliana