TY  - JOUR
AU  - Pietiäinen, Vilja
AU  - Polso, Minttu
AU  - Migh, Ede
AU  - Guckelsberger, Christian
AU  - Harmati, Mária
AU  - Diósdi, Ákos
AU  - Turunen, Laura
AU  - Hassinen, Antti
AU  - Potdar, Swapnil
AU  - Koponen, Annika
AU  - Gyukity-Sebestyén, Edina
AU  - Kovács, Ferenc
AU  - Kriston, András
AU  - Hollandi, Réka
AU  - Burián, Katalin
AU  - Terhes, Gabriella
AU  - Visnyovszki, Ádám
AU  - Fodor, Eszter
AU  - Lacza, Zsombor
AU  - Kantele, Anu
AU  - Kolehmainen, Pekka
AU  - Kakkola, Laura
AU  - Strandin, Tomas
AU  - Levanov, Lev
AU  - Kallioniemi, Olli
AU  - Kemény, Lajos
AU  - Julkunen, Ilkka
AU  - Vapalahti, Olli
AU  - Buzás, Krisztina
AU  - Paavolainen, Lassi
AU  - Horváth, Péter
AU  - Hepojoki, Jussi
TI  - Image-based and machine learning-guided multiplexed serology test for SARS-CoV-2
JF  - CELL REPORTS METHODS
J2  - CELL REP METH
VL  - 3
PY  - 2023
IS  - 8
PG  - 19
SN  - 2667-2375
DO  - 10.1016/j.crmeth.2023.100565
UR  - https://m2.mtmt.hu/api/publication/34107493
ID  - 34107493
N1  - HCEMM-USZ Skin Research Group 
Funding Agency and Grant Number: LENDULET-BIOMAG grant; European Regional Development Funds; H2020-discovAIR; H2020 ATTRACT-Spheroid -Picker; Chan Zuckerberg Initiative, Seed Networks for the HCA-DVP [2018-342, GINOP-2.3.2-15-2016-00006, GINOP-2.3.2-15-2016-00026]; Finnish TEKES/BusinessFinland FiDiPro [GINOP-2.3.2-15-2016-00037]; Academy of Finland; EU H2020 VEO project; Minerva Foundation for COVID-19 Research project grant [874656]; Academy of Finland Flagship program, Finnish Center for Artificial Intelligence [40294/13, iCOIN-336496, 308613, 321809, 310552, 337530]; NKFIH grants;  [FIRI2020-337036];  [2020-1.1.6-JOVO-2021-00010];  [TKP2020-NKA-17]
            Funding text: The authors thank the Minerva Institute (Helsinki, Finland) for providing utilities for the project, Prof. Perttu Hamalainen (Aalto University, Finland) for providing the expertise of his group for the project, the FIMM High Throughput Biomedicine Unit for providing access to high-throughput robotics, the FIMM High Content Imaging and Analysis Unit for HC imaging and analysis (HiLIFE, University of Helsinki and Biocenter Finland; EuroBioImaging, ISIDORe partner), and the CSC - IT Center for Science, Finland, for computational resources. We acknowledge support from the LENDULET-BIOMAG grant (2018-342), from the European Regional Development Funds (GINOP-2.3.2-15-2016-00006, GINOP-2.3.2-15-2016-00026, and GINOP-2.3.2-15-2016-00037), from the H2020-discovAIR (874656), from the H2020 ATTRACT-Spheroid -Picker, and from the Chan Zuckerberg Initiative, Seed Networks for the HCA-DVP. The Finnish TEKES/BusinessFinland FiDiPro Fellow Grant 40294/13 (to V.P., O.K., L.P., and P.H.), grants awarded by the Academy of Finland (iCOIN-336496 to O.K., V.P., and O.V.; 308613 to J.H.; 321809 to T.S.; 310552 to L.P.; 337530 to I.J.; and FIRI2020-337036 to FIMM-HCA, A.H., L.P., V.P., and P.H.), the EU H2020 VEO project (O.V.), and a Minerva Foundation for COVID-19 Research project grant (to V.P.) are also acknowledged. C.G. is funded by the Academy of Finland Flagship program, Finnish Center for Artificial Intelligence. OrthoSera Ltd. was funded by NKFIH grants (2020-1.1.6-JOVO-2021-00010 and TKP2020-NKA-17). The authors thank Dora Bokor, PharmD, for proofreading the manuscript.
AB  - 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 mea- surement 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 co- ronavirus 2 (SARS-CoV-2) as the model pathogen, we demonstrate that this method allows differentiation be- tween vaccine-induced and infection-induced antibody responses. Additionally, we established a dedicated web page for quantitative visualization of sample-specific results and their distribution, comparing them with controls and other samples. Our results provide a proof of concept for the approach, demonstrating fast and accurate measurement of antibody responses in a research setup with prospects for clinical diagnostics.
LA  - English
DB  - MTMT
ER  -