Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning
Abstract Background Survivors of acute COVID-19 often suffer prolonged, diffuse symptoms post-infection, referred to as “Long-COVID”. A lack of Long-COVID biomarkers and pathophysiological mechanisms limits effective diagnosis, treatment and disease surveillance. We performed targeted proteomics and...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-02-01
|
Series: | Molecular Medicine |
Subjects: | |
Online Access: | https://doi.org/10.1186/s10020-023-00610-z |
_version_ | 1797864448752353280 |
---|---|
author | Maitray A. Patel Michael J. Knauer Michael Nicholson Mark Daley Logan R. Van Nynatten Gediminas Cepinskas Douglas D. Fraser |
author_facet | Maitray A. Patel Michael J. Knauer Michael Nicholson Mark Daley Logan R. Van Nynatten Gediminas Cepinskas Douglas D. Fraser |
author_sort | Maitray A. Patel |
collection | DOAJ |
description | Abstract Background Survivors of acute COVID-19 often suffer prolonged, diffuse symptoms post-infection, referred to as “Long-COVID”. A lack of Long-COVID biomarkers and pathophysiological mechanisms limits effective diagnosis, treatment and disease surveillance. We performed targeted proteomics and machine learning analyses to identify novel blood biomarkers of Long-COVID. Methods A case–control study comparing the expression of 2925 unique blood proteins in Long-COVID outpatients versus COVID-19 inpatients and healthy control subjects. Targeted proteomics was accomplished with proximity extension assays, and machine learning was used to identify the most important proteins for identifying Long-COVID patients. Organ system and cell type expression patterns were identified with Natural Language Processing (NLP) of the UniProt Knowledgebase. Results Machine learning analysis identified 119 relevant proteins for differentiating Long-COVID outpatients (Bonferonni corrected P < 0.01). Protein combinations were narrowed down to two optimal models, with nine and five proteins each, and with both having excellent sensitivity and specificity for Long-COVID status (AUC = 1.00, F1 = 1.00). NLP expression analysis highlighted the diffuse organ system involvement in Long-COVID, as well as the involved cell types, including leukocytes and platelets, as key components associated with Long-COVID. Conclusions Proteomic analysis of plasma from Long-COVID patients identified 119 highly relevant proteins and two optimal models with nine and five proteins, respectively. The identified proteins reflected widespread organ and cell type expression. Optimal protein models, as well as individual proteins, hold the potential for accurate diagnosis of Long-COVID and targeted therapeutics. |
first_indexed | 2024-04-09T22:52:00Z |
format | Article |
id | doaj.art-c86175a23b0b49e483a857fd986bcdde |
institution | Directory Open Access Journal |
issn | 1528-3658 |
language | English |
last_indexed | 2024-04-09T22:52:00Z |
publishDate | 2023-02-01 |
publisher | BMC |
record_format | Article |
series | Molecular Medicine |
spelling | doaj.art-c86175a23b0b49e483a857fd986bcdde2023-03-22T11:36:20ZengBMCMolecular Medicine1528-36582023-02-0129111510.1186/s10020-023-00610-zOrgan and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learningMaitray A. Patel0Michael J. Knauer1Michael Nicholson2Mark Daley3Logan R. Van Nynatten4Gediminas Cepinskas5Douglas D. Fraser6Epidemiology and Biostatistics, Western UniversityPathology and Laboratory Medicine, Western UniversityMedicine, Western UniversityEpidemiology and Biostatistics, Western UniversityMedicine, Western UniversityLawson Health Research InstituteLawson Health Research InstituteAbstract Background Survivors of acute COVID-19 often suffer prolonged, diffuse symptoms post-infection, referred to as “Long-COVID”. A lack of Long-COVID biomarkers and pathophysiological mechanisms limits effective diagnosis, treatment and disease surveillance. We performed targeted proteomics and machine learning analyses to identify novel blood biomarkers of Long-COVID. Methods A case–control study comparing the expression of 2925 unique blood proteins in Long-COVID outpatients versus COVID-19 inpatients and healthy control subjects. Targeted proteomics was accomplished with proximity extension assays, and machine learning was used to identify the most important proteins for identifying Long-COVID patients. Organ system and cell type expression patterns were identified with Natural Language Processing (NLP) of the UniProt Knowledgebase. Results Machine learning analysis identified 119 relevant proteins for differentiating Long-COVID outpatients (Bonferonni corrected P < 0.01). Protein combinations were narrowed down to two optimal models, with nine and five proteins each, and with both having excellent sensitivity and specificity for Long-COVID status (AUC = 1.00, F1 = 1.00). NLP expression analysis highlighted the diffuse organ system involvement in Long-COVID, as well as the involved cell types, including leukocytes and platelets, as key components associated with Long-COVID. Conclusions Proteomic analysis of plasma from Long-COVID patients identified 119 highly relevant proteins and two optimal models with nine and five proteins, respectively. The identified proteins reflected widespread organ and cell type expression. Optimal protein models, as well as individual proteins, hold the potential for accurate diagnosis of Long-COVID and targeted therapeutics.https://doi.org/10.1186/s10020-023-00610-zLong-COVIDCOVID-19Targeted proteomicsMachine learningOrgan systemCell types |
spellingShingle | Maitray A. Patel Michael J. Knauer Michael Nicholson Mark Daley Logan R. Van Nynatten Gediminas Cepinskas Douglas D. Fraser Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning Molecular Medicine Long-COVID COVID-19 Targeted proteomics Machine learning Organ system Cell types |
title | Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning |
title_full | Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning |
title_fullStr | Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning |
title_full_unstemmed | Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning |
title_short | Organ and cell-specific biomarkers of Long-COVID identified with targeted proteomics and machine learning |
title_sort | organ and cell specific biomarkers of long covid identified with targeted proteomics and machine learning |
topic | Long-COVID COVID-19 Targeted proteomics Machine learning Organ system Cell types |
url | https://doi.org/10.1186/s10020-023-00610-z |
work_keys_str_mv | AT maitrayapatel organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT michaeljknauer organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT michaelnicholson organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT markdaley organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT loganrvannynatten organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT gediminascepinskas organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning AT douglasdfraser organandcellspecificbiomarkersoflongcovididentifiedwithtargetedproteomicsandmachinelearning |