IgG Antibody Responses to Epstein-Barr Virus in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Their Effective Potential for Disease Diagnosis and Pathological Antigenic Mimicry

Abstract

Background and Objectives: The diagnosis and pathology of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) remain under debate. However, there is a growing body of evidence for an autoimmune component in ME/CFS caused by the Epstein-Barr virus (EBV) and other viral infections. Materials and Methods: In this work, we analyzed a large public dataset on the IgG antibodies to 3054 EBV peptides to understand whether these immune responses could help diagnose patients and trigger pathological autoimmunity; we used healthy controls (HCs) as a comparator cohort. Subsequently, we aimed at predicting the disease status of the study participants using a super learner algorithm targeting an accuracy of 85% when splitting data into train and test datasets. Results: When we compared the data of all ME/CFS patients or the data of a subgroup of those patients with non-infectious or unknown disease triggers to the data of the HC, we could not find an antibody-based classifier that would meet the desired accuracy in the test dataset. However, we could identify a 26-antibody classifier that could distinguish ME/CFS patients with an infectious disease trigger from the HCs with 100% and 90% accuracies in the train and test sets, respectively. We finally performed a bioinformatic analysis of the EBV peptides associated with these 26 antibodies. We found no correlation between the importance metric of the selected antibodies in the classifier and the maximal sequence homology between human proteins and each EBV peptide recognized by these antibodies. Conclusions: In conclusion, these 26 antibodies against EBV have an effective potential for disease diagnosis in a subset of patients. However, the peptides associated with these antibodies are less likely to induce autoimmune B-cell responses that could explain the pathogenesis of ME/CFS.

Keywords: antigenic mimicry; autoimmunity; biomarker discovery; disease pathogenesis; machine learning.

Figure 1

Analysis of all ME/CFS patients versus HCs. (A) Density plot of each antibody’s average importance distribution obtained by the RF with the top 10 most important antibodies highlighted. (B) Accuracy of the SL classifier in the train (purple) and test (orange) subsets as a function of the number of antibodies included. The black and blue horizontal dashed lines indicate 85% (target accuracy). The best classifier is highlighted with a black dot. (C) Accuracy of the different classifiers assembled by the SL in the train subset. (D) Sensitivity and specificity of the SL classifiers in the test subset as a function of the number of antibodies included.

Figure 2

Analysis of ME/CFS patients with non-infectious or unknown disease triggers against HCs. (A) Density plot of each antibody’s average importance distribution obtained by the RF with the top 10 most important antibodies highlighted. (B) Accuracy of the SL classifier in the train (purple) and test (orange) subsets as a function of the number of antibodies included. The black and blue horizontal dashed lines referred to the 85% target accuracy. The best classifier is highlighted with a black dot. (C) Sensitivity and specificity of the SL classifiers in the test subset as a function of number of antibodies included.

Figure 3

Analysis of ME/CFS patients with an infectious disease trigger against HCs. (A) Density plot of each antibody’s average importance distribution obtained by the RF with the top 10 most important antibodies highlighted. (B) Accuracy of the SL classifier in the train and test subsets as a function of the number of antibodies included. The black and blue horizontal dashed lines indicate the target accuracy of 85% (i.e., 0.85). The best classifier is highlighted with a black dot. (C) Boxplots of the log10-levels of the selected 26 antibodies in HCs and ME/CFS patients. (D) Confusion matrix concerning the optimal classifier performance on the test subset. (E) ROC curve of the optimal classifier for both train and test subsets.

Figure 4

Bioinformatic analysis of the EBV peptides associated with the 26 antibodies for predicting ME/CFS patients with an infectious disease trigger. (A) Alignments between EBNA6_0070 and the human proteins HOXA-9A and ADRA1B_371 with the corresponding amino-acid coordinates within brackets. (B) Alignments between EBNA6_0488* and the human proteins CTCF and AEBP1 with the corresponding protein coordinates within brackets. (C). Scatterplot between the average importance of each EBV peptide and the maximum E-score alignment score with human proteins using the RefSeq reference protein database, where R is the Spearman correlation coefficient with the respective 95% confidence interval in brackets.