Dataset Information

Using Serum Metabolomics to Predict Development of Anti-drug Antibodies in Multiple Sclerosis Patients Treated With IFN?.

ABSTRACT: Background: Neutralizing anti-drug antibodies (ADA) can greatly reduce the efficacy of biopharmaceuticals used to treat patients with multiple sclerosis (MS). However, the biological factors pre-disposing an individual to develop ADA are poorly characterized. Thus, there is an unmet clinical need for biomarkers to predict the development of immunogenicity, and subsequent treatment failure. Up to 35% of MS patients treated with beta interferons (IFN?) develop ADA. Here we use machine learning to predict immunogenicity against IFN? utilizing serum metabolomics data. Methods: Serum samples were collected from 89 MS patients as part of the ABIRISK consortium-a multi-center prospective study of ADA development. Metabolites and ADA were quantified prior to and after IFN? treatment. Thirty patients became ADA positive during the first year of treatment (ADA+). We tested the efficacy of six binary classification models using 10-fold cross validation; k-nearest neighbors, decision tree, random forest, support vector machine and lasso (Least Absolute Shrinkage and Selection Operator) logistic regression with and without interactions. Results: We were able to predict future immunogenicity from baseline metabolomics data. Lasso logistic regression with/without interactions and support vector machines were the most successful at identifying ADA+ or ADA- cases, respectively. Furthermore, patients who become ADA+ had a distinct metabolic response to IFN? in the first 3 months, with 29 differentially regulated metabolites. Machine learning algorithms could also predict ADA status based on metabolite concentrations at 3 months. Lasso logistic regressions had the greatest proportion of correct classifications [F1 score (accuracy measure) = 0.808, specificity = 0.913]. Finally, we hypothesized that serum lipids could contribute to ADA development by altering immune-cell lipid rafts. This was supported by experimental evidence demonstrating that, prior to IFN? exposure, lipid raft-associated lipids were differentially expressed between MS patients who became ADA+ or remained ADA-. Conclusion: Serum metabolites are a promising biomarker for prediction of ADA development in MS patients treated with IFN?, and could provide novel insight into mechanisms of immunogenicity.

SUBMITTER: Waddington KE

PROVIDER: S-EPMC7380268 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Serum Metabolomics to Predict Development of Anti-drug Antibodies in Multiple Sclerosis Patients Treated With IFNβ.

Waddington Kirsty E KE Papadaki Artemis A Coelewij Leda L Adriani Marsilio M Nytrova Petra P Kubala Havrdova Eva E Fogdell-Hahn Anna A Farrell Rachel R Dönnes Pierre P Pineda-Torra Inés I Jury Elizabeth C EC

Frontiers in immunology 20200717

<b>Background:</b> Neutralizing anti-drug antibodies (ADA) can greatly reduce the efficacy of biopharmaceuticals used to treat patients with multiple sclerosis (MS). However, the biological factors pre-disposing an individual to develop ADA are poorly characterized. Thus, there is an unmet clinical need for biomarkers to predict the development of immunogenicity, and subsequent treatment failure. Up to 35% of MS patients treated with beta interferons (IFNβ) develop ADA. Here we use machine learn ...[more]

PMID: 32765529

Similar Datasets

Project description:Eighty-five percent of multiple sclerosis cases begin with a discrete attack termed clinically isolated syndrome, but 37% of clinically isolated syndrome patients do not experience a relapse within 20 years of onset. Thus, the identification of biomarkers able to differentiate between individuals who are most likely to have a second clinical attack from those who remain in the clinically isolated syndrome stage is essential to apply a personalized medicine approach. We sought to identify biomarkers from biochemical, metabolic and proteomic screens that predict clinically defined conversion from clinically isolated syndrome to multiple sclerosis and generate a multi-omics-based algorithm with higher prognostic accuracy than any currently available test. An integrative multi-variate approach was applied to the analysis of cerebrospinal fluid samples taken from 54 individuals at the point of clinically isolated syndrome with 2-10 years of subsequent follow-up enabling stratification into clinical converters and non-converters. Leukocyte counts were significantly elevated at onset in the clinical converters and predict the occurrence of a second attack with 70% accuracy. Myo-inositol levels were significantly increased in clinical converters while glucose levels were decreased, predicting transition to multiple sclerosis with accuracies of 72% and 63%, respectively. Proteomics analysis identified 89 novel gene products related to conversion. The identified biochemical and protein biomarkers were combined to produce an algorithm with predictive accuracy of 83% for the transition to clinically defined multiple sclerosis, outperforming any individual biomarker in isolation including oligoclonal bands. The identified protein biomarkers are consistent with an exaggerated immune response, perturbed energy metabolism and multiple sclerosis pathology in the clinical converter group. The new biomarkers presented provide novel insight into the molecular pathways promoting disease while the multi-omics algorithm provides a means to more accurately predict whether an individual is likely to convert to clinically defined multiple sclerosis.

Dataset Information

Using Serum Metabolomics to Predict Development of Anti-drug Antibodies in Multiple Sclerosis Patients Treated With IFN?.

Publications

Using Serum Metabolomics to Predict Development of Anti-drug Antibodies in Multiple Sclerosis Patients Treated With IFNβ.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets