Targeted metabolomics combined with machine learning to identify and validate new biomarkers for early SLE diagnosis and disease activity.

Abstract

The early diagnosis of systemic lupus erythematosus (SLE) and the assessment of disease activity progression remain a great challenge. Targeted metabolomics has great potential to identify new biomarkers of SLE. Serum from 44 healthy participants and 89 SLE patients were analyzed using HM400 high-throughput targeted metabolomics. Machine learning (ML) with seven learning models and trained the model several times iteratively selected the two best prediction model in a competitive way, which were independent validated by enzyme-linked immunosorbent (ELISA) with 90 SLE patients. In this study, 146 differential metabolites, most of them organic acids, amino acids, and bile acids, were detected between patients with initial SLE and healthy participants, and 8 potential biomarkers were found by intersection of ML and statistics (area under the curve [AUC] > 0.95) showing a significant positive correlation with clinical indicators. In addition, we identified and validated 2 potential biomarkers for SLE classification (P < 0.05, AUC > 0.775; N-Methyl-L-glutamic acid, L-2-aminobutyric acid) showing a significant correlation with the SLE Disease Activity Index. These differential metabolites were mainly involved in metabolic pathways, amino acid biosynthesis, 2-oxocarboxylic acid metabolism and other pathways. This study indicated that the tricarboxylic acid cycle might be associated with SLE drug therapy. We identified 8 diagnostic models biomarkers and 2 biomarkers that could be used to identify initial SLE and distinguish different activity degree, which will promote the development of new tools for the diagnosis and evaluation of SLE.