A Metabolic Fingerprint of Ovarian Cancer: A Novel Diagnostic Strategy Employing Plasma Exosome-Based Metabolomics and Machine Learning Algorithms

Abstract Ovarian cancer (OC) is the third most common malignant tumor of women and is accompanied by an alteration of systemic metabolism. A liquid biopsy that captures and detects tumor-related biomarkers in body fluids has great potential for OC diagnosis. Exosomes, nanosized extracellular vesicles found in the blood, have been proposed as promising biomarkers for liquid biopsies. In this study we recruited 37 OC patients, 22 benign ovarian tumor (BE) patients, and 46 control (CON) patients. Plasma exosomes were purified from blood samples and sensitive thermal separation probe-based mass spectrometry analysis using a global untargeted metabolic profiling strategy was employed to characterize the metabolite fingerprints. Uniform manifold approximation and projection (UMAP) analysis demonstrated a distinct separation of exosomes among the three groups. We screened for diagnostic biomarkers from plasma exosome metabolites using seven machine learning algorithms, including artificial neural network (ANN), decision tree (DT), K nearest neighbor (KNN), logistics regression (LR), Naïve Bayes (NB), random forest (RF), and support vector machine (SVM). DT (0.98), RF (0.92), and ANN (0.89) were given the highest AUC values for the OC-CON comparison. RF (0.93), NB (0.88), and SVM (0.81) were given the highest AUCs for the OC-BE comparison. A total of 18, 138, and 157 metabolic features exhibited significant differences (FC= 1.5, p < 0.01, q < 0.01) in the OC vs BE, BE vs CON, and OC vs CON, comparisons, respectively. Notably, the quantities of 9-octadecenamide and 1,4-methanobenzocyclodecene were significantly elevated, while maltol showed a significant reduction in the OC group compared to the BE group. When comparing the OC group to the CON group, the concentrations of 4-amino-furazan-3-carboxylic acid 2-hydroxy-4-methoxybenzaldehyde, N-phenylethyl, and 4-morpholineethanamine were significantly elevated, while the remaining metabolites, including hydrazine and pyridine sulfonamide, were reduced, in the OC group. The metabolites showing different abundancies are associated with cancer-related mutations, immune responses, and metabolic reprogramming. We demonstrate that the RF algorithm, combined with sensitive thermal separation probe-based mass spectrometry analysis of plasma exosomes, can effectively identify OC patients with good accuracy. Thus, our study has shortlisted a set of potential biomarkers in plasma exosomes, and the proposed approach could serve as a routine prescreening tool for ovarian cancer.