Top-Down Proteomics Detection of Potential Salivary Biomarkers for Autoimmune Liver Diseases Classification.
Alessandra OlianasGiulia GuadalupiTiziana CabrasCristina ContiniSimone SerraoFederica IavaroneCastagnola MassimoIrene MessanaSimona OnaliLuchino ChessaGiacomo DiazBarbara ManconiPublished in: International journal of molecular sciences (2023)
(1) Autoimmune hepatitis (AIH) and primary biliary cholangitis (PBC) are autoimmune liver diseases characterized by chronic hepatic inflammation and progressive liver fibrosis. The possible use of saliva as a diagnostic tool has been explored in several oral and systemic diseases. The use of proteomics for personalized medicine is a rapidly emerging field. (2) Salivary proteomic data of 36 healthy controls (HCs), 36 AIH and 36 PBC patients, obtained by liquid chromatography/mass spectrometry top-down pipeline, were analyzed by multiple Mann-Whitney test, Kendall correlation, Random Forest (RF) analysis and Linear Discriminant Analysis (LDA); (3) Mann-Whitney tests provided indications on the panel of differentially expressed salivary proteins and peptides, namely cystatin A, statherin, histatin 3, histatin 5 and histatin 6, which were elevated in AIH patients with respect to both HCs and PBC patients, while S100A12, S100A9 short, cystatin S1, S2, SN and C showed varied levels in PBC with respect to HCs and/or AIH patients. RF analysis evidenced a panel of salivary proteins/peptides able to classify with good accuracy PBC vs. HCs (83.3%), AIH vs. HCs (79.9%) and PBC vs. AIH (80.2%); (4) RF appears to be an attractive machine-learning tool suited for classification of AIH and PBC based on their different salivary proteomic profiles.
Keyphrases
- mass spectrometry
- machine learning
- end stage renal disease
- ejection fraction
- liquid chromatography
- newly diagnosed
- chronic kidney disease
- deep learning
- artificial intelligence
- oxidative stress
- high resolution
- big data
- patient reported
- amino acid
- capillary electrophoresis
- simultaneous determination
- sensitive detection