Machine Learning Reveals Serum Glycopatterns as Potential Biomarkers for the Diagnosis of Nonalcoholic Fatty Liver Disease (NAFLD).

Nonalcoholic fatty liver disease (NAFLD) has emerged as the predominant chronic liver condition globally, and underdiagnosis is common, particularly in mild cases, attributed to the asymptomatic nature and traditional ultrasonography's limited sensitivity to detect early-stage steatosis. Consequently, patients may experience progressive liver pathology. The objective of this research is to ascertain the efficacy of serum glycan glycopatterns as a potential diagnostic biomarker, with a particular focus on the disease's early stages. We collected a total of 170 serum samples from volunteers with mild-NAFLD (Mild), severe-NAFLD (Severe), and non-NAFLD (None). Examination via lectin microarrays has uncovered pronounced disparities in serum glycopatterns identified by 19 distinct lectins. Following this, we employed four distinct machine learning algorithms to categorize the None, Mild, and Severe groups, drawing on the alterations observed in serum glycopatterns. The gradient boosting decision tree (GBDT) algorithm outperformed other models in diagnostic accuracy within the validation set, achieving an accuracy rate of 95% in differentiating the None group from the Mild group. Our research indicates that employing lectin microarrays to identify alterations in serum glycopatterns, when integrated with advanced machine learning algorithms, could constitute a promising approach for the diagnosis of NAFLD, with a special emphasis on its early detection.

Alterations of mannosylated glycopatterns recognized by Hippeastrum hybrid lectin in saliva of patients with lung cancer.

OBJECTIVES: Lung cancer (LC) is the malignant tumor with the highest mortality rate worldwide, and precise early diagnosis can improve patient prognosis. The purpose of this study was to investigate whether alterations in the glycopatterns recognized by the Hippeastrum hybrid lectin (HHL) in salivary proteins are associated with the development of LC. MATERIALS AND METHODS: First, we collected saliva samples from LC (15 lung adenocarcinoma (ADC); 15 squamous cell carcinoma (SCC); 15 small cell lung cancer (SCLC)) and 15 benign pulmonary disease (BPD) for high-throughput detection of abundance levels of HHL-recognized glycopatterns using protein microarrays, and then validated the pooled samples from each group with lectin blotting analysis. Finally, the N-glycan profiles of salivary glycoproteins isolated from the pooled samples using HHL-magnetic particle conjugates were characterized separately using MALDI-TOF/TOF-MS. RESULTS: The results showed that the abundance level of glycopatterns recognized by HHL in salivary proteins was elevated in LC compared to BPD. The proportion of mannosylated N-glycans was notably higher in ADC (31.7%), SCC (39.0%), and SCLC (46.6%) compared to BPD (23.3%). CONCLUSIONS: The altered salivary glycopatterns such as oligomannose, Manα1-3Man, or Manα1-6Man N-glycans recognized by HHL might serve as potential biomarkers for the diagnosis of LC patients. CLINICAL RELEVANCE: This study provides crucial information for studying changes in salivary to differentiate between BPD and LC and facilitate the discovery of biomarkers for LC diagnosis based on precise alterations of mannosylated N-glycans in saliva.