UPLC-MS/MS based diagnostics for epithelial ovarian cancer using fully sialylated C4-binding protein

Fucosylated C4b-binding protein α-chain, a novel serum biomarker that predicts lymph node metastasis in pancreatic ductal adenocarcinoma

C4b-binding protein α-chain (C4BPA) was previously identified as a novel serum biomarker for pancreatic ductal adenocarcinoma (PDAC). To apply this biomarker for clinical diagnosis, a lectin ELISA was established to measure serum fucosylated (Fuc)-C4BPA levels in 45 patients with PDAC, 20 patients with chronic pancreatitis (CP) and 50 healthy volunteers (HVs) in one training and three validation sets. The lecithin ELISA developed in the current study exhibited satisfactory within-run (2.6–6.7%) and between-day (1.8–3.6%) coefficient of variations. Serum Fuc-C4BPA levels in patients with PDAC (0.54±0.27 AU/ml) was significantly higher than that in HVs (0.21±0.06 AU/ml; P<0.0001) and patients with CP (0.25±0.03 AU/ml; P<0.0001). Additionally, serum Fuc-C4BPA levels in preoperative patients were significantly decreased compared with postoperative patient sera (P<0.0003). The receiver operating characteristic (ROC) curve analyses revealed that the area under the curve (AUC) of Fuc-C4BPA (0.985) was higher than that of carbohydrate antigen (CA)19-9 (0.843), carcinoembryonic antigen (0.548) and total C4BPA (0.875) (P<0.001). To analyze the clinical significance of Fuc-C4BPA, the ability of Fuc-C4BPA to predict lymph node metastasis was compared with that of CA19-9. The AUC of serum Fuc-C4BPA levels (0.703) was significantly higher than that of serum CA19-9 levels (0.500) in patients with PDAC (P<0.001). The current study established a novel lectin ELISA for measuring serum Fuc-C4BPA levels. Thus, Fuc-C4BPA has potential clinical applications owing to its high diagnostic value in PDAC.

Comprehensive Serum Glycopeptide Spectra Analysis Combined with Artificial Intelligence (CSGSA-AI) to Diagnose Early-Stage Ovarian Cancer

Ovarian cancer is a leading cause of deaths among gynecological cancers, and a method to detect early-stage epithelial ovarian cancer (EOC) is urgently needed. We aimed to develop an artificial intelligence (AI)-based comprehensive serum glycopeptide spectra analysis (CSGSA-AI) method in combination with convolutional neural network (CNN) to detect aberrant glycans in serum samples of patients with EOC. We converted serum glycopeptide expression patterns into two-dimensional (2D) barcodes to let CNN learn and distinguish between EOC and non-EOC. CNN was trained using 60% samples and validated using 40% samples. We observed that principal component analysis-based alignment of glycopeptides to generate 2D barcodes significantly increased the diagnostic accuracy (88%) of the method. When CNN was trained with 2D barcodes colored on the basis of serum levels of CA125 and HE4, a diagnostic accuracy of 95% was achieved. We believe that this simple and low-cost method will increase the detection of EOC.