M2BPgs-HCC: An Automated Multilectin Bead Array Indicating Aberrant Glycosylation Signatures Toward Hepatitis C Virus-Associated Hepatocellular Carcinoma Prognosis

Abstract

Regular monitoring of patients with a history of hepatitis C virus (HCV) infection is critical for the detection and management of hepatocellular carcinoma (HCC). Mac-2 binding protein glycosylation isomer (M2BPGi) has been used to monitor fibrosis progression and predict HCC. However, HCC prediction based on M2BPGi has not been optimized. Here, we identified HCC risk-related glycan signatures of M2BP using a newly developed automated bead array with multiplexed lectins. Among 955 patients with HCV who achieved sustained virological response following direct-acting antiviral treatment, we compared M2BP glycosylation from sera of 42 patients diagnosed with HCC during follow-up and 43 without HCC (control) by the lectin microarray. At the HCC observation point, we found significant differences in 17 lectins. Using an automated bead array with 12 of 17 lectins, a principal component analysis (PCA) biplot differentiated HCC from control, along the PC1 axis, explaining 75.2% of variance. Based on PC1, we generated a scoring formula for an HCC-related glycosylation signature on M2BP (M2BPgs-HCC), showing good diagnostic performance for HCC (p = 2.92 × 10^-8, AUC = 0.829). This automated multilectin bead array improved the ability of M2BP to detect HCC, providing a candidate test for HCC surveillance in combination with other HCC markers.

Keywords: M2BPGi; glycosylation; hepatocellular carcinoma; lectin array.

Figure 1

Study flow chart.

Figure 2

Principal component analysis of clinical characteristics at the HCC observation point. Blue and red circles represent controls and patients with HCC, respectively. The right graph shows the eigenvectors of eight parameters.

Figure 3

Automatic glycofeature detection of serum M2BP using a 12-plexed lectin bead array. (A) Univariate analysis of lectin signals in control (blue) and HCC (red) groups. (B) Principal component analysis using 12-lectin signals for serum M2BP. The right graph shows eigenvectors of 12 lectins, where each lectin is indicated by an ID number listed in Table 3.

Figure 4

Comparison of the predictive value of M2BPGi-Qt, AFP-L3%, PIVKA-II, GALAD, M2BPgs-HCC, and the combination of M2BPgs-HCC and AFP-L3%. (A) Box-and-whisker diagram. Blue and red circles indicate individual patient values. (B) ROC curves are shown by red line.