Prediction of hepatocellular carcinoma risk in patients with chronic liver disease from dynamic modular networks
Journal of Translational Medicine Apr 01, 2021
Chen Y, Yang W, Chen Q, et al. - Researchers sought to develop risk prediction models and proposed the sequential allosteric modules (AMs)-based approach for hepatocellular carcinoma (HCC) risk prediction in chronic liver disease cases by combining the multi-source data (including AMs, clinical microarray data and The Cancer Genome Atlas dataset). Thirteen oncogenic allosteric modules (OAMs) were identified among chronic hepatitis B, cirrhosis and HCC network used SimiNEF. Eleven highly correlated gene pairs involving 15 genes were acquired from the 12 OAMs partial consistent with those in independent clinical microarray data, and thereafter, optimization of a three-gene set (cyp1a2-cyp2c19-il6) was accomplished to differentiate HCC from non-tumor liver tissues using random forests with an average area under the curve of 0.973. According to findings, not only HCC risk detection in chronic liver diseases could be enabled by sequential AMs-based approach but it also might be applied to any time-dependent risk of malignancy.
-
Exclusive Write-ups & Webinars by KOLs
-
Daily Quiz by specialty
-
Paid Market Research Surveys
-
Case discussions, News & Journals' summaries