Deep learning-based pathway-centric approach to characterize recurrent hepatocellular carcinoma after liver transplantation.

ABSTRACT:

Background

Liver transplantation (LT) is offered as a cure for Hepatocellular carcinoma (HCC), however 15-20% develop recurrence post-transplant which tends to be aggressive. In this study, we examined the transcriptome profiles of patients with recurrent HCC to identify differentially expressed genes (DEGs), the involved pathways, biological functions, and potential gene signatures of recurrent HCC post-transplant using deep machine learning (ML) methodology.

Materials and methods

We analyzed the transcriptomic profiles of primary and recurrent tumor samples from 7 pairs of patients who underwent LT. Following differential gene expression analysis, we performed pathway enrichment, gene ontology (GO) analyses and protein-protein interactions (PPIs) with top 10 hub gene netwo

SUBMITTER: To J 

PROVIDER: S-EPMC11151487 | biostudies-literature | 2024 Jun

REPOSITORIES: biostudies-literature