Computational theranostics strategy for pancreatic ductal adenocarcinoma.

Abstract

Pancreatic ductal adenocarcinoma (PDAC) is a formidable challenge in modern medicine, characterized by its insidious progression, early systemic metastasis, and alarmingly low survival rates. Given its clinical challenges, improving detection strategies for PDAC remains a critical area of research. This study has used advanced computational approaches to predict pancreatic adenocarcinoma-associated target genes using transcriptomics datasets. Predictive machine learning models were trained using the identified gene signatures, highlighting their potential relevance for future research into diagnostic strategies for PDAC. A total of thirteen differentially expressed genes (DEGs) associated with PDAC were identified, of which twelve were upregulated (CEACAM5, CEACAM6, CTSE, GALNT5, LAMB3, LAMC2, SLC6A14, TMPRSS4, TSPAN1, ITGA2, ITGB6, and POSTN) and one was down regulated (IAPP). These DEGs are all linked to cancer-associated pathways and potentially play a role in the growth and development of cancer. Furthermore, virtual screening evaluated the upregulated SLC6A14 gene-encoded protein for therapeutic repurposing, revealing promising candidates for PDAC treatment. This study offers exploratory insights into gene expression patterns and molecular biomarkers that may inform future research to improve PDAC prognosis and therapeutic development and provide the repurposed drug candidate for further exploration.