What question did this study set out to answer?

The aim is to identify molecular biomarkers and therapeutic targets in pancreatic ductal adenocarcinoma through transcriptomic analysis and machine learning.

May 30, 2026

Integrated transcriptomic profiling and explainable machine learning to reveal functional reprogramming and biomarker candidates in pancreatic ductal adenocarcinoma.

Key Points

The aim is to identify molecular biomarkers and therapeutic targets in pancreatic ductal adenocarcinoma through transcriptomic analysis and machine learning.
Gene expression analysis from 146 pancreatic tissue samples (72 normal, 74 tumor) using the Pan-Cancer Atlas (TCGA).
Differential expression analysis performed with DESeq2 and functional enrichment via GO and KEGG.
XGBoost algorithm used for classification; model interpretability assessed with SHAP values.
Significant dysregulation of genes like GJB3, S100A2, MSLN, and SLC2A1 was identified, indicating impaired exocrine function.
The classification model achieved an average AUC of 0.9868 and an accuracy of 98.6%.
Six genes were identified as both differentially expressed and key predictive features, supporting their role as robust biomarkers.

Abstract

e16002 Background: Pancreatic ductal adenocarcinoma (PDAC) is among the most aggressive and lethal malignancies of the digestive tract, with a five-year survival rate below 5%. Late diagnosis, high tumour heterogeneity, and limited therapeutic efficacy highlight the urgent need to identify molecular biomarkers and therapeutic targets. This study combines transcriptomic analysis with interpretable machine learning to characterise key functional alterations in PDAC. Methods: Gene expression data from 146 pancreatic tissue samples (72 normal and 74 tumour) were obtained from the Pan-Cancer Atlas (TCGA). Differential expression analysis was performed using DESeq2, followed by functional enrichment analysis via GO and KEGG. A classification model was built using the XGBoost algorithm and evaluated with 500 bootstrapping iterations. Model interpretability was assessed through SHAP (SHapley Additive exPlanations) values to identify genes with the highest predictive contribution, which were then cross-referenced with differentially expressed genes. Results: A comprehensive transcriptomic analysis revealed significant dysregulation of multiple genes between normal and tumor pancreatic tissues. Genes such as GJB3, S100A2, MSLN, and SLC2A1 were notably overexpressed, whereas DEFA6, APOB, and RBP2 exhibited marked downregulation, indicative of impaired exocrine function and aberrant epithelial reprogramming. The XGBoost classification model achieved an average area under the curve (AUC) of 0.9868 and an overall accuracy of 98.6%. SHAP (SHapley Additive exPlanations) analysis identified GJB3, LINC02086, and TSPAN1 as key predictive features. Six genes were concurrently identified as differentially expressed and highly influential within the model, supporting their potential utility as robust biomarkers for pancreatic tumor characterization. Conclusions: Pancreatic ductal adenocarcinoma is marked by extensive transcriptomic reprogramming. The integration of differential gene expression analysis with interpretable machine learning enabled the identification of a molecular signature with potential diagnostic and therapeutic relevance.

Demander à l'IA

Bookmark