Development of a Consensus Molecular Classifier for Pancreatic Ductal Adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) presents a significant challenge, with a five-year survival rate of approximately 10%. Tumor heterogeneity contributes to the limited effectiveness of treatments. Several tumor and stroma molecular classifiers have attempted to clarify this heterogeneity with moderate agreement. Recognizing the complexity introduced by this extensive array of taxonomies, this study aims to develop a consensus molecular classifier by including both tumor and stroma features. We integrated gene expression data through Virtual Microdissection and classified the training samples to apply Machine Learning algorithms for each previous classifier. The consensus classifier was then derived using a Markov Clustering Algorithm, and its association with overall survival was assessed. The results indicated that Elastic-Net emerged as the superior model. We identified two classes for tumor components (Consensus Classical and Consensus Non-classical) and stroma components (Consensus Normal-Immune and Consensus Activated-ECM). The consensus Random Forest achieved a balanced accuracy of 96.33% and 98.92%, respectively. While not consistent across retrospective series, the algorithm ( PDAConsensus ) independently predicted overall survival. We developed a robust consensus classifier for PDAC that integrates tumor and stroma features and made it accessible through the R package PDACMOC ( PDACMolecularOmniClassifier , https://github.com/pavillos/PDACMOC ) and a Shiny app ( https://pdacmoc.cnio.es/ ).