This study integrates single-cell RNA sequencing and spatial transcriptomic data from 17 human pancreatic cancer tissues to reveal a comprehensive landscape of pancreatic cancer cells and cancer-associated fibroblasts (CAFs). The analysis identified five distinct functional subclusters of pancreatic cancer cells and six distinct CAF subclusters. A novel cancer cell subcluster, Ep_VGLL1, was discovered, showing intermediate characteristics between the classical and basal-like subtypes, despite its prognostic value. The molecular features of Ep_VGLL1 suggest its transitional properties between the classical and basal-like subtypes, supported by spatial transcriptomic data. This integrative analysis provides a detailed understanding of the dynamic states of pancreatic cancer cells and identifies potential therapeutic targets. The study also highlights the importance of understanding the transition from classical to basal-like subtypes in the context of chemoresistance and drug resistance.This study integrates single-cell RNA sequencing and spatial transcriptomic data from 17 human pancreatic cancer tissues to reveal a comprehensive landscape of pancreatic cancer cells and cancer-associated fibroblasts (CAFs). The analysis identified five distinct functional subclusters of pancreatic cancer cells and six distinct CAF subclusters. A novel cancer cell subcluster, Ep_VGLL1, was discovered, showing intermediate characteristics between the classical and basal-like subtypes, despite its prognostic value. The molecular features of Ep_VGLL1 suggest its transitional properties between the classical and basal-like subtypes, supported by spatial transcriptomic data. This integrative analysis provides a detailed understanding of the dynamic states of pancreatic cancer cells and identifies potential therapeutic targets. The study also highlights the importance of understanding the transition from classical to basal-like subtypes in the context of chemoresistance and drug resistance.