This research investigates metabolic differences in ductal carcinoma in situ (DCIS) to predict breast cancer recurrence. Using gene expression data and computational modeling, it identifies increased fatty acid synthesis as a potential biomarker of recurrence. The work aims to improve risk prediction and personalize prevention strategies across diverse patient populations.

This research develops peptide-based drug delivery systems to improve cancer treatment targeting. Unlike conventional therapies, peptides can selectively bind tumors, reducing systemic side effects. Using AI to design high-affinity sequences, the system enhances precision delivery and efficacy, demonstrated by reduced tumor growth in vivo compared to non-targeted treatments.