Pancreatic cancer genome-wide sequencing and the complementary search for targeted therapies against pancreatic cancer have distracted the field from focusing on optimizing one of the most clinically utilized agents (gemcitabine) against this devastating disease. Prospective and randomized clinical trials reveal that a select set of human pancreatic cancers exhibit sensitivity to the chemotherapeutic agent gemcitabine. While this subset is small (for instance, CONKO-001 demonstrates that 10% of patients experience a durable response to gemcitabine in the adjuvant setting), these findings unique to gemcitabine provide a rationale to devise molecular strategies to expand the efficacy to more patients or predict which patients might best benefit from gemcitabine-based therapies. Gemcitabine monotherapy remains the standard of care in the adjuvant setting and a recent positive trial in advanced patients has established gemcitabine-Abraxane as a preferred front line regimen. In the present proposal, we will establish an unprecedented predictive marker for gemcitabine efficacy using samples from a multi-institution phase III trial and develop a biomarker assay applicable to all patients (both localized and advanced). In addition, we will gain insights into molecular mechanisms that govern the metabolism of gemcitabine. In a prior study, we demonstrated that post-transcriptional gene regulation in pancreatic cancer cells plays an important role in gemcitabine efficacy. We demonstrated that the RNA binding protein, HuR (ELAV1), up-regulates deoxycytidine kinase (dCK), an enzyme that produces DNA precursor molecules and also metabolizes the nucleoside analog, gemcitabine. Validating our in vitro findings, patient tumors with increased cytoplasmic HuR protein expression were associated with improved survival after resection in patients treated with gemcitabine. We hypothesize that dCK (stabilized by HuR) efficiently metabolizes the prodrug gemcitabine, thereby enhancing drug efficacy against cancer cells. Recently, we identified CMPK1 and RRM2 as two additional HuR targets that play a Central role in gemcitabine metabolism. Herein, we will 1) firmly establish HuR as a bona fide predictive marker of gemcitabine efficacy for pancreatic cancer treatment using surgical specimens from a multi-institutional, randomized, clinical trial of adjuvant gemcitabine therapy for pancreatic cancer (ESPAC3); 2) evaluate the feasibility and accuracy of cytologic aspirates to determine HuR status (compared to surgical specimens), which will expand the relevance of the test to patients with advanced disease; and 3) determine precisely how HuR regulates gemcitabine efficacy (both as single agent and with Abraxane) through biochemical and cellular assays, and spectroscopic analyses of gemcitabine metabolites in pancreatic cancer cells. We expect results of these studies to yield immediate improvement in our ability to identify which patients are most likely to benefit from gemcitabine-based therapies. In addition, we expect that mechanistic insights gained into HuR's global control of gemcitabine metabolism will eventually lead to therapeutic strategies that enhance gemcitabine response.