Abstract B109: Reinforcing risk prediction for intraductal papillary mucinous neoplasms of the pancreas with AI-optimized nucleotide-to-amino acid analyses

Abstract

Abstract Intraductal papillary mucinous neoplasms (IPMNs) often precede invasive pancreatic ductal adenocarcinoma, with each IPMN tumor carrying a 10-25% risk of progressing to cancer within 10 years of detection. The objective of this work is to employ AI-augmented analyses of single mutations occurring at specific tri-nucleotide sequences or codons and identify markers associated with the progression of cysts to pancreatic cancer. Despite being precursors of pancreatic cancer there is a lack of validated intervention targets for precision prevention for IPMNs. Currently cancer prevention for patients with IPMN is centered on surgery using a risk-tailored approach; the clinical ability to stratify risk of cancer progression of individual IPMN tumors is poor and essentially no effective non-surgical interventions exist. To advance the precision cancer prevention for IPMNs we develop an intelligent, machine learning (ML) derived framework addressing the challenge of IPMN stratification from samples with limited data space, e.g., somatic mutations. Our study incorporates the text-based statistical and ML analyses of the mutational profiles of patients’ genomes followed by an integration of codon sequence derived mutational features for biomarkers validation. Given the potential of genome spatial organization to understand mutagenesis and genomic instability, we also map the DNA sequence information onto the local spatial genome organization to elucidate intrinsic features and molecular mechanisms that potentially lead to mutations. Results of this study show that information extracted from mutational profiles with the proposed methods significantly improves performance of the ML models in stratification of IPMNs and biomarker identification. We also present how utilization of these ML tools for mutational data, spatial genome organization, and functional analyses from tumor samples, can aid understanding of the underlying mechanisms of mutations in IPMNs and pancreatic cancer. Citation Format: Nam Nguyen, Jamie K. Teer, Margaret A. Park, Patricia McDonald, Jason B. Fleming, Jennifer B. Permuth, Kwang-Cheng Chen, Aleksandra Karolak. Reinforcing risk prediction for intraductal papillary mucinous neoplasms of the pancreas with AI-optimized nucleotide-to-amino acid analyses [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Pancreatic Cancer; 2023 Sep 27-30; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(2 Suppl):Abstract nr B109.