Abstract 2769: Project Survival: Prospective clinical study utilizing multiomics and artificial intelligence to discover novel molecular markers for detection, stratification, and outcome in pancreatic cancer
2017
Pancreatic adenocarcinoma is the third leading cause of cancer death and has an extremely poor response to first line therapies. There is a critical unmet need to discover and implement effective diagnostic panels to stratify this disease and personalize treatment. Project Survival is a prospective study designed to discover biomarkers for patient diagnosis, stratification, and prognostics for pancreatic cancer. The multisite study is in year 2 of enrolling subjects within 6 categories: healthy volunteers with a relative with pancreatic cancer (N=50), pancreatitis (N=50), pancreatic cystic neoplasm (N=50), suspicious pancreatic masses with pathology other than pancreatic cancer (N=50), early stage (N=200) and metastatic pancreatic cancer (N=200). The study analyzes matched subject sera, plasma, buffy coat, saliva, urine, and tumor/adjacent normal tissues and integrates them with full clinical annotation. Multiple time points per subject per year are taken longitudinally over the course of the six year timeline enabling dynamic modeling. Samples are analyzed by Mass Spectrometry for the proteome, signaling lipidome, structural lipidome, and metabolome. The BERG Interrogative Biology® platform utilizes Artificial Intelligence to integrate multiomic profiles with medical annotation and clinical endpoints. Utilizing the power of the Bayesian Network learner, bAIcis™ (BERG Artificial Intelligence Clinical Information System), multiomic profiles were aligned to the longitudinal clinical information and subjected to the AI-algorithms that inferred probabilistic cause-and-effect relationships among molecular and clinical variables inferring markers of pancreatic cancer status and defining the interconnectivity of molecular features with clinical phenotype. Network features linking clinical endpoints and key network pressure points will be identified as molecular drivers. The drivers of clinical endpoints will be analyzed to rank potential biomarkers. Citation Format: Rangaprasad Sarangarajan, John Crowley, Amy Stoll-D9Astice, Valerie Bussberg, Cindy Nguyen, Leonardo O. Rodrigues, Emily Chen, Eric Michael Grund, Vivek K. Vishnudas, Michael Kiebish, Viatcheslav R. Akmaev, Manuel Hidalgo, Niven R. Narain, A. James Moser. Project Survival: Prospective clinical study utilizing multiomics and artificial intelligence to discover novel molecular markers for detection, stratification, and outcome in pancreatic cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 2769. doi:10.1158/1538-7445.AM2017-2769
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI