The Molecular Twin artificial-intelligence platform integrates multi-omic data to predict outcomes for pancreatic adenocarcinoma patients

Abstract

Contemporary analyses focused on a limited number of clinical and molecular biomarkers have been unable to accurately predict clinical outcomes in pancreatic ductal adenocarcinoma. Here we describe a precision medicine platform known as the Molecular Twin consisting of advanced machine-learning models and use it to analyze a dataset of 6,363 clinical and multi-omic molecular features from patients with resected pancreatic ductal adenocarcinoma to accurately predict disease survival (DS). We show that a full multi-omic model predicts DS with the highest accuracy and that plasma protein is the top single-omic predictor of DS. A parsimonious model learning only 589 multi-omic features demonstrated similar predictive performance as the full multi-omic model. Our platform enables discovery of parsimonious biomarker panels and performance assessment of outcome prediction models learning from resource-intensive panels. This approach has considerable potential to impact clinical care and democratize precision cancer medicine worldwide.

Pancreatic Ductal Adenocarcinoma (PDAC): A Review of Recent Advancements Enabled by Artificial Intelligence

“…While most ’biomarker-detecting’ models have addressed one data type, more multi-omics analyses are emerging [ 84 ]. For instance, Osipov et al proposed the Molecular Twin AI platform using clinical and multi-omics data to predict PDAC patients’ outcomes [ 34 ]. Another example by Sinkala et al involves subtyping pancreatic cancer cell lines using multiple biomarkers, including mutation, methylation, protein expression, and miRNA, leading to the identification of two clinically distinct subtypes [ 91 ].…”

“…Numerous studies highlight the significant challenge in the early detection of PDAC, which is frequently diagnosed at and therefore results in predominantly unresectable cases [ 10 , 30 ]. Compounding this issue is the lack of biomarkers outside of the CA-19-9 biomarker, the only FDA-approved biomarker for PDAC [ 15 , 34 ]. Given that approximately 10% of PDAC cases stem from hereditary mutations, there is a pressing need for improving screening methods to identify the remaining 90% of patients who develop sporadic PDAC [ 35 ].…”