The novel artificial intelligence (AI)-based Molecular Twin Precision Oncology Platform may be capable of identifying biomarkers that may outperform the standard test for predicting pancreatic cancer survival, according to a recent study published by Osipov et al in Nature Cancer.
Background
Pancreatic ductal adenocarcinoma, the most aggressive type of pancreatic cancer, develops in the cells lining ducts that carry digestive enzymes from the pancreas to the small intestine.
“[The] Molecular Twin [tool], which we developed at Cedars-Sinai, can be used to study any tumor type—including pancreatic cancer, which is notoriously difficult to treat,” explained senior study author Dan Theodorescu, MD, PhD, Director of Cedars-Sinai Cancer and Distinguished Chair of the PHASE ONE Foundation. “Using our [novel] technology, we anticipate creating tests that can be used even in locations that lack access to advanced resources and technology, pairing patients with the most effective therapies and expanding the availability of precision medicine,” he continued.
Study Methods and Results
In the recent study, researchers used the Molecular Twin tool to examine the blood and tissue samples from 74 patients with pancreatic ductal adenocarcinoma. They first combined 6,363 different biological data points such as genetic and molecular information to create a model that could accurately predict disease survival in 87% of patients. The researchers then used AI to streamline the data and develop a tool that could perform nearly as well with just 589 data points. They further determined that blood proteins were the most effective single predictors of pancreatic cancer survival.
Launched in 2021, the Molecular Twin tool outperformed the only U.S. Food and Drug Administration–approved pancreatic cancer test: the CA 19-9 blood test. The researchers used independent data sets from The Cancer Genome Atlas, Massachusetts General Hospital, and Johns Hopkins University to validate their findings.
“There’s a huge unmet need for the development of biomarkers to guide our treatment of pancreatic cancer,” stressed lead study author Arsen Osipov, MD, Assistant Professor of Medicine and Program Lead in the Pancreatic Cancer Multidisciplinary Clinic and Precision Medicine Program at Cedars-Sinai Cancer. “We had already undertaken a comprehensive collection of blood and tissue samples from patients with pancreatic cancer, and this gave us a good opportunity to test the Molecular Twin [tool]. As we grow the platform with more patients, [the novel tool] will become … even more robust, not just in pancreatic cancer, but across all cancers,” he highlighted.
Conclusions
Although the new research showed genetic information was helpful in predicting a patient’s risk of developing cancer and the subtyping of the cancer, proteins may be the key to predicting patient survival.
“Once a patient has cancer, proteins act as the body’s first responders, and their activity helps us determine how a patient’s body is reacting,” revealed co–study author Jennifer Van Eyk, PhD, Director of the Advanced Clinical Biosystems Institute in the Department of Biomedical Sciences at Cedars-Sinai. “Proteins turned out to be the main drivers of our pancreatic cancer models, and in future studies, proteins will also help us track how well a patient is responding to treatment,” she suggested.
The researchers noted that the initial use of the Molecular Twin tool aimed to develop tests to guide the treatment of patients with pancreatic cancer; however the tool and its uses will continue to expand. The researchers are currently incorporating data from a larger number of patients and branching out to include additional data types such as medical imaging, samples of the gut microbiome and tumor microenvironment, and feedback from wearable devices that measure physical activity.
“A majority of our patients [with cancer] are allowing us to include their clinical information and samples from [their] blood, tumor, and other sources so that we can continue to build the Molecular Twin [tool],” Dr. Theodorescu underscored. “This rich pool of data will help us discover biomarkers for additional cancer types and eventually lead to the development of new treatments and the opportunity to identify at-risk patients before their cancer develops—so we can prevent it entirely,” he concluded.
Disclosure: The research in this study was supported by a grant from the National Institutes of Health, a Conquer Cancer Foundation ASCO Career Development Award, and a grant from the U.S. Department of Defense Congressionally Directed Medical Research Programs. For full disclosures of the study authors, visit nature.com.
