New Techniques to Improve Pancreatic Cancer Patient Care

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

Cedars-Sinai Cancer researchers used the Molecular Twin Precision Oncology Platform, a novel precision medicine and artificial intelligence (AI) platform, to find biomarkers that outperformed the usual test for predicting Pancreatic Cancer Patient Care. Their research, published in Nature Cancer, illustrates the feasibility of a tool that could one day guide and improve cancer treatment for all patients.

“Molecular Twin, which we developed at Cedars-Sinai, can be used to study any tumor type, including pancreatic cancer, which is notoriously difficult to treat,” said Dan Theodorescu, MD, Ph.D., director of Cedars-Sinai Cancer Center and the PHASE ONE Foundation Distinguished Chair, the study’s senior author. “Using our Molecular Twin 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.”

The Molecular Twin platform was utilized by researchers to evaluate blood and tissue samples from 74 individuals suffering from pancreatic ductal adenocarcinoma, the most common and aggressive form of pancreatic cancer. The disease starts in the cells lining the ducts that transport digestive enzymes from the pancreas to the small intestine.

The researchers first collected 6,363 different biological data points, including genetic and molecular information, to develop a model that correctly predicted illness survival in 87% of patients. The scientists then applied AI to simplify the data, resulting in a model that performed almost as well with only 589 data points. Further investigation revealed that blood proteins were the best single predictor of pancreatic cancer survival.

The full and simplified models, as well as the blood-protein test, performed better than the sole FDA-approved pancreatic cancer blood test, CA 19-9. The findings were validated using separate datasets from The Cancer Genome Atlas, Massachusetts General Hospital, and Johns Hopkins University.

Cedars-Sinai Cancer’s Molecular Twin platform will be introduced in 2021, according to Arsen Osipov, MD, assistant professor of Medicine, program lead in the Pancreatic Cancer Multidisciplinary Clinic and Precision Medicine Program, and study’s first author.

“There’s a huge unmet need for the development of biomarkers to guide our treatment of pancreatic cancer,” Arsen Osipov, said. “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 platform. As we grow the platform with more patients, Molecular Twin will become an even more robust tool, not just in pancreatic cancer, but across all cancers.”

Jennifer Van Eyk, Ph.D., an expert in protein research, director of the Advanced Clinical Biosystems Institute in the Department of Biomedical Sciences at Cedars-Sinai, and a key member of the Molecular Twin team, stated that while genetic information is useful in predicting a patient’s risk of developing cancer and cancer subtyping, this study demonstrates that proteins are critical 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,” said Jennifer Van Eyk. “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.”

While the initial use of Molecular Twin is to develop tests to guide pancreatic cancer treatment, Theodorescu stated that the platform and its applications would continue to grow. Researchers are collecting data from more patients and expanding to include other types of data such as medical imaging, gut microbiome and tumor microenvironment samples, and feedback from wearable devices that assess physical activity.

“A majority of our cancer patients are allowing us to include their clinical information and samples from blood, tumor and other sources so that we can continue to build the Molecular Twin platform,” said Theodorescu. “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 that we can prevent it entirely.

More information: Arsen Osipov et al, The Molecular Twin artificial-intelligence platform integrates multi-omic data to predict outcomes for pancreatic adenocarcinoma patients, Nature Cancer (2024). DOI: 10.1038/s43018-023-00697-7

Source: Cedars-Sinai Medical Center

more recommended stories