An artificial intelligence-powered approach reveals novel features of tumor cell metastasis
Eye on Innovation
In a world of ever-faster technical change, Mayo Clinic Laboratories is uniquely positioned to innovate. Collaboration with clinicians pinpoints unmet patient needs and facilitates the development of diagnostic testing that provides answers.
Quantifying malignant stem cells remains a challenge in cancer research. Looking for them is like looking for a shape-shifting needle in a haystack. This makes it difficult for researchers to track the activity of such rare cells and understand their similarities, differences, output, productivity, and potency.
In a recent study, Mayo Clinic researchers developed the first cellular DNA barcoding with a machine-learning approach to reveal previously unknown metastatic behavior of tumor cells. Researchers barcoded the DNA of millions of human ovarian cancer cells and transplanted them in mice, where rare tumor initiating cells and their progenies could be tracked within the primary tumor as well as in every other organ they were spreading into. The entire community of cells generated by a single barcoded cell had identical barcodes. This enabled the tracking of a large number of benign and metastatic clones by sequencing DNA barcodes in tumors and various organs, including blood and ascites.
“Metastasis by nature is grossly inefficient and highly unpredictable. Our new approach allows us to dissect the regenerative, colonizing, and travel history of each barcoded cell competing for resources across an individual’s anatomy,” says Nagarajan Kannan, Ph.D., director of Mayo Clinic’s Stem Cell and Cancer Biology Laboratory.
Using the cellular DNA barcoding approach and a newly developed data analysis system, researchers could track clonal growth dynamics in various metastatic sites and trace it back to its ancestral tumor-initiating cell. They used artificial intelligence to tackle the complex data to identify if the clonal metastatic spread is happening peritoneally or through blood routes.
“It is malignant stem cell tracking at an unprecedented scale. We are essentially tracking the fate of millions of cells from blood to the brain and all vital organs around the body,” says Dr. Kannan. “If we find 10 unique barcodes in a metastatic organ, then we know we have 10 malignant stem cells that have colonized there, and we can track their routes and measure each of their growth activities.”
“The method we developed – Clone Initiating Cell Calculator – is a quantitative approach primarily driven by data and bioinformatics algorithms to provide much-needed resolution for preclinical assessment of malignant stem cell number and type,” says Krishna Kalari, Ph.D., co-senior author.
The ability to monitor clonal activity within a highly heterogeneous disease lends significant insight into the process. If it is found that only a tiny fraction of malignant stem cells can metastasize, then doctors can pinpoint which cells to target for effective treatment.
“We now know that malignant stem cells are not made equal. In most cases, only a small subset can grow to be lethal,” says Dr. Kannan. “We found that clones that were colonizing to the brain, salivary glands, and heart using blood-route had distinct clonal dynamics from clones using peritoneal-route to colonize ovary, kidney, and ascites, suggesting barcoded cells in tumor had distinct malignant behavior.”
These findings put a spotlight on metastasis and allow doctors to see the process more clearly, how the cells in various organs are all connected, and what the sequence of events looks like in any cancer type.
Dr. Kannan hopes to develop a clinical platform that doctors can use to fine-tune cancer treatment.
“We could use this technology to mimic a patients’ cancer cell clonal growth patterns in animals and tailor treatments,” says Dr. Kannan. “Cancer tumors are like honeycombs. We need to find the queen bee. We don’t have to kill every cell in the tumor, we just need to kill the right ones, and the challenge is to find them.”
At Mayo Clinic, this workflow is being used in preclinical research in breast and ovarian cancer and will soon extend to colorectal and pancreatic cancer. This technology can help researchers enhance immunotherapy, study drug resistance, and discover more unknown cancer processes.
Dr. Kannan is confident that this study will help fill the technological gap for cancer researchers.
“We are excited about the knowledge, methods we developed, and utility of those, but we still have a journey ahead of us,” says Dr. Kannan. “This is just the beginning. We are developing the next steps, and Mayo Clinic will be at the forefront of this technology.”
Mayo Clinic’s cardiac (CV) remote monitoring service uses the compact MoMe Kardia cardiac monitoring device that yields a continuous, 24/7 stream of a patient’s ECG and motion data, no matter their location. Any troubling or burgeoning events are observed virtually the moment they occur, allowing one of Mayo Clinic’s certified rhythm analysis technicians to intervene and facilitate care in near real time. And this is only the beginning; remote patient services are the way of the future, and the future is already here.
Tying together the expertise and curiosity of Mayo Clinic autoimmune neurology researchers with eager patients who have rare disease and are looking for answers, the innovative collaboration benefits both patients affected by MOGAD and scientists on the front lines of discovery.
VEXAS syndrome is a severe autoinflammatory disease that results in a spectrum of rheumatologic and hematologic conditions. The underlying cause of newly identified VEXAS (vacuoles, E1 enzyme, X-linked, autoinflammatory, somatic) syndrome — somatic mutations in the UBA1 gene of blood cells — was discovered at the National Institutes of Health (NIH) in 2020. Within six months, Mayo Clinic Laboratories was able to add a UBA1 test to the MayoComplete panel, as the team simultaneously worked on a single gene assay to allow doctors to test specifically for UBA1 mutations to screen patients for VEXAS syndrome. The team opted for a droplet digital PCR test — a novel and highly accurate approach to testing for UBA1 gene mutations.