New computational strategy designed for more personalized cancer treatment

Simplifying complex biomolecular data about tumors.

cancer cell made in 3d software
cancer cell made in 3d software Image: Shutterstock

Scientists at the Johns Hopkins University have developed a new computational strategy that changes exceedingly complex data into a rearranged arrange that accentuates persistent to-understanding variety in the sub-atomic marks of tumor cells. This novel strategy could improve complex biomolecular information about tumors, on a fundamental level.

Scientists actually wanted to introduce this methodology in order to prescribe the appropriate treatment for a specific patient.

Donald Geman, a professor in the Department of Applied Mathematics and Statistics who was senior author of the study said, “One of the things that people in this field have noticed over the past 10 years—and, in fact, it has been startling—is how much heterogeneity there is even between two patients with the same subtype of cancer. By that, I mean that in two patients who were both diagnosed with melanoma, the skin lesions may look quite similar to the naked eye but the cancerous cells may be very different at the molecular level. They may have different forms of dysregulation, including different genetic variants and different gene expression profiles.”

Knowing as much as could be expected about the hereditary cosmetics and hindered organic pathways of a specific patient could enable doctors to settle on more educated choices about the forecast and treatment, changing them to the specific sub-atomic profile.

Geman said, “They want to know if they are looking at a profile of a woman who likely will or will not respond to a particular drug. Or does the data indicate the patient will likely relapse within the next five years? Or does a man have a particularly aggressive type of prostate cancer? Or is it necessary to surgically remove the lymph nodes to determine the presence or absence of metastases in a patient with some form of head and neck cancer?”

Scientists envisioned the bloodwork summaries commonly produced when a patient visits a doctor for an annual physical exam in order to provide answers to the questions. These for the most part report whether glucose, cholesterol, and different outcomes are inside or are outside of solid levels.

Taking a sign from these tests, scientists figured out how to greatly simplify the information on tens of thousands of molecular states by converting these data to binary labels, indicating whether a measurement falls within or beyond healthy levels.

Geman, who previously devoted many years to improving computer vision technology, is encouraged by the cancer-related project and hopes it will serve as a model for other fruitful collaborations involving advanced math and medicine.

“The goal,” he said, “is taking classification problems of genuine clinical interest and producing an algorithm that is accurate, interpretable and makes sense biologically.”

Co-lead authors of the PNAS article were Wikum Dinalankara, an oncology fellow at the Johns Hopkins Kimmel Cancer Center and the Johns Hopkins University School of Medicine; and graduate student Qian Ke of the Department of Applied Mathematics and Statistics in the university’s Whiting School of Engineering. Co-authors from these two departments were Yiran Xu, Lanlan Ji, Nicole Pagane, Anching Lien, Tejasvi Matam, Elana J. Fertig, Laurent Younes and Luigi Marchionni. Another co-author, Nathan D. Price, was from the Institute for Systems Biology in Seattle.

The research is detailed recently in the journal Proceedings of the National Academy of Sciences.