Scientists Develop Powerful AI Algorithm for More Cancer Understanding

A new study released last Wednesday by Scientists at Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine may provide treatment insight for glioblastoma multiforme (GBM) and other cancers.

Key takeaways:

The University of Miami scientists, along with international researchers, created a detailed AI algorithm that is able to execute computational analysis in order to recognize future therapeutics.

Findings could benefit glioblastoma patients, a deadly condition, and cancer treatment production.

The National Health Institute says glioblastoma multiforme is a fast-growing form of central nervous system tumor that derives from glial tissue of the brain and spinal cord, containing a unique look compared to normal cells.

Glioblastoma is the most common adult primary malignant brain tumor, causing 90% of patients to pass within 24 months following diagnosis.

Research released on February 2, in the journal Nature Cancer, details the AI algorithm referred to as Substrate PHosphosite-based Inference for Network of KinaseS (SPINKS). The AI algorithm helped locate two protein kinases associated with tumor advances in two subtypes of GBM and other forms of cancer.

Precision cancer medicine uses protein kinases as vital targets to help determine a patient’s cancer properties. In the study, researchers label "master kinases" as the most active kinases that are targeted by clinicians with drugs and therapeutics during cancer treatments.

Author of the study, Antonio Iavarone, M.D., and deputy director of Sylvester Comprehensive Cancer Center believes SPINKS will have a big part to play in future cancer treatments.

"Our work represents translational science that offers immediate opportunities to change the way glioblastoma patients are routinely managed in the clinic," Iavarone said in a news release. "Our algorithm offers applications to precision cancer medicine, giving oncologists a new tool to battle this deadly disease and other cancers as well."

This new study builds on Iavarone’s research from 2021, in a piece titled "The Making of the Glioblastoma Classification." Previous research listed a new glioblastoma classification by grouping glioblastoma patients based on their likelihood of survival and their tumor’s vulnerability to drugs.

The new investigation is able to confirm the previous research’s classification through multiple omics platforms, featuring genes, proteins, fat molecules, epigenetics, and metabolites. Those omic datasets enable SPINKS to construct an interactome, which is a set of biological interactions that help discover the kinases creating tumor growth treatment resistance in each glioblastoma subtype.

Scientists involved with the SPINKS research believe it can be easily inputted into molecular pathology labs. The study includes a clinical classifier that can match the correct glioblastoma subtype to each patient. Researchers believe SPINKS can help benefit three-quarters of glioblastoma patients.

Co-senior author of the study and professor of biochemistry and molecular biology at Sylvester Comprehensive Cancer, Anna Lasorella, M.D., believes the classifications provided by SPINKS need to be used as soon as possible.

"This classifier can be used in basically any lab," Lasorella said. "By importing the omics information into the web portal, pathologists receive classification information for one tumor, ten tumors, however many they import. These classifications can be applied immediately to patient care."

Initially, SPINKS was intended for glioblastoma, but the AI algorithm is able to assist with other forms of cancers. Researchers located the identical cancer-driving kinases in breast, lung, and pediatric brain tumors.

According to the CDC, breast cancer is the second most common form of cancer behind skin cancer. However, lung cancer was the leading cause of cancer death in 2020, responsible for 23% of cancer deaths.

Iavarone and his team of researchers believe the findings from SPINKS may lead to a new clinical trial.

"We are exploring the concept of basket trials, which would include patients with the same biological subtype but not necessarily the same cancer types. If patients with glioblastoma or breast or lung cancer have similar molecular features, they could be included in the same trial," Iavarone said. "Rather than doing multiple trials for a single agent, we could conduct one combined trial and potentially bring more effective drugs to more patients faster."


Leave a reply

Your email will not be published. All fields are required.