Doctors meet AI! Powerful algorithm could help researchers understand cancer

A thorough AI algorithm was developed by the University of Miami experts in collaboration with researchers from other countries. It can perform computational analysis in order to identify potential medicines.

Patients suffering from Glioblastoma multiforme (GBM) and other tumours may benefit from the findings of the recent study that was published last Wednesday by researchers at the University of Miami Miller School of Medicine's Sylvester Comprehensive Cancer Centre.

Glioblastoma multiforme, according to the National Health Institute, is a fast-growing variety of central nervous system tumour that arises from glial tissue of the brain and spinal cord and has a distinctive appearance in comparison to normal cells.

Almost 90% of people with glioblastoma, the most prevalent adult primary malignant brain tumour, pass away within 24 months of their diagnosis.

SPINKS

The Substrate Phosphosite-based Inference for the Network of KinaseS (SPINKS) AI method was described in research published on February 2 in the journal Nature Cancer. Two protein kinases connected to tumour advancements in two subtypes of GBM and other cancers were discovered by the AI algorithm.

Protein kinases are crucial targets in precision cancer medication because they can be used to assess a patient's cancer characteristics. The most active kinases that doctors target with medications during cancer treatments are referred to in the study as "master kinases," according to the researchers.

SPINKS, according to research author and deputy director of Sylvester Comprehensive Cancer Centre Antonio Iavarone, MD, will likely play a significant role in the development of new cancer therapies, reported Health News.

"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."

The information from Iavarone's article titled "The Making of the Glioblastoma Classification" from 2021 is expanded in this new study. Previous studies categorised glioblastoma patients according to their chances of surviving and how susceptible their tumours were to medication.

The new study uses a variety of omics platforms, including genes, proteins, fat molecules, epigenetics, and metabolites, to confirm the categorisation of the earlier study. These omic datasets allow SPINKS to create an interactome, a collection of biological interactions that aids in identifying the kinases driving treatment resistance in each subtype of glioblastoma.

The SPINKS research team is certain that it can be simply included in molecular pathology labs. A clinical classifier used in the study can identify the proper subtype of glioblastoma for each patient. Three-quarters of glioblastoma patients may benefit from SPINKS, according to researchers.

The classifications offered by SPINKS, according to Anna Lasorella, MD, co-senior author of the study and professor of biochemistry and molecular biology at Sylvester Comprehensive Cancer, should 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 tumour, ten tumours, however many they import. These classifications can be applied immediately to patient care."

Although SPINKS was initially developed to treat glioblastoma, the AI algorithm can also help with other tumours. The same kinases that cause cancer were discovered in breast, lung, and child brain tumours.

Breast cancer is the second most frequent type of cancer after skin cancer, according to the CDC. However, lung cancer, which was to blame for 23% of cancer fatalities in 2020, was the main "killer cancer".

The research findings from SPINKS, according to Iavarone and his team, could result in a fresh clinical trial.