Israeli researchers use artificial intelligence to identify cancer genes


3 min read
Dr. Shai Rosenberg of Hadassah Hospital in Jerusalem.
Hadassah SpokespersonDr. Shai Rosenberg of Hadassah Hospital in Jerusalem.

'The model we created has a high accuracy of 96.5 percent,' says Dr. Shai Rosenberg

For the first time in the world, researchers at Hadassah Hospital in Jerusalem developed an artificial intelligence (AI) algorithm to identify mutations that cause cancer.

The discovery is considered an important breakthrough in cancer research. 

Video poster

The breakthrough could serve as a platform for the development of personalized treatment for carriers of these mutations and successfully combat the cancer from which they suffer. 

The initial development was published in the prestigious journal Briefings in Bioinformatics and has echoed around the world. 

"To understand what we discovered, I'm taking us back a bit," says Dr. Shai Rosenberg, author of the article.

"Cells in the human body where certain genetic changes have occurred are very likely to become cancer cells. Each of us carries a gene called the TP53 gene, whose function is to protect the normal cells of the body by correcting genetic changes. When too many changes occur, the gene causes a planned 'suicide' of the cell, thus preventing the cell from becoming cancerous," Dr. Rosenberg explained.

"A genetic change in the TP53 gene damages the body's defense mechanism and causes cancer, and indeed this mechanism is prevalent and appears in 50 percent of tumors; it is considered the most important gene in cancer biology." ...

This post can't be displayed because social networks cookies have been deactivated. You can activate them by clicking .

“Today, we can already say that carriers of a TP53 gene mutation have an increased risk of developing cancer at an early age,” Dr. Rosenberg pointed out. 

"In the TP53 gene, there are a possible 2,314 different point mutations, some of which cause impairment of gene function and cancer and some of which do not affect the gene at all and therefore have no medical significance," he continued.

After the discovery, the researchers used machine learning methods to train an AI algorithm that "learns" from these mutations and creates a predictive model applied to the 2,314 possible mutations. This model classifies mutations as carcinogenic or neutral. 

"The model we created has a high accuracy of 96.5 percent, which allows for its clinical application," Dr. Rosenberg concluded.

This article received 0 comments