Artificial Intelligence Designs a Cancer Drug

Monday, 04 August 2014 - 12:46PM
Technology
Medical Tech
Monday, 04 August 2014 - 12:46PM
Artificial Intelligence Designs a Cancer Drug

Is artificial intelligence the future of drug discovery? Where cancer drugs usually take 24 to 48 months and approximately $100 million to create in a lab (and even after all this, 95% of the drugs are found to be ineffective in trials), an artificial intelligence has developed a drug essentially on its own in half the time.

 

The biotech start-up Berg has begun human trials for the first cancer drug that was developed by an artificial intelligence. The drug was designed not by extracting chemical compounds in a lab, but by comparing thousands of data points from tissue, urine, and blood samples from both cancer patients and healthy patients. By analyzing this data, the program finds differences that could lead to a treatment or cure. 

 

This particular drug, called BPM 31510, attempts to restore normal cell death processes by modifying the behavior of mitochondria. Mitochondria are generally responsible for triggering death in damaged cells, but this process malfunctions in cancer patients, allowing the damage to spread. With this drug, Berg aims to change the metabolic environment inside the mitochondria in patients with cancer in order to help them function normally.

 

"BPM 31510 works by switching the fuel that cancer likes to operate on. Cancer cells prefer to operate in a less energy-efficient manner," says Berg president and co-founder Niven Narain. "Cancers with a high metabolic function, like triple negative breast cancer, glioblastoma, and colon cancer--that's the sweet spot for this technology."

 

Not only is the drug itself potentially groundbreaking, but the fact that it was designed by a data-driven artificial intelligence signifies a breakthrough for repairing the inefficiencies of the drug discovery system. According to Narain, "If all of us in pharma worked in any other industry, we would be fired, because one out of every 1,000 compounds makes it to an approved drug." If artificial intelligence could take on the busy work of drug development, it would save an incalculable amount of time, money, and man hours. 

Science
Artificial Intelligence
Technology
Medical Tech

Load Comments