AI Platform Can Identify Personalized Drug Combinations to Treat Multiple Myeloma

August 16, 2018

A new technology platform utilizing artificial intelligence (AI) could change how drug combinations are designed and help doctors to identify optimal personalized drug combinations for patients with multiple myeloma.

A new technology platform could change how drug combinations are designed and help doctors to identify optimal personalized drug combinations for patients with multiple myeloma (MM), according to research published in Science Translational Medicine.

Researchers at the National University of Singapore (NUS) used an artificial intelligence (AI) technology platform, called Quadratic Phenotypic Optimisation Platform (QPOP), to not only establish new drug combinations, but also to identify patients who might be more responsive.

QPOP can use a small amount of blood or bone marrow sample to map the drug response for a specific patient’s cancer cells. The researchers used a pool of 114 FDA-approved oncology drugs and identified a new combination that outperformed standard of care for relapsed MM.

Read more about how AI is being used in medicine.

In the case of MM, drug combinations are used for first and secondary lines of treatment and proteasome inhibitors, like bortezomib (Bort), are often used to improve median survival. The problem, noted the authors, is that resistance to Bort is common and results in treatment failure.

“Thus, identifying effective drug combinations against Bort-resistant MM may lead to the development of improved secondary lines of treatment in the context of refractory or relapsed MM after Bort treatment,” they explained.

From the 114 drugs, the researchers identified candidate drugs and FDA drugs approved to treat MM. They used the resulting 14 drugs in a QPOP analysis. Through the analysis with QPOP, the investigators were able to identify the top 2-drug combinations: dactinomycin and mitomycin C, followed by Bort and mechlorethamine hydrochloride.

“QPOP revolutionizes the way in which drug combinations are designed and represents a key area in healthcare that can be transformed with AI,” Edward Kai-Hua Chow, PhD, principal investigator at the Cancer Science Institute of Singapore at NUS, who led the study, said in a statement. “The efficiency of this platform in utilizing small experimental data sets enables the identification of optimal drug combinations in a timely and cost-efficient manner, which marks a big leap forward in the field of personalized medicine.”

The researchers are now working to translate their findings into the clinic and are recruiting patients for prospective clinical trials in 2019.

Reference

Rashid MBMA, Toh TB, Hooi L, et al. Optimizing drug combinations against multiple myeloma using a quadratic phenotypic optimization platform (QPOP). Sci Transl Med. 2018:8;10(453). doi: 10.1126/scitranslmed.aan0941.