Using artificial intelligence to improve tuberculosis treatments
A medical illustration of drug-resistant, Mycobacterium tuberculosis bacteria, presented in the Centers for Disease Control and Prevention (CDC) publication entitled, Antibiotic Resistance Threats in the United States, 2019 (AR Threats Report). Credit: Medical Illustrators: Alissa Eckert; James Archer

There are 20 new compounds that have shown some effectiveness in treating a disease like Tuberculosis, which affects 10 million people worldwide and kills 1.5 million annually. For effective treatment, patients will need to take a combination of three or four drugs for months or even years because the Tuberculosis bacterium behave differently in different environments in cells. There are twenty compounds in three and four drug combinations. Which drugs should be tested together?

The study was published in the September issue of Cell Reports Medicine and used data from large studies that contained laboratory measurement of two-drug combinations of 12 anti-tuberculosis drugs. The team used mathematical models to find a set of rules that drug pairs need to satisfy in order to be good treatments.

Drug pairs cut down on the amount of testing that needs to be done before moving a drug combination into further study.

"If we use the design rules we've established and tested, we can substitute one drug pair for another drug pair and know with a high degree of confidence that the drug pair should work in concert with the other drug pair to kill the Tuberculosis in theRodent model," said The selection process we developed is more efficient in predicting success than previous processes, which may have considered less combinations.

The lab of Aldridge, who is also an associate director of the Stuart B. Levy Center for Integrated Management of Antimicrobial Resistance, has previously developed and used a method to study pairwise and high-level drug interactions. The speed at which scientists determine which drug combinations will most effectively treat Tuberculosis can be increased with the design rules established in this study.

More information: Jonah Larkins-Ford et al, Design principles to assemble drug combinations for effective tuberculosis therapy using interpretable pairwise drug response measurements, Cell Reports Medicine (2022). DOI: 10.1016/j.xcrm.2022.100737 Journal information: Cell Reports Medicine