Researchers from Massachusetts have developed a data-driven system using artificial intelligence to discover various drug combinations to treat tuberculosis
Research to find drug combinations (Credit: Chokniti Khongchum/pexels)
Recently, new antibiotics have been developed which can treat TB successfully as tuberculosis is the second leading infectious disease in the world. Researchers are finding it difficult to determine which drugs will work best in combination, as it’s a mathematically complex, expensive, and time-consuming process. Hence, to overcome this hurdle, researchers from Tufts University used machine learning to design a data-driven solution that will allow researchers to consider novel drug combinations at a new scale. The new system would be capable to reduce the time and cost of scientists to determine which drug combinations will effectively treat tuberculosis.
“Our framework creates accurate predictions of how effective treatments will be when we move from testing in a lab to testing in mouse models, which is an important step in choosing which treatments progress to human clinical trials,” says Bree Aldridge, associate professor of molecular biology and microbiology at Tufts University School of Medicine and of biomedical engineering at the School of Engineering, and a member of the immunology and molecular microbiology program faculty at the Graduate School of Biomedical Sciences. “It provides a more efficient avenue for determining what multi-drug treatments should be moved to preclinical studies. And it provides interpretable rules to help researchers and drug developers construct their optimal combinations of drugs to test.”
The researcher included data from large studies that consisted of laboratory measurements of two and three-drug combinations of twelve commonly used anti-tuberculosis drugs. They discovered a set of rules that drug pairs need to satisfy to obtain efficient treatments by implementing mathematical models and artificial intelligence. The system and use of drug pairs reduce the amount of testing that is essential before using a drug pair for further study.
It is necessary to discover new cocktail combinations that work well and are better than the existing mix and can treat the disease more quickly than four to six months to get better control over this contagious and deadly disease.
Click here for the Published Research Paper