Artificial intelligence could be used to improve tuberculosis treatments
Researchers at Tufts University, in Boston, United States, conducted a study published in Cell Reports Medicine that ensures that the artificial intelligence could be used to improve tuberculosis treatmentscurrently considered complex.
Tuberculosis affects 10 million people worldwide and kills 1.5 million each year. For effective treatmentpatients need to take a combination of three or four drugs for months or even years because bacteria behave differently in cells and, in some cases, evolve to become resistant to drugs.
Twenty compounds in three-drug and four-drug combinations offer almost 6,000 possible combinations. In the middle of 2022, it seems that the best idea to speed this up is with the help of artificial intelligence.
Science Daily cites the research, explaining that the experts used data from large studies containing laboratory measurements of combinations ranging from two drugs to 12 anti-TB drugs.
Using mathematical models and supported by an AI called DiaMONDthe team discovered a set of rules that drug pairs must meet to be potentially good treatments as part of three-drug and four-drug cocktails.
Using drug pairs instead of measuring three-drug and four-drug combinations significantly reduces the amount of testing that must be done before moving a drug combination to further study.
Bree Aldridge, associate professor of molecular biology and microbiology in the Tufts University School of Medicine and of biomedical engineering in the School of Engineering, explained: “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 conjunction with the other drug pair to kill the bacteria”.
“The selection process we developed is more agile and more accurate in predicting success than previous processes, which necessarily considered fewer combinations”.
The study’s team of researchers developed the DiaMOND artificial intelligence, a method that studies high-order, pairwise drug-combination interactions to identify shorter and more efficient treatment regimens for tuberculosis and potentially other bacterial infections.