A new study published in the Translational Psychiatry journal has described how AI can be used to match the genes behind several illnesses, such as Alzheimer’s disease, bipolar disorder and depression, with drugs that can help treat them.
Using a machine learning technique called network medicine, researchers from Brazil investigated the chemical basis of psychiatric and neurological disorders. This allowed the scientists to link existing drugs that have been approved for one disease to other diseases with chemically similar natures.
Finding additional uses for existing, proven drugs has the advantage of avoiding the long and expensive process to develop new drugs. However, the wealth of information on available drugs and existing disorders presented a challenge to the researchers.
“We are producing much more knowledge than we can absorb. Scientific journals publish more than a million articles per year, so it is impossible to keep abreast of the literature in areas other than one’s research interests,” the study’s principal investigator Helder Nakaya from University of São Paulo’s School of Pharmaceutical Sciences said.
Network medicine applies techniques from network science, such as using AI to process large amounts of data, to the medical field. By using IBM’s Watson for Drug Discovery (WDD) and in-house developed programs, the scientists were able to gather information from millions of scientific articles and build a network of data on disorders, genes and drugs.
“Network medicine uses graph theory to analyse these complex interactions and suggest drugs that have never been tested for the treatment of certain diseases,” Nakaya said. “We organised and structured a network of knowledge about psychiatric and neurological disorders correlating with information about relevant drugs and genes.”
Using AI, the researchers correlated a total of 1,588 genes with 722 drugs, with the potential to help treat a range of conditions including Alzheimer’s disease, Parkinson’s disease, Huntington’s disease, depression, anxiety, bipolar disorder, schizophrenia and autism.
The researchers also developed a new way to screen drugs that can be applied to other disease studies. They also performed another study using the methodology with the aim of re-purposing drugs to treat Covid-19.
“The analysis revealed drugs never before described as alternatives for the treatment of psychiatric and neurological disorders. We hope other researchers will use the list produced by our research to begin testing in vitro, in animals, and in future clinical trials if all goes well to determine whether these drugs do in fact work against the indicated diseases,” said Thomaz Lüscher Dias, first author of the paper.