According to a study published in Translational Psychiatry, Artificial Intelligence can increase the effectiveness of drug repositing or research remodeling.
In the study, which was supported by the São Paulo Research Foundation-FAPESP, Brazilian researchers used correlated information on genes associated with approved mental and neurological disorders and drugs for use in the treatment of other diseases, suggesting potential for these diseases. Can interrupt or activate.
The study identified 31 genes and 63 drugs targeting potential candidates for testing against Alzheimer’s disease, Parkinson’s disease, Huntington’s disease, depression, anxiety, bipolar disorder, schizophrenia, and autism. A total of 1,588 genes were correlated with 722 drugs.
In addition to identifying these candidate drugs, the researchers also developed a novel drug screening approach that can be used in the study of other diseases. He then applied the novel method in another study aimed at the reuse of drugs for treatment.
“We are producing more knowledge than we can absorb. Scientific journals publish more than a million articles per year, so the study’s lead investigator, Helder Nakaya, said that it is impossible to keep literature in areas other than more than one research interest.
Nakaya is a professor at the University of Sao Paulo School of Pharmaceutical Sciences (FCF-USP) in Brazil and a senior researcher at the Center for Research in Research for Innovation and Discipline Centers (RIDCs). By FAPESP.
Novel Approach: Network Medicine
The development of medicine requires large amounts of time and money. Repurposing can be an important shortcut as existing drugs have already undergone relevant safety tests. The general approach is to study how drugs and disease share molecular mechanisms.
To make these correlations more effective, researchers used a machine learning approach, known as network medicine, to examine the molecular characteristics and mechanisms of psychiatry and neurological disorders.
Network medicine is an emerging field that combines systems biology and network science to understand how genes interact in disease and health.
“We organized and structured a network of knowledge about psychiatric and neurological disorders that correlated with information about relevant drugs and genes,” Nakaya explained. “Network medicine uses graph theory to analyze these complex interactions and to suggest never tested drugs for the treatment of certain diseases.”
The group used IBM Watson for Drug Discovery (WDD), as well as programs developed in its laboratory, to find information in millions of scientific articles published over the last 50 years and to connect knowledge about disorders, genes, and drugs Built the network.
“IBM WDD can read over 20 million articles faster than a human being. Computers used machine learning algorithms to make correlations based on information in articles, such as gene activation and inhibition by certain substances, and The relationship between these processes and mental health problems. “It’s not magic. You don’t just press a button to get results. It’s hard to identify associations that are important.”
Tool to guide future study
Researchers found completely novel candidates for drug revival studies. “Analysis of drugs described as an alternative to the treatment of psychiatric and neurological disorders has never happened before.
We hope that other researchers will start using the list produced by our research in vitro, in animals, and in future clinical trials, if all goes well to determine if these drugs are used for the indicated diseases.
Really work against, “said Thomas Lusher Dias, the paper’s first author. The study was his Ph.D. research, supported by the coordination of the Ministry of Education for the Improvement of Higher Education Personnel (CAPES) and by Nakaya Supervision was done.
The combination of machine learning and network medicine made the drug revitalization process more effective. Dias said, “Instead of screening 2,000 potential candidates and then testing to determine which of them can cure the disease, our analysis of a smaller and more vocal list of potential candidates It is possible to use the results of the study. ”
In a soon-to-be-published study, the group led by Nakaya carried out laboratory experiments to test the effect of one of the drugs included in the list when used to treat schizophrenia. “We have established a research collaboration to determine if treatment with this drug is effective. Experimental verification is fundamental to prove the usefulness of these analyzes, ”he said.