2024-10-29 11:45:00
When a machine learning algorithm (a form of artificial intelligence) is used to predict which diseases a drug designed for other uses might be used for (a repurposing known as “repurposing”), the algorithm can recommend some drugs, but does not explain any the reason. , and this raises doubts about the reliability of the prediction. Therefore, it would be ideal to have a repositioning mechanism that also explains why it predicts the way it will unfold.
This is where a group of researchers from the Polytechnic University of Madrid (UPM) in Spain stepped in and provided a solution. The team has just developed a drug repositioning method with a clear emphasis on interpretability, as they aim for the system to offer explanations as to why it proposes to treat disease X with drug Y.
This new algorithm – called “XG4REPO” (eXplainable Graphs for Repurponendo) – not only repositions, but also presents the results in an understandable way, indicating which biological mechanisms are used for prediction. This allows your predictions to be validated by medical experts, who can immediately assess whether it is a valid explanation or not, thus generating much more robust predictions and saving time that would otherwise be spent searching for explanations.
The process of creating medicines is slow and expensive, as it involves numerous tests to ensure the safety of the new medicine in order to obtain marketing authorization from the health authorities. An alternative that is increasingly gaining strength to alleviate this situation is the repositioning of existing drugs, which consists of identifying new applications for already approved drugs. This means using an existing drug to treat a different disease than the one you had in mind when the drug was designed.
Drug repositioning, as a technique, has a number of advantages that cannot be ignored. The first is that it allows the drug development time to be significantly shortened, since the drug is approved and its side effects are known. The second great advantage is linked to the cost of developing the drug, which does not require the repetition of expensive safety tests, first on animals and then in clinical studies. Likewise, most drugs developed in laboratories do not reach the market due to their adverse effects, a problem that repositioning does not present.
These advantages allow us to consider repositioning a technique capable of introducing important changes in medicine. On the one hand, it allows us to develop treatments for new diseases much more quickly than creating a drug from scratch. During the COVID pandemic, for example, repositioning has made headlines for attempts to use different drugs to treat this new disease. But, furthermore, repositioning represents great hope for patients suffering from rare diseases, as it would allow the laboratory to develop low-cost treatments.
Symbolic artistic recreation of the concept of rapidly finding new uses of drugs using artificial intelligence. (Illustration: Amazings/NCYT)
On a technical level, a drug influences a specific biological process; Paracetamol, for example, blocks part of the human body’s pain impulse. The big challenge of repositioning is identifying which patterns, influenced by a specific drug, appear in other diseases. Therefore, if two diseases have a similar trend and a certain drug is used to treat the first, it is likely that it can also be used for the second. But performing this pattern identification by experts is an expensive process that requires in-depth knowledge of diseases and their mechanisms. On the other hand, currently available machine learning techniques are very effective in detecting these patterns, hence the great interest that has recently arisen in drug repositioning using artificial intelligence.
However, AI techniques have the problem of interpretability. In an attempt to solve it, the team led by Ana Jiménez, from the Polytechnic University of Madrid (UPM) found the solution to the described problem thanks to the design of a new algorithm that she and her colleagues called “XG4Repo”. This provides a framework for drug repurposing using knowledge graphs that predict diseases that can be treated with a given compound. Along with the prediction, the model provides the rules that support the prediction and the importance of the rule.
To demonstrate the effectiveness of “XG4REPO”, the researchers tried to predict the application of three well-known anticancer drugs and found that, among the algorithm’s predictions, there were many that were already in the early stage of clinical trials . This means that there is medical evidence that validates the predictions made by “XG4REPO”. Therefore, as Professor Santiago Zazo, who was part of the working group, underlines, “this mechanism constitutes a further step towards the application of artificial intelligence techniques in the medical field, not to replace experts, but to facilitate their analysis ”. of a large amount of data in a short time and accelerate the drug development process.”
Ana Jiménez and her colleagues present the technical details of their new algorithm in the academic journal Scientific Reports, under the title “Explainable drug repurusing via path based knowledge graph completion”. (Source: UPM)
#Artificial #intelligence #find #drugs #record #time