There are more than 7,000 rare and undiagnosed diseases worldwide.
Although each condition occurs in a small number of individuals, collectively these diseases exert a staggering human and economic cost because they affect approximately 300 million people worldwide.
Yet with only 5 to 7 percent of these conditions having an FDA-approved drug, they remain largely untreated or undertreated.
Developing new drugs represents a daunting challenge, but a new artificial intelligence tool may spur the discovery of new treatments from existing drugs, offering hope to patients with rare and neglected diseases and the clinicians who treat them.
The AI ​​model, called TxGNN, is the first developed specifically to identify drug candidates for rare diseases and untreatable conditions.
It identified drug candidates from existing drugs for more than 17,000 diseases, many of them without any existing treatment. This represents the largest number of diseases that any AI model can handle to date. The researchers note that the model could be applied to even more diseases beyond the 17,000 it worked on in the original experiments.
The project, described on September 25 at Nature Medicineled by Harvard Medical School scientists. The researchers have made the tool available for free and want to encourage clinicians to use it in their search for new treatments, especially for conditions with no or limited treatment options.
With this tool we aim to identify new treatments across the disease spectrum, but when it comes to rare, extremely rare and neglected conditions, we predict that this model could help close, or at least reduce, a gap that creates serious inequalities in health”.
Marinka Zitnik, principal investigator, assistant professor of biomedical informatics at the Blavatnik Institute at HMS
“This is where we see the promise of artificial intelligence in reducing the global burden of disease, finding new uses for existing drugs, which is also a faster and more cost-effective way to develop treatments than designing new drugs from scratch,” Zitnik added. . , who is an adjunct faculty member at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University.
The new tool has two central features -? one identifying treatment candidates along with possible side effects and another explaining the rationale for the decision.
In total, the tool identified drug candidates from nearly 8,000 drugs (both FDA-approved and experimental drugs now in clinical trials) for 17,080 diseases, including diseases with no available treatments. It also predicted which drugs would have side effects and contraindications for specific conditions -? something that the current approach to drug discovery determines primarily by trial and error during early safety-focused clinical trials.
Compared to leading AI models for drug repurposing, the new tool was nearly 50 percent better, on average, at identifying drug candidates. It was also 35 percent more accurate at predicting which drugs would have contraindications.
Advantages of using already approved drugs
Repurposing existing drugs is an attractive way to develop new treatments because it is based on drugs that have been studied, have understood safety profiles, and have gone through the regulatory approval process.
Most drugs have multiple effects beyond the specific targets for which they were originally developed and approved. But many of these effects remain unexplored and poorly studied during initial testing, clinical trials, and review, and emerge only after years of use by millions of people. Indeed, nearly 30 percent of FDA-approved drugs have acquired at least one additional therapeutic indication after initial approval, and many have acquired dozens of additional therapeutic indications over the years.
This approach to drug reuse is haphazard at best. It relies on patient reports of unexpected beneficial side effects or doctors’ intuition about whether to use a drug for a condition for which it was not intended, a practice known as off-label use.
“We tend to rely on luck and serendipity rather than strategy, which limits drug discovery to diseases for which drugs already exist,” Zitnik said.
The benefits of drug repurposing extend beyond diseases without cures, Zitnik noted.
“Even for more common diseases with approved treatments, new drugs could offer alternatives with fewer side effects or replace drugs that are ineffective for some patients,” he said.
What makes the new AI tool better than existing models?
Most current AI models used for drug discovery are trained on a single disease or a handful of conditions. Instead of focusing on specific diseases, the new tool was trained in a way that allows it to use existing data to make new predictions. It does this by identifying common features in many diseases, such as common genomic aberrations.
For example, the AI ​​model identifies common disease mechanisms based on common genomic substrates, which allows it to extrapolate from a well-understood disease with known treatments to a poorly understood one without treatments.
This ability, the research team said, brings the AI ​​tool closer to the type of reasoning a human clinician might use to generate new ideas if they had access to all the pre-existing knowledge and raw data that the AI ​​model does. but the human brain cannot be accessed or stored.
The tool was trained on massive amounts of data, including DNA information, cell signaling, gene activity levels, clinical notes and more. The researchers tested and refined the model by asking it to perform various tasks. Finally, the tool’s performance was validated on 1.2 million patient records and asked to identify drug candidates for various diseases.
The researchers also asked the tool to predict which patient characteristics would make the identified drug candidates contraindicated for specific patient populations.
Another task involved asking the tool to identify existing small molecules that could effectively block the activity of certain proteins involved in disease-causing pathways and processes.
In a test designed to measure the model’s ability to reason as a human clinician might, the researchers pushed the model to find drugs for three rare conditions it hadn’t seen as part of its training. a neurodevelopmental disorder, a connective tissue disease, and a rare genetic condition that causes water imbalance.
The researchers then compared the model’s recommendations for drug treatment with current medical knowledge about how the proposed drugs work. In each example, the tool’s recommendations are aligned with current medical knowledge.
Furthermore, the model not only identified drugs for all three diseases but also provided the rationale behind its decision. This ability to explain allows for transparency and can increase physician confidence.
The researchers caution that any treatments identified by the model will require additional evaluation of dosage and timing of delivery. But, they add, with this unprecedented capability, the new AI model will accelerate drug repurposing in a way that has not been possible before. The team is already working with several rare disease institutions to help identify potential treatments.
Source:
Journal Reference:
Huang, K., et al. (2024). A foundational model for clinician-centered drug repurposing. Nature Medicine. doi.org/10.1038/s41591-024-03233-x.