The Promise of Drug Repurposing: A Faster, Cost-Effective Path to New Therapies
Repurposing existing drugs offers a faster, cost-effective way to bring new treatments to patients. By identifying new therapeutic uses for compounds that have already undergone development, drug repurposing reduces risks, saves time, and accelerates innovation. Learn how AI and advanced analytics are transforming this approach, unlocking new possibilities for rare diseases, unmet medical needs, and beyond.
One of the fastest and most cost-effective ways to bring new treatments to patients is by looking at existing drugs in a new light. Drug repurposing also known as drug repositioning, focuses on identifying new therapeutic uses for drugs that have already been through some stages of development.
The Power of Repurposing
History has shown how repurposed drugs can transform patient care:
- Semaglutide (Ozempic) and Liraglutide (Victoza) was initially developed to manage type 2 diabetes, these GLP-1 receptor agonists have since been approved for weight management and obesity treatment (Wegovy). Emerging research also suggests their potential in addressing alcohol and drug addiction, opening new avenues for therapeutic intervention.
- Sildenafil (Viagra) was initially developed for heart conditions but found a new life in treating erectile dysfunction.
- Thalidomide, despite its tragic past, is now used to treat cancer and inflammatory conditions under strict guidelines.
Repurposing drugs allows developers to take advantage of studies that have already been carried out, including preclinical and clinical pharmacokinetic, pharmacodynamic and safety trials. This saves both time and money and had potential to get drugs to the market more quickly and at a lower risk of failure.
Developing a drug for rare and neglected diseases can be particularly challenging, because of the limited patient populations, disease complexity and high development costs. The cost-effectiveness of drug repurposing means that it can play a useful role in the treatment of rare diseases, as well as ensuring that drugs get to patients in great need much more quickly.
A Data-Driven Approach to Drug Repurposing
Historically, drug repurposing has been because of serendipity – for example, researchers testing the monoamine oxidase inhibitor iproniazid in patients with tuberculosis noticed improvements in mood, appetite, and sleep. While it has now been withdrawn, it began the era of MOA inhibitors in depression. Another example is fenfluramine, which was launched as an appetite suppressant in obesity in the 1960s. It was withdrawn in the 1960s but approved in the 2020s for seizures associated with Dravet syndrome and Lennox–Gastaut syndrome.
Drugs for repurposing may be those that have made their way through preclinical and clinical studies and discontinued for lack or efficacy or delivery challenges, drugs that have been dropped for commercial reasons or are coming close to patent expiry, or drugs from academia where development simply has not been pursued. They may also be drugs that are successfully on the market for another indication, or in another form, for example as an oral tablet but with potential as an inhaled drug.
There is a wealth of information that can feed into drug repurposing, including:
- Drug profiles
- Target profiles
- Disease profiles and mechanisms
- Biological pathways
- Compound libraries
- Preclinical and clinical trial results
- Patient records and other real-world data
- Omics data
- Biomarker data
- Scientific literature, including journal papers and conference proceedings
Some big pharma companies have made compounds available for development, particularly for rare and neglected diseases.
Drug repurposing can be structure-based (affinity to disease-causing proteins), genomics-based (correlating transcriptomic signatures and disease signatures), network pharmacology-based (mapping the relationships between drugs, targets, and diseases), or mechanism-driven (selection based on disease mechanisms).
The Role of AI in Repurposing—And the Road Ahead
The vast amount of available data holds great potential for drug repurposing, but uncovering meaningful connections remains a challenge. AI and advanced analytics can help extract insights, speeding up the process and reducing reliance on chance discoveries. Researchers are increasingly using AI to identify new candidates for rare diseases and conditions without treatments. AI-driven approaches have already supported drug repurposing efforts for COVID-19, Alzheimer’s, and infectious diseases. While much of this work has been in academia, there’s growing opportunity for industry to collaborate and advance these methods further.
At Agilisium, we recognize the immense potential of AI in drug repurposing. While the field is still evolving, advanced analytics and AI-driven insights can help researchers navigate the vast landscape of biomedical data, identifying promising drug-disease matches faster and more effectively.
Our focus is on leveraging AI to streamline data integration, uncover trends, and support decision-making in early research stages. By bringing together structured and unstructured data - scientific literature, clinical trial reports, patient records, and more AI-powered solutions can enhance the repurposing process, helping researchers make informed, data-driven choices.
As the industry continues to explore AI’s role in drug repurposing, collaboration between pharma, AI innovators, and domain experts will be key to realizing its full potential.
%20(1).png)
.avif)
%20(5).avif)
.avif)
