Rare neuromuscular diseases often have no cure because developing targeted drugs is time-consuming, expensive, and risky for companies. New approaches using AI and stem cell models could ultimately shift the balance.
Belgian AI company Kantify was operating as usual until a cancer diagnosis forced the team to rethink its direction. “We built algorithms for areas like marketing and transportation,” said Ségolène Martin, co-founder and CEO of Kantify.
“Those were complex projects that had nothing to do with health, but they allowed us to build deep expertise in AI.”
That changed in 2017 when the company’s chief technology officer, Nick Subramanian, was diagnosed with sarcoma. Sarcoma is a rare type of cancer that forms tumors in connective tissues such as bones, muscles, and blood vessels.
This experience led the company to shift its focus to health and explore the potential of AI to help identify new drugs for rare diseases and improve testing methods.
“It changed our lives,” Martin said. “We are now fully focused on AI for human health and have developed technology specifically for AI-based drug discovery.”
That expertise is now being put to full use as part of a five-year EU-funded research initiative called DREAMS. It focuses on improving treatments for a group of five rare neuromuscular diseases that cause a gradual loss of muscle function.
increase the probability of patients
Developing treatments for rare diseases remains one of the greatest challenges in modern medicine. This process is long, expensive, and uncertain, requiring years of research, regulatory approval, and clinical trials.
For pharmaceutical companies, the small number of patients often makes it difficult to justify such investments. As a result, many symptoms remain untreated.
Currently, only about 5-6% of the estimated 7,000-10,000 rare diseases have approved treatments, a gap that organizations such as the World Health Organization continue to highlight as a global priority.
AI could help change that. By rapidly analyzing vast datasets, AI can narrow down potential drug candidates at an early stage and identify existing drugs that could be repurposed for rare conditions.
Focus on neuromuscular disorders
Within DREAMS, researchers are focusing on five rare neuromuscular diseases, including Duchenne muscular dystrophy, which primarily affects boys and causes muscle degeneration, and Emery-Dreyfus muscular dystrophy, which can cause severe heart problems.
Although these symptoms have different genetic causes, the underlying mechanism of action at the cellular level appears to be the same. By targeting these common pathways, researchers hope to develop treatments that can treat multiple diseases at once, rather than tackling each disease individually.
To do this, the research team reprograms the patient’s cells into so-called induced pluripotent stem cells (iPSCs) – a type of master cell that can turn into many other cell types – and then into skeletal muscle tissue. This allows researchers to study rare neuromuscular diseases in a controlled environment.
By combining these laboratory models with AI, researchers can identify common therapeutic targets across multiple conditions.
“This type of research is very important for patients and their families,” said Xavier Nissan, project coordinator for DREAMS and research director at I‑Stem, a French research institute specializing in stem cell therapy and the treatment of monogenic diseases.
“They are suffering and have to fight disease every day. They need technology like this.”
From data to potential treatments
In addition to identifying underlying disease processes, DREAMS researchers are using AI to analyze billions of new and existing drugs to predict which compounds will be most effective.
“This is one way AI can create real social value,” Martin said. “We can truly accelerate research and impact areas where progress is lagging.”
In the lab, the team is testing a library of 2,700 EMA- and FDA-approved drugs to assess whether any of them can improve common disease-related symptoms.
“In our lab, we are testing thousands of existing drugs on iPSC-derived muscle cells from patients with these diseases,” Nissan said.
“AI is also used to understand how drugs work, identify targets, and predict additional diseases where treatment may be helpful. By combining these approaches, we can move faster and focus on the most promising candidates.”
The team spent three years generating data that feeds the AI and enables predictions of drug reuse.
At the heart of this drug search is Kantify’s AI platform, Sapian. It is trained on vast amounts of data, from molecular and protein information to patents and properties of all types of medicines. Based on this information, the platform can predict which drugs are suitable for specific types of diseases, such as rare neuromuscular diseases.
“It’s not a crystal ball,” Martin said. “It generates hypotheses that need to be tested in the real world. But we’ve found from different projects that the hypotheses are very good.”
in the same basket
It remains unclear when this approach will lead to new treatments for patients with rare diseases. Nissan points out that there are many factors at play, and is taking a cautious stance because it does not want to give false hope to patients currently living with these conditions.
“This project will end at the end of 2028. Beyond that there is a big question mark. We are trying our best, but in the drug world things can take a long time.”
A lot depends on what happens when these approaches are tested in patients. New drugs can take decades to complete clinical trials, and even existing drugs that have already gone through these processes still need to go through several tests.
The DREAMS team is working to make some of these trials more feasible for rare diseases. One of the problems they face is that there aren’t enough people living with these diseases to conduct large enough clinical trials.
So researchers are proposing a different approach. “Some rare diseases have very different symptoms but share a common biological cause,” Nissan said.
“This is why we want to conduct so-called basket trials, where we test one drug on people with different symptoms and diseases that share a similar cause,” he said.
This approach, led by patient organization AFM‑Téléthon and patients themselves, could help accelerate drug development for people with rare neuromuscular diseases.
Regulators are currently considering widespread adoption of a basket clinical trial approach for rare diseases, Nissan Motor Co., Ltd. said.
For Nissan and Martin, this research is more than just research. It’s personal.
“Patients need us,” Nissan said. “It’s a big responsibility. I feel like I need to be successful. But it also means I have a chance to make a big difference in a lot of people’s lives. That’s a great thing to take on.”
This article was originally published in Horizon, EU Research and Innovation Magazine.
The research for this article was funded by the EU’s Horizon program.
Source link
