AI Takes on the Talent Gap in Rare Disease Treatment
Despite major advances in gene editing and drug design, thousands of rare diseases still lack effective treatments. According to biotech leaders, the issue is no longer scientific capability—but human capacity. A shortage of skilled researchers has long slowed progress in rare disease research, and artificial intelligence is now emerging as a critical way to scale innovation across the sector.
Speaking at Web Summit Qatar, executives from Insilico Medicine and GenEditBio explained how AI is acting as a force multiplier, allowing smaller teams to tackle complex biological problems that were previously out of reach.
Building “Pharmaceutical Superintelligence”
At the conference, Alex Aliper, CEO and founder of Insilico Medicine, outlined his company’s ambition to develop what he calls “pharmaceutical superintelligence.” The firm recently launched its MMAI Gym, a platform designed to train generalist large language models—such as ChatGPT and Gemini—to perform at the level of highly specialised drug discovery systems.
The aim is to create a multi-modal, multi-task AI model capable of handling numerous drug development challenges simultaneously, and with greater accuracy than traditional approaches.
“We really need this technology to increase the productivity of our pharmaceutical industry and tackle the shortage of labor and talent in that space, because there are still thousands of diseases without a cure, without any treatment options, and there are thousands of rare disorders which are neglected,” Aliper said in an interview with TechCrunch. “So we need more intelligent systems to tackle that problem.”
Insilico’s platform integrates biological, chemical, and clinical datasets to generate hypotheses around disease targets and potential drug candidates. By automating processes that once required large teams of chemists and biologists, the company says it can explore vast molecular design spaces, identify promising therapies, and even repurpose existing drugs—cutting both cost and development time.
One recent application involved using AI models to assess whether approved drugs could be repurposed to treat ALS, a rare and progressive neurological condition.
AI Beyond Drug Discovery
While AI is accelerating early-stage research, executives argue that labour constraints extend well beyond drug discovery. Many rare conditions require interventions at a deeper biological level—where gene editing plays a critical role.
GenEditBio represents what researchers describe as the “second wave” of CRISPR technology. Instead of editing cells outside the body (ex vivo), the company focuses on precise gene editing directly inside the body (in vivo). Its goal is to deliver a one-time gene-editing injection directly to affected tissues.
“We have developed a proprietary ePDV, or engineered protein delivery vehicle, and it’s a virus-like particle,” said Tian Zhu, co-founder and CEO of GenEditBio, speaking to TechCrunch. “We learn from nature and use AI machine learning methods to mine natural resources and find which kinds of viruses have an affinity to certain types of tissues.”
GenEditBio maintains a large library of thousands of unique, nonviral and nonlipid polymer nanoparticles—engineered delivery systems designed to transport gene-editing tools safely into specific cells.
Using AI to Target the Right Tissue
The company’s NanoGalaxy platform applies AI to analyse how chemical structures interact with different tissues, such as the eye, liver, or nervous system. The system predicts which chemical modifications improve delivery efficiency while avoiding immune reactions.
These predictions are validated through in vivo testing in wet labs, with results continuously fed back into the AI models to improve future accuracy.
Zhu says efficient, tissue-specific delivery is essential for scalable in vivo gene editing and argues that GenEditBio’s approach reduces manufacturing costs while standardising a historically complex process.
“It’s like getting an off-the-shelf drug [that works] for multiple patients, which makes the drugs more affordable and accessible to patients globally,” Zhu said.
Recently, GenEditBio received FDA approval to begin clinical trials of a CRISPR-based therapy targeting corneal dystrophy.
The Data Bottleneck in AI-Driven Biotech
Despite rapid progress, both companies acknowledge that AI’s effectiveness in healthcare is ultimately constrained by data availability.
“We still need more ground truth data coming from patients,” Aliper said. “The corpus of data is heavily biased over the western world, where it is generated. I think we need to have more efforts locally, to have a more balanced set of original data, or ground truth data, so that our models will also be more capable of dealing with it.”
Insilico addresses this challenge through automated laboratories that generate multi-layer biological data from disease samples at scale, without human intervention. This data is then fed directly into its AI-powered discovery systems.
Zhu notes that much of the most valuable biological data already exists within the human genome. While only a small portion of DNA codes for proteins, the rest contains regulatory instructions that have historically been difficult to interpret—an area where AI is making rapid strides. Recent examples include Google DeepMind’s AlphaGenome, which aims to decode how genetic sequences influence biological function.
GenEditBio follows a similar philosophy, testing thousands of nanoparticle delivery systems in parallel rather than sequentially. The resulting datasets, which Zhu describes as “gold for AI systems,” are used both internally and in collaborations with external partners.
Toward Virtual Trials and Personalised Therapies
Looking ahead, Aliper believes one of the industry’s most transformative developments will be the creation of digital twins—virtual human models used to simulate clinical trials.
“We’re in a plateau of around 50 drugs approved by the FDA every year annually, and we need to see growth,” Aliper said. “There is a rise in chronic disorders because we are aging as a global population […] My hope is in 10 to 20 years, we will have more therapeutic options for the personalized treatment of patients.”
While still in its early stages, the combination of AI-driven discovery, scalable gene editing, and richer biological data could redefine how rare diseases are treated—helping the biotech industry overcome both scientific and workforce limitations.
0 Comments