AI Speeds Up Cures for Thousands of Rare Diseases

Thousands of rare diseases have no cure, not because we lack the science, but because we don't have enough scientists to do the work.

That problem just got a massive solution. Two biotech companies revealed this week at Web Summit Qatar how their AI systems are filling the talent gap that has left rare disorders untreated for decades, potentially unlocking personalized therapies for millions of patients worldwide.

Insilico Medicine just launched its MMAI Gym platform, training AI models to perform drug discovery tasks with what CEO Alex Aliper calls "superhuman accuracy." The platform ingests biological, chemical and clinical data to generate hypotheses about disease targets and candidate molecules, automating steps that once required teams of chemists and biologists.

"We really need this technology to increase the productivity of our pharmaceutical industry and tackle the shortage of labor and talent in that space," Aliper told TechCrunch. The FDA currently approves roughly 50 drugs annually, but biotech leaders say AI-driven platforms could accelerate personalized medicine within 10 to 20 years.

The company recently deployed its AI to identify whether existing drugs could treat ALS, a rare neurological disorder affecting roughly 5,000 Americans annually. By automating the search through vast design spaces, Insilico can nominate high-quality therapeutic candidates at dramatically reduced cost and time.

But drug discovery is only half the battle. Boston-based GenEditBio is tackling the next frontier with FDA-approved trials for in vivo CRISPR therapy, delivering gene editing directly into patient tissues with a single injection.

"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," co-founder and CEO Tian Zhu explained. The company's NanoGalaxy platform maintains a library of thousands of unique nanoparticles that act as delivery vehicles for gene-editing tools.

The AI analyzes data to identify how chemical structures correlate with specific tissue targets like the eye, liver or nervous system, then predicts which tweaks will help the vehicle carry its payload without triggering an immune response. The company tests thousands of delivery nanoparticles in parallel, feeding results back into the AI to refine predictive accuracy for the next round.

GenEditBio recently received FDA approval to begin trials for CRISPR therapy treating corneal dystrophy, marking a significant regulatory milestone for in vivo gene editing. "It's like getting an off-the-shelf drug for multiple patients, which makes the drugs more affordable and accessible to patients globally," Zhu said.

The Ripple Effect

The impact extends far beyond individual treatments. Modern biotech has the tools to address thousands of rare diseases simultaneously, but manual research methods created an impossible bottleneck. By automating both drug discovery and gene editing delivery, these AI platforms transform personalized medicine from a luxury for the few into a scalable solution for millions.

Insilico is building automated labs that generate multi-layer biological data from disease samples without human intervention, feeding it directly into AI-driven discovery platforms. GenEditBio argues that the data AI needs already exists in human DNA shaped by thousands of years of evolution, information that's been difficult for humans to interpret but increasingly accessible to AI models.

Both companies acknowledge challenges around data quality and diversity, with current datasets heavily biased toward Western populations. However, their parallel approaches to generating new training data at scale could help AI models better serve patients globally.

Within two decades, researchers say we could see virtual clinical trials using digital twins of humans, though the technology is still in early stages.