How AI is helping solve the labor issue in treating rare diseases

Modern biotechnology has the tools to edit genes and design drugs, yet thousands of rare diseases remain untreated. According to executives at Insilico Medicine and GenEditBio, the missing ingredient for years has been finding enough smart people to continue the work. AI, they say, will be the force multiplier that will allow scientists to tackle problems that industry has long left unaddressed.

Speaking this week at the Web Summit Qatar, Insilico president Alex Aliper explained his company’s goal of developing “pharmaceutical super intelligence.” Insilico recently released its “MMAI gym” which aims to train generalist large language models, such as ChatGPT and Gemini, to perform as well as specialist models.

The goal is to build a multimodal, multitask model that, Aliper says, can solve many different drug discovery tasks simultaneously with superhuman accuracy.

“We really need this technology to increase the productivity of our pharmaceutical industry and address the labor and talent shortages in that field, because there are still thousands of diseases without a cure, without any treatment options, and there are thousands of rare conditions that are being neglected,” Aliper said in an interview with TechCrunch. “So we need more intelligent systems to tackle that problem.”

Insilico’s platform processes biological, chemical and clinical data to generate hypotheses about disease targets and candidate molecules. By automating steps that once required legions of chemists and biologists, Insilico says it can search vast design spaces, nominate high-quality therapeutic candidates, and even reuse existing drugs – all at dramatically reduced cost and time.

For example, the company recently used its AI models to identify whether existing drugs could be repurposed to treat ALS, a rare neurological disorder.

But the labor market bottleneck does not end with drug discovery. Even if AI can identify promising targets or therapies, many diseases require interventions at a more fundamental biological level.

GenEditBio is part of the ‘second wave’ of CRISPR gene editing, moving the process from editing cells outside the body (ex vivo) to precise delivery inside the body (in vivo). The company’s goal is to make gene editing a one-time injection directly into the affected tissue.

“We have developed our own ePDV, or engineering protein delivery vehicle, and it is a virus-like particle,” Tian Zhu, co-founder and CEO of GenEditBio, told TechCrunch. “We learn from nature and use AI machine learning methods to extract natural resources and discover which types of viruses have an affinity for certain types of tissues.”

The “natural resource” Zhu is referring to is GenEditBio’s vast library of thousands of unique, non-viral, non-lipid polymer nanoparticles – essentially delivery vehicles designed to safely transport gene-editing tools to specific cells.

The company says its NanoGalaxy platform uses AI to analyze data and identify how chemical structures correlate with specific tissue targets (such as the eye, liver or nervous system). The AI ​​then predicts which adjustments to a van’s chemistry will help it carry a load without triggering an immune response.

GenEditBio tests its ePDVs in vivo in wet labs, and the results are fed back to the AI ​​to refine predictive accuracy for the next round.

Efficient, tissue-specific delivery is a prerequisite for in vivo gene editing, Zhu says. She says her company’s approach reduces the cost of goods and standardizes a process that has been difficult to scale in the past.

“It’s like getting a ready-made medicine [that works] for multiple patients, making the medicines more affordable and accessible to patients around the world,” said Zhu.

Her company recently received FDA approval to begin trials of CRISPR therapy for corneal dystrophy.

The fight against the persistent data problem

As with many AI-driven systems, advances in biotechnology ultimately encounter a data problem. Modeling the edge cases of human biology requires far more high-quality data than researchers can currently obtain.

“We still need more ground truth data from patients,” Aliper said. “The data corpus is heavily biased towards the Western world, where it is generated. I think we need to make more efforts locally to have a more balanced set of original data so that our models can handle it better as well.”

Aliper said Insilico’s automated labs generate multi-layered biological data from disease samples at scale, without human intervention, which it then feeds into its AI-driven discovery platform.

Zhu says the data AI needs is already present in the human body, shaped by thousands of years of evolution. Only a small part of the DNA directly “codes” proteins, while the rest acts more as a manual for how genes behave. That information has traditionally been difficult for humans to interpret, but is becoming increasingly accessible to AI models, including recent efforts like Google DeepMind’s AlphaGenome.

GenEditBio uses a similar approach in the laboratory, testing thousands of nanoparticles in parallel instead of one at a time. The resulting datasets, which Zhu calls “gold for AI systems,” are used to train his models and, increasingly, to support collaborations with external partners.

One of the next big efforts, according to Aliper, will be building digital twins of humans to conduct virtual clinical trials, a process he says is “still in its infancy.”

“We are at a plateau of about 50 medications approved by the FDA every year annually, and we need to see growth,” Aliper said. “There is an increase in chronic conditions because we are aging as a global population… My hope is that in 10 to 20 years we will have more therapeutic options for the personalized treatment of patients.”