Despite modern biotechnology possessing sophisticated tools for gene editing and drug design, a significant number of rare diseases remain without effective treatments. Executives from Insilico Medicine and GenEditBio contend that the primary obstacle for years has been a shortage of skilled individuals to advance this critical work. They highlight artificial intelligence as the transformative force multiplier, empowering scientists to tackle complex challenges that the industry has long considered intractable.
During his address at Web Summit Qatar this week, Alex Aliper, CEO and founder of Insilico, articulated his company's ambitious objective: to cultivate "pharmaceutical superintelligence." Insilico recently unveiled its "MMAI Gym," an initiative designed to train generalist large language models, such as ChatGPT and Gemini, to achieve the performance levels of specialized models.
The ultimate aim, Aliper explains, is to construct a multi-modal, multi-task model capable of simultaneously executing numerous drug discovery tasks with unparalleled accuracy.
“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 emphasized in an interview with TechCrunch. He added, “So we need more intelligent systems to tackle that problem.”
Insilico's platform processes biological, chemical, and clinical data to generate hypotheses regarding disease targets and potential therapeutic molecules. By automating processes that traditionally demanded extensive teams of chemists and biologists, Insilico claims it can efficiently navigate vast design landscapes, identify high-quality therapeutic candidates, and even repurpose existing drugs—all while significantly reducing both cost and development time.
For instance, the company recently leveraged its AI models to investigate whether existing drugs could be repurposed for the treatment of Amyotrophic Lateral Sclerosis (ALS), a rare neurological disorder.
However, the talent bottleneck isn't confined to drug discovery. Even when AI successfully identifies promising targets or therapies, many diseases necessitate interventions at a more fundamental biological level.
GenEditBio is a key player in the "second wave" of CRISPR gene editing, shifting the paradigm from editing cells outside the body (ex vivo) to precise delivery within the body (in vivo). The company's vision is to make gene editing a single-injection treatment delivered directly to the affected tissue.
“We have developed a proprietary ePDV, or engineered protein delivery vehicle, and it’s a virus-like particle,” GenEditBio’s co-founder and CEO Tian Zhu informed TechCrunch. She elaborated, “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.”
The ‘natural resources’ Zhu references are GenEditBio’s extensive library of thousands of distinct, nonviral, nonlipid polymer nanoparticles—essentially, sophisticated delivery vehicles engineered to safely transport gene-editing tools into specific cells.
The company states that its NanoGalaxy platform utilizes AI to analyze data, discerning correlations between chemical structures and specific tissue targets, such as the eye, liver, or nervous system. The AI then predicts precise chemical adjustments to a delivery vehicle that will enable it to carry its payload without eliciting an immune response.
GenEditBio conducts in vivo testing of its ePDVs in wet labs, with the experimental results continuously fed back into the AI system to refine its predictive accuracy for subsequent iterations.
Zhu asserts that efficient, tissue-specific delivery is an indispensable requirement for in vivo gene editing. She argues that her company's methodology not only lowers the cost of goods but also standardizes a process that has historically proven challenging to scale.
“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 explained.
Her company recently secured FDA approval to commence trials for a CRISPR therapy targeting corneal dystrophy.
As is often the case with AI-driven systems, progress in biotechnology eventually confronts a data challenge. Accurately modeling the intricate edge cases of human biology demands a significantly larger volume of high-quality data than researchers currently possess.
“We still need more ground truth data coming from patients,” Aliper stated. He added, “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.”
Aliper highlighted that Insilico's automated laboratories generate multi-layer biological data from disease samples at scale and without human intervention, which is then fed directly into its AI-driven discovery platform.
Zhu posits that the data essential for AI already resides within the human body, honed by millennia of evolution. Only a small fraction of DNA directly "codes" for proteins, while the remainder functions as a comprehensive instruction manual for gene behavior. This information, historically difficult for humans to decipher, is becoming increasingly accessible to AI models, including recent advancements like Google DeepMind’s AlphaGenome.
GenEditBio employs a similar strategy in its labs, testing thousands of delivery nanoparticles concurrently rather than sequentially. The resulting datasets, which Zhu describes as “gold for AI systems,” are utilized to train their models and are increasingly supporting collaborations with external partners.
According to Aliper, one of the forthcoming major endeavors will involve constructing "digital twins" of humans to facilitate virtual clinical trials, a process he acknowledges is “still in nascence.”
“We’re in a plateau of around 50 drugs approved by the FDA every year annually, and we need to see growth,” Aliper asserted. He noted, “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.”
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.