Despite modern biotechnology's advanced tools for gene editing and drug design, thousands of rare diseases remain without effective treatments. A significant hurdle, according to biotech leaders, has been the scarcity of specialized human talent to drive this complex work. However, artificial intelligence (AI) is now emerging as a powerful force multiplier, enabling scientists to tackle long-neglected medical challenges. At Web Summit Qatar, executives from Insilico Medicine and GenEditBio highlighted how AI-powered automation, data analysis, and gene editing are revolutionizing drug discovery and rare disease treatment, effectively bridging critical labor gaps in the biotech industry.
Insilico Medicine's Vision for "Pharmaceutical Superintelligence"
Speaking at Web Summit Qatar, Alex Aliper, CEO and founder of Insilico Medicine, outlined his company's ambitious goal to develop "pharmaceutical superintelligence." Insilico recently launched its MMAI Gym, an initiative designed to train generalist large language models, such as ChatGPT and Gemini, to achieve the performance levels of highly specialized AI models. The ultimate aim is to create a multi-modal, multi-task model capable of solving diverse drug discovery challenges simultaneously with superhuman accuracy.
Addressing the Labor Shortage with AI
Aliper emphasized the urgent need for this technology to boost productivity within the pharmaceutical industry and address the persistent shortage of labor and talent. "There are still thousands of diseases without a cure, without any treatment options, and there are thousands of rare disorders which are neglected," Aliper stated in an interview with TechCrunch. "So we need more intelligent systems to tackle that problem."
Insilico's platform leverages biological, chemical, and clinical data to generate hypotheses about disease targets and potential drug candidates. By automating processes that traditionally required extensive human labor from chemists and biologists, Insilico can efficiently explore vast design spaces, identify high-quality therapeutic candidates, and even repurpose existing drugs. This approach dramatically reduces both costs and development timelines. For instance, the company recently utilized its AI models to investigate whether existing medications could be repurposed to treat ALS, a rare neurological disorder.
GenEditBio's In Vivo Gene Editing Breakthroughs
The labor bottleneck in biotech extends beyond initial drug discovery. Even when AI identifies promising targets or therapies, many diseases necessitate interventions at a more fundamental biological level. GenEditBio is at the forefront of the "second wave" of CRISPR gene editing, shifting the paradigm from editing cells outside the body (ex vivo) to precise delivery and editing within the body (in vivo). The company's vision is to make gene editing as simple as a single injection directly into the affected tissue.
Tian Zhu, co-founder and CEO of GenEditBio, explained their innovation: "We have developed a proprietary ePDV, or engineered protein delivery vehicle, and it’s a virus-like particle." She added, "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." These "natural resources" refer to GenEditBio's extensive library of thousands of unique, nonviral, nonlipid polymer nanoparticles, which serve as sophisticated delivery vehicles for safely transporting gene-editing tools into specific cells.
GenEditBio's NanoGalaxy platform employs AI to analyze data, identifying correlations between chemical structures and specific tissue targets like the eye, liver, or nervous system. The AI then predicts optimal modifications to a delivery vehicle's chemistry to ensure it can carry its therapeutic payload without triggering an immune response. The company rigorously tests its ePDVs in vivo in wet labs, feeding the results back into the AI system to continuously refine its predictive accuracy for subsequent rounds of development. Zhu highlighted that efficient, tissue-specific delivery is crucial for successful in vivo gene editing, noting that their approach reduces manufacturing costs and standardizes a process historically difficult 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 affirmed. The company recently received FDA approval to commence trials for CRISPR therapy targeting corneal dystrophy.
Combating the Persistent Data Problem
Despite these advancements, progress in many AI-driven biotech systems ultimately confronts a significant data challenge. Accurately modeling the intricate edge cases of human biology demands a far greater volume of high-quality data than researchers currently possess. Aliper acknowledged this, stating, "We still need more ground truth data coming from patients. 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 by operating automated labs that generate multi-layer biological data from disease samples at scale, without human intervention, which is then fed into its AI-driven discovery platform.
Zhu offered a different perspective on data, suggesting that much of what AI needs already exists within the human body, shaped by millennia of evolution. Only a small fraction of DNA directly "codes" for proteins; the majority acts as an intricate instruction manual for gene behavior. While historically challenging for humans to interpret, this information is becoming increasingly accessible to AI models, including recent initiatives like Google DeepMind’s AlphaGenome. GenEditBio applies a similar principle in its labs, testing thousands of delivery nanoparticles in parallel rather than sequentially. The resulting datasets, which Zhu describes as "gold for AI systems," are used to train their models and support growing collaborations with external partners.
Looking ahead, Aliper believes one of the next major endeavors will be the creation of digital twins of humans to conduct virtual clinical trials, a process he admits is "still in nascence." He concluded with a hopeful outlook: "We’re in a plateau of around 50 drugs approved by the FDA annually, and we need to see growth. 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."
