In 2025, we will see AI and machine learning begin to amplify the impact of Crispr genome editing in medicine, agriculture, climate change and the basic research that underpins these fields. It should be said frankly that the field of AI is filled with big promises like this. With any major new technological advancement there is always a hype cycle and we are in it right now. In many cases, the benefits of AI will be felt in the next few years, but in genomics and life sciences research, we are seeing real impacts now.
In my field, Crispr gene editing and genomics more broadly, we often deal with huge data sets—or, in many cases, we cannot solve them properly because we simply don’t have the tools or the time. Supercomputers can take weeks to months to analyze data sets for a given question, so we must be highly selective about the questions we choose to ask. AI and machine learning have removed these limitations, and we are using AI tools to quickly search and explore within our large genomic datasets.
In my lab, we recently used AI tools to help us find small gene-editing proteins that had not been discovered in public genome databases because we simply did not capable of processing all the data we have collected. A team at the Institute for Innovative Genomics, the research institute I founded 10 years ago at UC Berkeley, recently collaborated with members of the Department of Electrical Engineering and Computer Science (EECS) and the Center for Computational Biology. mathematics, and developed a way to use a large language model, like the one used by many popular chatbots, to predict new functional RNA molecules that are more heat-resistant than nature. Imagine what else is waiting to be discovered in the massive genomic and structural databases that scientists have built together in recent decades.
These types of discoveries have real-world applications. For the two examples above, smaller genome editors could help deliver therapies into cells more efficiently, and predicted heat-stable RNA molecules would help improve biomanufacturing processes that result medicines and other valuable products. In the field of medical and drug development, we recently saw the approval of the first Crispr-based sickle cell disease therapy, and there are approximately 7,000 other genetic diseases waiting for a therapy. similar. AI can help accelerate development by predicting the best editing targets, maximizing Crispr’s accuracy and efficiency, while reducing off-target effects. In agriculture, AI-powered Crispr advances promise to produce crops with greater resilience, productivity and nutrition, ensuring greater food security and reducing lead times. to market by helping researchers focus on the most effective methods. On climate, AI and Crispr can unlock new solutions to improve natural carbon capture and environmental sustainability.
It’s still early days, but the potential to properly harness the collective power of AI and Crispr, arguably the two most profound technologies of our time, is clear and exciting—and it’s already begun.
