In 2025, artificial intelligence and machine learning will begin to expand the impact of Crispr genome editing in medicine, agriculture, climate change, and the fundamental research that underlies these fields. It’s worth saying right away that the field of artificial intelligence is full of such great promises. With every major advancement in technology, there is always a hype cycle, and we are in one right now. In many cases, the benefits of artificial intelligence will take several years to materialize, 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 datasets or, in many cases, jargon deal with them properly because we simply don’t have the tools or time. It can take supercomputers weeks or months to analyze subsets of data for a given question, so we have to be very selective about the questions we ask. Artificial intelligence and machine learning are already addressing these limitations, and we are using AI tools to quickly search and make discoveries in our huge genomic data sets.
In my lab, we recently used artificial intelligence tools to aid us find diminutive gene-editing proteins that had until now gone undiscovered in public genome databases because we simply didn’t have the capacity to process all the data we collected. A group from the Creative Genomics Institute, a research institute I founded 10 years ago at the University of California, Berkeley, recently teamed up with members of the Department of Electrical Engineering and Computer Science (EECS) and the Center for Computational Biology and developed a way to utilize a huge language model similar to the one I utilize many popular chatbots, to predict modern functional RNA molecules that have greater heat tolerance compared to natural sequences. Imagine what else is waiting to be discovered in the expansive genome and structural databases that scientists have collectively built over the past decades.
These types of discoveries have real-world applications. In the two examples above, smaller genome editors could aid deliver therapies more efficiently to cells, and predicting heat-stable RNA molecules could aid improve biomanufacturing processes that produce drugs and other valuable products. In health and drug development, the first Crispr-based therapy for sickle cell disease was recently approved, and approximately 7,000 other genetic diseases are waiting for similar therapy. Artificial intelligence can aid speed up the software development process by predicting the best editing targets, maximizing Crispr precision and efficiency, and reducing side effects. In agriculture, AI-powered advances in Crispr technology promise to create more resilient, productive and nutritious crops, ensuring greater food security and reducing time to market, helping researchers focus on the most fruitful approaches. In climate, AI and Crispr can unlock modern solutions to improve natural carbon capture and environmental sustainability.
It’s early days, but the potential to properly harness the combined power of AI and Crispr, arguably two of the most cutting-edge technologies of our time, is clear and invigorating – and has already begun.