In 2025, we will see AI and machine learning begin to increase the power of Editing of Crispr genomes in medicine, agriculture, climate change, and the basic research that supports these fields. It is worth saying up front that the field of AI holds great promise like this. With every new technological advance there is always a vicious cycle, and we are in one now. In most cases, the benefits of AI are several years in the future, but in genomics and life sciences research we are seeing real results right now.
In my field, Crispr gene editing and genomics more broadly, we often encounter large datasets—or, more often, I can’t deal with them properly because we don’t have the tools or the time. High-end computers can take weeks or months to analyze the small parts of a given query, so we need to be very selective about the questions we can ask. AI and machine learning are already removing these barriers, and we are using AI tools to rapidly search and discover the content of our large genomic datasets.
In my lab, we recently used AI tools to help us find small gene-editing proteins that had been missing from human genomes because we couldn’t scramble our entire collection. The Innovative Genomics Institute, a research organization that I founded 10 years ago at UC Berkeley, recently collaborated with members of the Department of Electrical Engineering and Computer Sciences (EECS) and the Center for Computational Biology, and developed a method to use it. a large model of language, similar to what many popular chatbots use, to predict new RNA molecules with high temperature compared to natural phenomena. Just imagine some of the things expected to be found in the large genomes and tools that scientists have put together over the past few decades.
These types of findings have specific applications. In the two examples above, small genome editors can facilitate the efficient delivery of drugs into cells, predicting that intact RNA molecules will help improve biomanufacturing processes that produce drugs and other valuable products. In the development of health and medicine, we recently saw the approval of Crispr’s first treatment for sickle cell disease, and there are approximately 7,000 other genetic diseases awaiting similar treatment. AI can help speed up the development process by predicting the best conversion targets, increasing Crispr’s accuracy and efficiency, and reducing unwanted results. In agriculture, the development of AI-informed Crispr promises to create more productive, profitable, and nutritious crops, ensuring food security and reducing time to market by helping researchers consider the most profitable options. In the climate world, AI and Crispr can open up new ways to tackle natural carbon capture and environmental sustainability.
It’s still early days, but the potential to harness the combined power of AI and Crispr, arguably two of the most immersive technologies of our time, is clear and exciting, and has already begun.
Leave a Reply