Revolutionary AI Model Translates Genetic Code of Plants

Researchers from the John Innes Centre and the University of Exeter have unveiled Plant RNA-FM, the first AI model capable of understanding the genetic language of plants. This breakthrough promises to revolutionize plant science and open new doors for crop improvement and genetic research.

In a groundbreaking collaboration, plant researchers from the John Innes Centre and computer scientists from the University of Exeter have unveiled Plant RNA-FM, believed to be the first artificial intelligence (AI) model that understands the genetic “language” of plants. This innovative model marks a significant milestone in plant science, with far-reaching implications for agriculture, environmental sustainability and genetic research.

Developed using an extensive dataset of 54 billion RNA sequences from 1,124 plant species worldwide, Plant RNA-FM is a sophisticated AI model trained similarly to the language processing model ChatGPT. RNA, much like DNA, carries genetic instructions in the form of sequences and structures. The AI was taught to decode these patterns, which govern a wide array of biological functions, including plant growth and stress responses.

Ke Li’s team from the University of Exeter partnered with Yiliang Ding’s group at the John Innes Centre to bring this project to fruition. Ding’s research focuses on RNA structures, the foundational elements of RNA language. The successful training of Plant RNA-FM on this vast dataset has enabled it to make precise predictions about RNA functions and identify functional patterns with high accuracy. These predictions were later validated through experimental observations.

“While RNA sequences may appear random to the human eye, our AI model has learned to decode the hidden patterns within them,” Haopeng Yu, a postdoctoral researcher in Ding’s group, said in a news release.

The Plant RNA-FM model can potentially drive discovery and innovation not only in plant science but also in studies concerning invertebrates and bacteria. The researchers believe that this AI model could have profound implications for crop improvement, resilience against climate change and the next generation of AI-based gene design.

“Our PlantRNA-FM is just the beginning,” added Ding. “We are working closely with Dr. Li’s group to develop more advanced AI approaches to understand the hidden DNA and RNA languages in nature. This breakthrough opens new possibilities for understanding and potentially programming plants, which could have profound implications for crop improvement and the next generation of AI-based gene design. AI is increasingly instrumental in helping plant scientists tackle challenges, from feeding a global population to developing crops that can thrive in a changing climate.”

Support for the project also came from scientists at the Northeast Normal University and the Chinese Academy of Sciences. The collaborative effort reflects a growing trend of interdisciplinary approaches in scientific discovery, blending plant biology with cutting-edge computer science.

The findings and details of this revolutionary project have been published in the journal Nature Machine Intelligence.

The unveiling of Plant RNA-FM signifies an exciting advancement in our capability to decode the natural world. As plant genetic research continues to evolve, the integration of AI models like Plant RNA-FM will likely lead the way in addressing some of the most pressing agricultural and environmental challenges of our time.