Indian scientists validate AI-designed gene editor for crops
Researchers at India’s Central Rice Research Institute say they have demonstrated the first successful use of an AI-designed genome-editing tool in plants. The work could broaden the toolbox available for breeding crops with higher yield, better resilience and lower technology barriers.
Scientists at the Indian Council of Agricultural Research’s Central Rice Research Institute have reported the development and experimental validation of what The Hindu BusinessLine describes as the world’s first AI-designed genome-editing tool for plants. The advance is significant because most existing CRISPR systems still depend on naturally occurring microbial proteins. For crop science, that means the new work points toward a more flexible generation of editing tools that could be designed for agricultural needs rather than borrowed only from nature.
The article explains gene editing as a precise way to cut and rewrite sections of plant DNA in order to build traits such as higher yield, climate resilience or disease resistance without introducing foreign genes. Until now, those systems relied mainly on proteins sourced from bacteria and other microbes. The Indian team’s breakthrough is that artificial intelligence was used to design entirely new enzymes that can function efficiently inside plant cells.
Led by scientist Kutubuddin Ali Molla, the researchers showed that the AI-designed enzymes can accurately edit plant DNA and support gene knockout, base editing and prime editing in crops. The report notes that a similar AI-designed system had earlier been developed in the United States for human cells, but this is the first successful demonstration in plants. The study was accepted for publication in the international journal New Phytologist after appearing on the BioRxiv preprint server.
The new platform is called Plant-OpenCRISPR1, or POC1, and it builds on OpenCRISPR-1, an AI-generated nuclease first developed for human cells. Molla said the significance lies in reducing reliance on the narrow set of bacterial enzymes such as Cas9 and Cas12a that currently dominate genome editing and can face limitations in plant systems. He also said AI-driven protein design, using large language models trained on broad natural protein diversity, is reshaping nuclease engineering.
According to the report, the team validated a suite of OC1-based editing tools in rice as a model crop and showed strong performance across multiple editing modes. Molla said POC1, like OC1, will be open for academic and commercial use, which could lower access barriers and help work around some intellectual-property constraints associated with current CRISPR platforms. The research team also included Priya Das, Romio Saha, Debasmita Panda, Chandana Ghosh, S. P. Avinash, Sonali Panda and Mirza J. Baig from CRRI in Cuttack. For agriculture, the practical implication is a possible new route to designing cheaper, more adaptable editing systems for food-security and crop-resilience goals.