10102069FloraFold: an AI tool for crop disease resistance trait discoveryClosedCollaborative R&DInnovate UKIn modern agriculture, safeguarding crops from diseases is paramount to ensuring both consistent yield and global food security. A pivotal aspect of this is understanding the interactions between plants and their pests & pathogens, which traditionally has been a laborious process fraught with trial and error. Our project aims to bring a significant technological advance to this domain by employing cutting-edge artificial intelligence (AI) to expedite the process of identifying key protein interactions between plants and parasites. Central to our initiative is the development of a sophisticated computational tool designed to sift through vast datasets of plant and parasite proteins. By evaluating the likelihood of interaction between these proteins, we aim to pinpoint the most promising targets for further analyses in the laboratory. This tool is propelled by the power of AI, specifically leveraging the revolutionary protein-folding capabilities of OpenFold and Google DeepMind's AlphaFold2\. By customising OpenFold with our curated datasets, we anticipate a substantial leap in both predictive accuracy and computational efficiency in analysing plant-parasite protein interactions. The backbone of our tool is a proprietary pipeline that integrates established scientific tools to process and analyse a comprehensive in-house database of protein structures. This fusion of AI with rigorous computational biology aims to significantly outpace traditional methods, offering a more rapid and precise approach to identifying potential plant-parasite interactions. To validate the practical utility of our AI-driven tool, we plan to conduct an extensive series of laboratory experiments. The predictions made by our tool will be tested empirically to ascertain their accuracy and relevance. This validation is crucial not only for refining our tool but also for paving the way for its integration into the broader scientific and agricultural communities. In summary, our project represents an innovative melding of AI, computational biology, and empirical validation aimed at enhancing the efficiency and accuracy of plant-parasite interaction analysis. By propelling an AI-driven approach to this critical area of study, we aspire to significantly advance our understanding and control of plant diseases. This endeavour not only holds promise for accelerating research in plant pathology but also contributes to the broader goals of sustainable agriculture and food security, aligning with the pressing global need for more resilient and productive agricultural systems.