New computer tool could lead to better crops and safer pesticides
By Jeff Salton
September 23, 2009
Researchers engaged in developing new strains of crops, such as drought-resistant wheat and new pesticides that are more environmentally-friendly, are also creating a computing tool that could help scientists predict how plants will react to different environmental conditions. It’s hoped their findings will help create better crops, such as tastier and longer-lasting tomatoes.
To achieve the best agricultural results, scientists need to predict how the genes inside plants will react when they are subjected to different chemicals or environmental conditions.
The tool will form part of a new £1.7 million (USD$2.8 million) Syngenta University Centre at Imperial College London, which will provide facilities for researchers from Imperial and Syngenta who are working together to improve agricultural products.
Prof Stephen Muggleton, Director of the new center from the Department of Computing at Imperial College London, says: “We believe our computing tool will revolutionize agricultural research by making the process much faster than is currently possible using conventional techniques. We hope that our new technology will ultimately help farmers to produce hardier, longer-lasting and more nutritious crops.”
A prototype of the new tool lets researchers analyze in a matter of minutes, instead of months, which genes are responsible for different processes inside a plant, and how different genes work together. The tool the researchers are using is a sophisticated set of algorithms that allows a computer to ‘learn’ based on data that it is analyzing. The researchers say the tool will recognize complex patterns in that data to find important pockets of information about plant biology that might previously have taken months or even years to find.
Scientists believe the ‘machine learning’ capabilities of the new tool will allow them to gain a greater understanding of different plants, even when they are lacking information about some aspects of their inner workings. Previously, modeling a plant’s behavior had been imprecise and time-consuming because a lack of information had resulted in poor results.
You say tomatoes …
The tool’s first project will be studying how different genes affect the way a tomato’s flesh hardens and tastes, and how the fruit’s skin changes color from green to red.
The researchers hope that this will enable them to develop new tomato strains that are tastier, and that redden earlier and soften later so that they can be transported more easily to market. These qualities could be especially useful in developing countries, where factors such as poor transport can quickly spoil fruit and vegetables.
Scientists are also testing the safety of pesticides that Syngenta is developing. The tool will allow them to construct models that might reveal whether a proposed pesticide might affect metabolites, which are responsible for processing energy inside a plant.
All software developed by researchers at Imperial College is intended to be made publicly available over the next four years.