This is a brief account of the plenary talk given to the meeting of the Chinese Society of Chemical Science and Technology held in Oxford on 6 October 2001. The talk covered the application of pattern recognition techniques to discover molecules which will bind to the binding sites of proteins. Three situations were considered: the structure of the protein being unknown; the structure known but the binding site unknown; and finally, and this is the most important case for the future, both the structure and nature of the target site available in atomic detail. For this case we have developed a massively distributed computer program using a screensaver which now involves over one million personal computers, including over a thousand in China. The project will involve the screening of 3 5 billion small molecules against 16 protein targets, all of which are implicated in the process of cancer. This is a brief account of the plenary talk given to the meeting of the Chinese Society of Chemical Science and Technology held in Oxford on 6 October 2001. The talk of the application of pattern recognition techniques to discover molecules which will bind to the binding sites of the structure of the protein is unknown; the structure known but the binding site unknown; and finally this and the most important case for the future, both the structure and nature of the target site available in atomic For this case we have developed a massively distributed computer program using a screensaver which now involves over one million personal computers, including over a thousand in China. The project will involve the screening of 3 5 billion small molecules against 16 protein targets, all of which are implicated in the process of cancer.