New database hailed in cancer fight
Published 11/11/2013 | 00:46
Weather forecasting science is being used to predict the most effective ways to fight cancer in a ground-breaking new development.
Techniques borrowed from the Met Office have been incorporated into a unique "artificial intelligence" database containing 1.7 billion experimental results.
Just as weathermen make their predictions using powerful computers to crunch information from a myriad sources, scientists tapping into the CanSAR database will be guided to the most effective drugs and treatments.
CanSAR, developed in the UK, brings together vast quantities of data from patients, clinical trials, and genetic, biochemical and pharmacological research. It condenses more data than would be generated by operating the Hubble Space Telescope for a million years.
Dr Bissan Al-Lazikani, a leading member of the CanSAR team from the Institute of Cancer Research (ICR) in London, said: "CanSAR uses artificial intelligence, like that used in weather forecasts, to predict which potential drugs are likely to work in which circumstances.
"The database is capable of extraordinarily complex virtual experiments drawing on information from patients, genetics, chemistry and other laboratory research. It can spot opportunities for future cancer treatments that no human eye could be expected to see."
CanSAR is being made freely available to scientists around the world. It contains more than eight million experimentally derived measurements, information on nearly one million biologically active chemical compounds, and data from more than 1,000 cancer cell lines.
It also holds drug target information from the human genome, the "book of life" containing our genetic code, and laboratory animals.
Using the database, research that had previously taken months will now take minutes.
Dr Al-Lazikani added: " CanSAR is the only one of its kind, it is the largest database of cancer disease information in the world. There is also nothing like it for any other disease.
"We are living in an exciting era where new technologies are allowing us to build huge databases of patient data, gene variations that are related to disease and many more clinical observations.
"The problem is, the more of these gold-mines of raw material that we have, the more important the following question becomes: how do we bridge the gap from this raw knowledge to drugs for patients?
"To build this bridge, we need to bring in a whole battery of other knowledge to add to these raw patient genome data. Knowledge such as how different drugs may interact with the genes from these patients? Which of these genes is more likely to be suitable for drug development? What are the key experiments that need to be done in the lab to get us on our way to a new drug?
"This is where CanSAR comes in, it provides this bridge. It links such raw gold-mines of genetic data to whole raft of independent chemistry, biology, patient data and disease information. It then uses sophisticated computer machinery and artificial intelligent to draw paths of knowledge between them, predicts risks and opportunities and make drug-relevant suggestions that can be tested in the lab and take us closer to a drug."
CanSAR, which launched today, was developed at the ICR with funding from Cancer Research UK.
Professor Paul Workman, the institute's deputy chief executive, said: "This is an extraordinary time for cancer research, as advances in scientific techniques open up new possibilities and generate unprecedented amounts of data. Our aim is to make this wealth of information, coming from both the clinic and from the laboratory, freely available in a very user-friendly form to as many people as possible.
"This database speaks many different languages - a chemist and a clinician can access data from each other without having to understand each other's jargon. It is so easy to use that anyone can have a go. I fully envisage a bright A-level student using it and in the future that might even be where we see fresh ideas coming from."
Nell Barrie, Cancer Research UK's senior science information manager, said; "Research into cancer relies on international collaboration, and the CanSAR database makes it easy for scientists around the world to tap into huge amounts of information - from the lab and the clinic - to fuel new discoveries. The clues we need to tackle cancer are hidden in data like this and by making it freely available we can boost our progress and make breakthoughs sooner."