EU researchers have developed a virtual laboratory to help doctors around the world match drugs to patients and to make treatments for HIV, the virus that causes AIDS, and other infectious diseases more effective. EU support for the research came from the VIROLAB ('Virtual laboratory for decision support in viral diseases treatment') project, which received EUR 3.3 million from the 'Information society technologies' (IST) Thematic area of the Sixth Framework Programme (FP6). The VIROLAB, scheduled to be online before the end of 2010, uses the latest advances in machine learning, data mining, grid computing, modelling and simulation to turn the content of millions of scientific journal articles, databases and patients' medical histories into knowledge that can effectively be used to treat disease. Up to seven hospitals are already using the virtual laboratory to provide personalised treatment to HIV patients, and it is attracting widespread interest as a potent decision-support tool for doctors. 'VIROLAB finds new pathways for treatment by integrating different kinds of data, from genetic information and molecular interactions within the body, measured in nanoseconds, up to sociological interactions on the epidemiological level spanning years of disease progression,' explained Peter Sloot, a computational scientist at the University of Amsterdam in the Netherlands, and the coordinator of VIROLAB. HIV, like other viruses, poses great challenges because it frequently mutates and can quickly become resistant to drugs. Doctors therefore need to know which medications are likely to be effective in slowing the progression of the disease, taking into account the strain of the virus, the patient's own medical history, genetic information and even sociological factors. 'It's like a lock and key,' said Professor Sloot. 'Drugs are keys made to fit certain locks, which are part of the viruses. If the locks change then the key no longer fits - and each lock is different for each patient. That is why we need personalised medicine.' The system continuously crawls grid-connected databases of virological, immunological, clinical, genetic and experimental data, extracts information from scientific journal articles and draws on other sources of information. This data is then processed to give it machine-readable semantic meaning and analysed to produce models of the likely effects of different drugs on a given patient. Each medication is then ranked according to its predicted effectiveness in light of the patient's personal medical history, and the information delivered via a simple-to-use web interface. The system records every step it and the doctor take to find the right drug for a patient, and allows cases of other patients living a few streets or even thousands of kilometres (km) away to be compared. Moreover, it can generate models simulating the likely spread and progression of different mutations of viruses based not only on medical data but also on sociological information. 'Say a government has EUR 500 million to spend on HIV research and wants to know whether they should focus on funding the development of new drugs or on preventive measures, we can give them an answer as to what would be more effective,' Professor Sloot pointed out. He said the project's focus on HIV was driven by the scale and importance of the AIDS epidemic and by the wealth of information about the disease. HIV drug resistance is one of the few areas in medicine where genetic information has been widely used for a considerable number of years. Professor Sloot and other VIROLAB partners are now looking at how the programme could be used to create personalised drug rankings to improve the treatment of people suffering from other diseases. This research is being carried out via DYNANETS ('Computing real-world phenomena with dynamically changing complex networks'), an EU-funded project looking at drug dynamics in people infected with the H1N1 flu virus and co-infections, in addition to drug-resistant HIV. Support for DYNANETS stands at EUR 2.41 million.