IQ develops innovative mining patterns and models
European researchers work diligently to develop and improve technology. Case in point is the EU-funded IQ ('Inductive queries for mining patterns and models') project, which has succeeded in generating new methods to analyse complex data from databases, and can then be used in real-life applications. IQ is supported under the Information and Society Technologies (IST) Theme of the Sixth Framework Programme (FP6) with EUR 1.5 million in funding. Before the project got off the ground, the team realised that a data-mining framework was missing. The researchers, led by Professor Saso Dzeroski from the Josef Stefan Institute in Slovenia, had determined that in order to secure one, inductive databases (IDBs) had to be created. IDBs contain both data and patterns, which can either be local like an item-set (i.e. a component of an association rule and consists of items) or global such as decision trees (i.e. tree diagram). Enter the Eve robot, which uses advanced artificial intelligence combined with innovative data-mining and knowledge-discovery techniques to analyse the results of pharmacological experiments it conducts itself. This 'scientist' will have the capacity to make informed guesses about the effectiveness of the chemical compounds fighting diseases. The new data mining techniques developed by the IQ consortium will help fuel Eve's success in drug discovery capabilities, especially because they permit knowledge discovery processes. By linking the chemical structure of the compound to its pharmacological activity, the Eve robot can determine which chemical compounds should be tested next. The end result is a degree of predictability in drug screen procedures. 'Over time, Eve will learn to pick out the chemical compounds that are likely to be most effective against a certain target by analysing data from past experiments and comparing chemical structures to their pharmacological properties,' ICT Results quoted Professor Dzeroski as saying. The researcher provided support in the development of Eve's data mining capabilities. 'That should help scientists and pharmaceutical companies identify more effective compounds to treat different diseases, allowing them to find drug leads in a fraction of the time and at a fraction of the cost of current methods,' he explained. One of the beauties of Eve lies in the fact that the robot could minimise the need for random testing of chemical compounds. 'Eve is the first computer system capable of originating its own experiments, physically performing them, interpreting the results and then repeating the cycle,' the Slovenian researcher commented. Based on the existing system, pharmacological researchers must conduct a blind study of tens or hundreds of thousands of chemical compounds. Once this is completed, they apply them to an assay for a disease. The results obtained establish the Quantitative Structure-Activity Relationships (QSARs), which relate the structure of a chemical compound to its pharmacological activity. The main problem with this system is that not only does it waste time, but it must be, more often than not, repeated every time researchers look for a new drug. 'We have carried out some preliminary trials and the compounds picked by Eve show more promise than those selected randomly,' Professor Dzeroski said. The IQ partners are Katholieke Universiteit Leuven (Belgium), University of Antwerp (Belgium), Albert-Ludwigs-Universität Freiburg (Germany), Institut National des Sciences Appliquées (INSA) de Lyon (France), University of Helsinki-Helsinki Institute for Information Technology (Finland), and University of Wales Aberystwyth (UK).
Countries
Belgium, Germany, Finland, France, United Kingdom