Research lead
Researchers from Ruder Boškovic Instititute and Faculty of Natural Sciences and Mathematics from Zagreb, Croatia, have combined traditional molecular biology techniques with an artificial intelligence system, to develop a novel approach for producing protein fingerprints of diverse tissues. They say this could form the basis of convenient new methods in medical diagnostics.
To date over half a million different protein species have been identified in humans, and different tissues, such as muscles, bones, nerves or skin, are distinguished by unique protein fingerprints of the different proteins contained in their cells. Pathological changes in any type of tissue have an impact on the protein composition, and therefore protein fingerprinting can be used for early diagnosis and identification of diseases such as tumours or infections.
Until now, producing a good quality protein fingerprint has been complicated, time consuming and expensive. The Croatian team have used artifical intelligence techniques to train a computer to extract the most relevant information on the protein fingerprint from the fuzzy experimental data obtained by 1D protein electrophoresis, a well known, simple, quick and cheap technique. This opens up the possibility of a cheap, convenient and reliable method for producing good quality protein fingerprints.
The work will be published in the January issue of the journal Proteomics.
Receive the Funding Newswire each Tuesday, our Policy Bulletin each Thursday, and news about bridging Europe’s east-west innovation gap twice a month in The Widening. 
A unique international forum for public research organisations and companies to connect their external engagement with strategic interests around their R&D system.
