idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
idw - Informationsdienst
Wissenschaft
Chemists of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) are developing an artificial intelligence application which can predict which molecule structures will produce or suppress specific odours. The Volkswagen Foundation has granted the project 96,100 euros of funding for the next 18 months as part of its ‘Experiment!’ programme.
It’s something that everyone has experienced. You buy an inflatable exercise ball to improve your posture at your desk, but you have to leave it outside for the first three days until it no longer stinks. Or you pick up a packaged salami at the supermarket and it smells more like plastic than beechwood smoke. Researchers at FAU’s Computer Chemistry Center (CCC) are working to make undesirable smells in packaging and products a thing of the past. To this end, they are developing an artificial intelligence application that can predict with great certainty which molecule combinations neutralise or specifically foster odours. The project is called ‘CLINGON: Computer Linguistics of Olfaction’ and will receive close to 96,100 euros of funding over the next year and a half from the Volkswagen Foundation.
Understanding the molecule as a sentence
‘We will be spending most of our time working at the computer, not in the laboratory,’ said Dr. Thilo Bauer. Together with Dr. Tatyana Shubina from CCC and Prof. Dr. Andrea Büttner from the Chair of Food Chemistry, Bauer has developed a database which pools knowledge about the molecular structure of fragrances and aromas: ‘We use computer linguistics for this purpose. It’s similar to processing language; the programme is supposed to understand odour molecules as a sentence in which the molecule fragments represent the words. The combination of the fragments determines the meaning of the sentence, or in our case, the smell.’
Avoiding and creating odours
In the near future the FAU chemists hope to use pattern recognition to make reliable predictions about the creation of odours, thus making time-consuming trial and error experiments unnecessary – and not only for purposes of avoiding certain odours, but also for creating scents. ‘In the cosmetics industry many thousands of molecules are synthesised and tested for their scent every year. Only a few of them ever make it onto the market,’ said Thilo Bauer. ‘Our programme could help to make the development of new products more effective and resource-efficient.’
Funding ambitious research projects
The Volkswagen Foundation uses its funding initiative ‘Experiment!’ to foster ambitious research projects which fundamentally challenge established ideas, strive to establish unconventional hypotheses, methods or technologies or strike out in wholly new directions in research. Researchers from the natural sciences, engineering and life sciences have the opportunity to test the practicability of their concept during the exploratory phase, which is limited to 100,000 euros in funding over 18 months. The Foundation explicitly accepts failure of the funded projects as a result. Since the initiative was established in November 2012, 67 proposals have been approved.
Further information:
Dr. Thilo Bauer
Phone: +49 9131 8570229
thilo.bauer@fau.de
https://www.fau.eu/2016/12/14/news/research/artificial-intelligence-to-predict-o...
Criteria of this press release:
Journalists
Chemistry
transregional, national
Research projects
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
