Machine Learning approach to discriminate Saccharomyces cerevisiae yeast cells using sophisticated image features

More Information | Back to archive
Full Text of this article Full article [PDF] (724,86 kB)
doi doi:10.2390/biecoll-jib-2015-276
submission September 08, 2015
last revision September 09, 2015
published October 06, 2015

Mohamed S. Tleis and Fons J. Verbeek

Correspondence should be addressed to:
Mohamed Tleis
Niels Bohrweg 1, 2333 CA Leiden, The Netherlands
ln.vinunediel.scail@nullsielt.m


Abstract

In biological research, Saccharomyces cerevisiae yeast cells are used to study the behaviour of proteins. This is a time consuming and not completely objective process. Hence, Image analysis platforms are developed to address these problems and to offer analysis per cell as well. The robust segmentation algorithms implemented in such platforms enables us to apply a machine learning approach on the measured cells. Such approach is based on a set of relevant individual cell features extracted from the microscope images of the yeast cells. In this paper, we composed a set of features to represent the intensity and morphology characteristics in a more sophisticated way. These features are based on first and second order histograms and wavelet-based texture measurement. To show the discrimination power of these features, we built a classification model to discriminate between different groups. The building process involved evaluation of a set of classification systems, data sampling techniques, data normalization schemes and attribute selection algorithms. The results show a significant ability to discriminate different cell strains and conditions; subsequently it reveals the benefits of the classification model based on the introduced features. This model is promising in revealing subtle patterns in future high-throughput yeast studies.

Reference

Mohamed S. Tleis and Fons J. Verbeek. Machine Learning approach to discriminate Saccharomyces cerevisiae yeast cells using sophisticated image features. Journal of Integrative Bioinformatics, 12(3):276, 2015. Online Journal: http://journal.imbio.de/index.php?paper_id=276
imprint | sitemap | credits | top