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.
© 2015 The Author(s). Published by Journal of Integrative Bioinformatics.
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.