Characterizing the shape patterns of dimorphic yeast pseudohyphae.

Pseudohyphal growth of the dimorphic yeast Saccharomyces cerevisiae is analysed using two-dimensional top-down binary images. The colony morphology is characterized using clustered shape primitives (CSPs), which are learned automatically from the data and thus do not require a list of predefined features or a priori knowledge of the shape. The power of CSPs is demonstrated through the classification of pseudohyphal yeast colonies known to produce different morphologies. The classifier categorizes the yeast colonies considered with an accuracy of 0.969 and standard deviation 0.041, demonstrating that CSPs capture differences in morphology, while CSPs are found to provide greater discriminatory power than spatial indices previously used to quantify pseudohyphal growth. The analysis demonstrates that CSPs provide a promising avenue for analysing morphology in high-throughput assays.