Please join us this Friday March 7th for the David A Walsh Seminar for the Arts and Sciences in Snell 213 at noon.
Our speaker is Prof. Emmanuel Asante-Asamani, Assistant Professor in the Department of Mathematics at Clarkson, will speak about “Quantifying bristle cell patterns in fruit flies.”
Abstract
Repeating patterns are important for epithelia that sense the environment. Optimizing the organization of these tissues helps them to function normally. A major challenge for researchers is the ability to quantify and classify complex cell and tissue patterns across wildtype and perturbed conditions. We study this problem in the fruit fly Drosophila melanogaster, where the organization of sensory bristles on its thorax contributes to the proper function of its peripheral nervous system. A well-known perturbation in bristle cell organization is density, which has been found to increase in certain fly mutants. It is unclear if this density phenotype is shared by other mutants and whether additional pattern features beyond density exist that can be used to distinguish bristle patterns. In this study, we investigate the utility of clustering features of bristle organization in distinguishing between wildtype and perturbed patterns. We use the DB-Scan algorithm to identify and extract additional clustering features which, in addition to the pattern density, are used to train a logistic regression-based classification model. Our study finds pattern density and cluster heterogeneity to be the most significant features for quantifying bristle cell patterns and suggests that including both features in a
classification model maximizes predictive accuracy.