Cell High Throughput Imaging : investigate how separable are different conditions using bootstrap.
by
Andreas Hadjiprocopis, Institute of Cancer Research, London (contact details: 'andreashad2' then the funny snail symbol then 'gmail.com' without the quotes)


A large number of cells belonging to a variety of cell lines, grown in a variety of media and under different treatment conditions and durations (see here for details) have been imaged and their individual morphological features extracted (e.g. area, area of cytoplasm, ruffliness, etc.).

In order to investigate whether different cell-lines and treatment conditions have actually statistically significant different cell shape and texture we have devised a method using support vector machines, permutation tests and the bootstrap.

The result is a matrix of the degree of separability between the different cell lines, treatment conditions and treatment durations as below (separability is scaled between 0/white and 100/red, with 100/red meaning most separable):

Click on images to zoom in and out.