W0298
Automated Evaluation of Crystallisation Experiments.
Julie Wilson, York Structural Biology Laboratory, Dept. of Chemistry, Univ.
of York, Heslington, York YO10 5YW, England, e-mail:
julie@ysbl.york.ac.uk
A method to automatically evaluate images from crystallisation
experiments is being developed. It will not only indicate the presence or
absence of crystal-like objects but also classify of other possible outcomes of
crystallisation experiments. This will allow promising conditions that can be
optimised to produce diffraction quality crystals to be identified. Furthermore,
the results of failed experiments can also be stored, allowing automated
screening protocols to be developed to reduce the number of necessary
crystallisation trials.
Image discontinuities are used to identify artifacts within
the crystallisation drop. These are then considered as individual objects and
evaluated in terms of a number of attributes related to size and shape,
curvature of the boundary and variance in intensity. Other more obvious
crystal-like characteristics such as straight sections of the boundary and
straight lines of constant intensity within the object are also calculated and a
set of values, or feature vector is assigned to each object. A combination of
Kohonen self-organising maps and decision trees are used for classification. The
weights are obtained from the feature vectors associated with a training data
set, consisting of objects from each class that have been pre-classified by eye.
Consistent patterns in the combination of the variables allow new objects to be
assigned to various classes and given a related score. An overall score is then
given for the image.