To focus on the differences between the two classes we develop a discriminative HMM classifier.
In fact, comparing the width/depth ratio between the two classes, we observed that Type III notch presents averagely a lower value and consequently a smaller space available for the suprascapular nerve, increasing the possibility to have a case of suprscapular nerve entrapment.
To explain our results, we further investigated the communication intensity (i.e., the number of successful meetings) between the social classes we defined.
Since the objective was to create a classifier being able to discriminate between the different classes, we needed a balanced training dataset, or at least a large number of samples for each class.
To enable comparison of doses between the antidepressant classes, we converted daily dose to a defined daily dose, by using values assigned by the World Health Organization's Collaborating Centre for Drug Statistics Methodology (www.whocc.no/atc_ddd_index).
Since the GO-scores discriminate quite well between the two disease classes, we analysed the GO-terms that contribute the most to the prediction process.
When we used it to determine the differences between cell classes, we first averaged the cell lines in the four classes (HMEC, MSSM, N-est and T-est) and then performed the comparisons as instructed by the manufacturer.
As a measure of the power to discriminate between genotype classes, we used the Welch statistic (the t-statistic appropriate when the variances of classes are unequal, using the standard output for the t.test function in R [ 33]).
Because they represent the most dramatic differences between the two thioesterase classes, we chose to evaluate the effect of each of the residues flagged with red hourglass icons.
In an effort to increase the power of the statistical analyses to detect differences in the performance of the three tests between age classes, we used samples from badger populations where the likelihood of encountering TB positive individuals was known to be high [ 6, 14].
