First choose the wt amino
acid
residue (1 letter code), the
corresponding residue number (1-164), and any one of the 19 possible
residue
substitutions of the wt residue (1 letter code). Next, choose the
number of activity classes (2 or 4). For the two-class case, the
activity of a mutant is considered to be either "active" or "inactive".
Using four classes,
the mutant activity labels are "high", "medium", "low", or
"negative". Repeat for up to five single-point mutants of T4 lysozyme.
Finally, click on the "Check Activity Levels" button to
obtain the predicted activity levels of the requested T4 lysozyme
mutants.
All predictions are based on decision tree models generated by using
residual profile2
vectors for a training set of 2015 T4 lysozyme mutants
with experimentally measured activity levels. Decision tree models
based on the 1-against-all method are used for making the four-class
predictions. The activity levels for the training set data (those with
"known" activity
when queried above) can be located in Rennell et al.3
References