List of Main Keywords
See FAQ if you have questions. How to cite this applet? Are you looking for a new job in chemoinformatics?
- ANALYSIS Indicates method that will be used
to analyze data.
AVOID Indicates input variables that will not
be considered in the analysis.
- Two methods, i.e. to fit data and to select program parameters, namely
DEGREE and NUMBER, according to the LOO results, are currently available.
The variables indicated in this keyword will be deleted from the input
data set before any analysis.CRITERION Indicates criterion that will be
used to select the best model.
Two criterions, RR and RSS, are usually used in this approach and are
implemented in our program.DEGREE Indicate maximum degree of terms used
in the analysis.
Increase of this parameterINCLUDE Indicate input variables that will be
considered in the analysis.
The default value is to include all variables.INPUTS.Indicates
the number of input (independent) variables for neural network calculations.
This parameter should be identified for all calculations.ITERATIONS Number of algorithm iterations
The calculations will be stopped if maximal number of iterations was
exceeded.LOO Perform validation of the approach using the
A data entry is removed and its value predicted after neural network
calculations. This procedure is repeated for all data entries.MODELS Indicate if parameters of the models should
This keyword is useful to save calculated models for further analysis
of new data.NAMES.Indicate
if the first column of data table contains names.
Names should not contain spaces and tabs.NUMBER Indicates maximal number of terms in the
PRINT This paramter indicates options for output
The corresponding checkbox should be checked to activate each option.REVERSED.Indicates
that the reversed order of input and target values is used in the data
The standard order is X, independent variables, are followed by Y,
targets or dependent variables.STORED Indicates number of the best models that
will be selected by the program.
VALIDATION Indicate which data entries (rows)
will be used as a validation data set.
This option can be only used with RR criterion. Indicate parameters
that should be always verified.