0 ×

PLS Model Building

Schrödinger extension for KNIME Workbench version 20.3.139.202008121324 by Schrödinger

PLS analysis is carried out on input data to build a multiple linear regression model that can then be applied to other data sets. Both training set and testing set are required as input, these can be created using the Partitioning or Row Splitter KNIME nodes. Input data must contain 2 or more columns of numerical data, for the independent variables (X) and the dependent variable (Y).

Backend implementation

utilities/canvasPLS
canvasPLS is used to implement this node.

Options

Column containing structure titles
Select the column containing the title for each structure
Include input columns in output data
If selected, output plot data will also contain all input columns
Output PLS model name
The name of the output PLS model should be entered here
X variables
Select the independent X variables for the analysis
Y variable
Select the dependent Y variable (must not be the same as any X variable)
Maximum number of PLS factors
Specify the maximum number of PLS factors to use in the regression model. Regression models are built for increasing numbers of PLS factors up to this number.
Stop adding PLS Factors when SD drops to N
Select this option to stop adding PLS factors when the standard deviation of the regression drops below the value specified in the text box. Using this option could result in fewer PLS factors than the number specified in the Maximum number of PLS factors box.
Autoscale X variables
Scale the X variables by dividing the values of each property by the standard deviation in the value of the property.
Eliminate X variables with [t-value] less than N
Eliminate X variables whose t-value is less than the value given in the text box.

Input Ports

Icon
Numerical data of the training set variables
Icon
Numerical data of the test set variables (identical Variable columns as defined for the Training set)

Output Ports

Icon
PLS Model and statics for each factor
Icon
Factor loadings
Icon
Plot data showing observed and predicted values of Y for both the training and test sets.

Views

Log view of PLS Model Building
Log view of PLS Model Building
Program out view of PLS Model Building
Program out view of PLS Model Building

Best Friends (Incoming)

Best Friends (Outgoing)

Installation

To use this node in KNIME, install Schrödinger Extensions for KNIME from the following update site:

KNIME 4.2
Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform.

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.