1.3 Heat Map with Dendrogram

Summary

The Heat Map with Dendrogram app can be used to

  1. Impute missing values, standardize data and perform log2 transform
  2. Perform hierarchical cluster analysis along columns and rows
  3. Plot heat map with dendrogram

Tutorial

  1. Right-click on the Heat Map with Dendrogram icon Heat Map with Dendrogram icon.png in the Apps Gallery and select Show in Folder.
  2. The GSEData.ogw workbook file is in the pop-up folder. Open this workbook file in Origin.
  3. Click on the Heat Map with Dendrogram icon Heat Map with Dendrogram icon.png to open the dialog.
  4. In the dialog, select Rows from Standardize drop-down list. The dialog settings is shown as below.
    Note: Pressing F1 key, the help file for this dialog will pop-up.
    Heat Map with Dendrogram 01.png
  5. Click OK. A Heat Map graph is created. Double click on X axis, in the opened X Axis dialog, go to Tick Labels tab, select Format sub-tab, and choose 45 from Rotate (deg.) combo box. Click OK button.
    Heat Map with Dendrogram 02.png
  6. The graph will look like as below.
    Heat Map with Dendrogram 03.png

Heatmap with Dendrogram Dialog Box

Input Data

Select data in the worksheet to plot heatmap with dendrogram.

Input Worksheet Specify the worksheet for data to plot.
Column Labels in Specify column labels for heatmap's x axis.
  • None

Use row number as heatmap's x axis tick labels.

  • 1st Row

Use 1st row in the worksheet as heatmap's x axis tick labels.

  • Long Name

Use column's long Name in the worksheet as heatmap's x axis tick labels.

  • Units

Use column's Units in the worksheet as heatmap's x axis tick labels.

  • Comments

Use column's Comments in the worksheet as heatmap's x axis tick labels.

Row Labels in Specify row labels for heatmap's y axis.
  • None

Use row number as heatmap's y axis tick labels.

  • 1st Column

Use 1st column in the worksheet as heatmap's y axis tick labels.

Transform

Transform data before plotting.

Impute Missing Value Specify the way to handle missing values.
  • None

Keep missing values

  • with Row Mean

Replace missing value with row mean.

  • with Column Mean

Replace missing value with column mean

Standardize Specify the method to standardize variables.
  • None

Data are not standardized.

  • Columns

Columns are standardized with zero mean and unit standard deviation.

  • Rows

Rows are standardized with zero mean and unit standard deviation.

Log2 Transform Specify whether to perform log2 transform.

Settings

Specify settings for the Hierarchical Cluster Analysis along columns and rows.

Cluster Specify the dimension to cluster data.
  • Columns

Perform Hierarchical Cluster Analysis along rows and cluster columns.

  • Rows

Perform Hierarchical Cluster Analysis along columns and cluster rows.

  • Both

Perform Hierarchical Cluster Analysis along rows and cluster columns, then along columns and cluster rows.

Cluster Columns Specify settings to cluster columns.
  • Cluster Method

Specify the linkage method to calculate the distance between a cluster and a new cluster. See cluster method options in Hierarchical Cluster Analysis

  • Distance Type

Specify a distance type to calculate the distance between two columns. See distance type options in Hierarchical Cluster Analysis

  • Number of Clusters

Specify the number of clusters. The value should be greater than 0 and no more than the number of columns.

Cluster Rows Specify settings to cluster rows.
  • Cluster Method

Specify the linkage method to calculate the distance between a cluster and a new cluster. See cluster method options in Hierarchical Cluster Analysis

  • Distance Type

Specify a distance type to calculate the distance between two rows. See distance type options in Hierarchical Cluster Analysis

  • Number of Clusters

Specify the number of clusters. The value should be greater than 0 and no more than the number of rows.

Plot Data

Specify the worksheet for heatmap plot data.

Recalculate

Specify the way to recalculate and update the result if there is any change in the input data or settings.

None The output will not be connected to the source data, and any change will not result in an update of the result. And you can't change settings to recalculate the result.
Auto The result automatically updates when source data change. You can also change settings to recalculate the result.
Manual The result will not automatically update when the source data changes. You must manually activate the update by clicking the Recalculate button Button Recalculate Manual.png in the Standard toolbar. You can also change settings to recalculate the result.

HeatmapDendrogram X-Function (Pro)

Brief Information

Perform hierarchical cluster analysis, and plot heatmap with dendrogram.

Command Line Usage

HeatMapDendrogram iw:=[Book1]Sheet1 -r 2 impute:=0 std:=2;

Variables

Display
Name
Variable
Name
I/O
and
Type
Default
Value
Description
Input Worksheet iw

Input

Worksheet

<active>
Specify the worksheet for data to plot.
Column Labels in clabel

Input

int

2
Specify column labels for heatmap's x axis.

Option list:

  • 0:None

Use row number as heatmap's x axis tick labels.

  • 1:1st Row

Use 1st row in the worksheet as heatmap's x axis tick labels.

  • 2:Long Name

Use column's long Name in the worksheet as heatmap's x axis tick labels.

  • 3:Units

Use column's Units in the worksheet as heatmap's x axis tick labels.

  • 4:Comments

Use column's Comments in the worksheet as heatmap's x axis tick labels.

Row Labels in rlabel

Input

int

1
Specify row labels for heatmap's y axis.

Option list:

  • 0:None

Use row number as heatmap's y axis tick labels.

  • 1:1st Column

Use 1st column in the worksheet as heatmap's y axis tick labels.

Impute Missing Value impute

Input

int

0
Specify the way to handle missing values.

Option list:

  • 0:None

Keep missing values

  • 1:with Row Mean

Replace missing value with row mean.

  • 2:with Column Mean

Replace missing value with column mean

Standardize std

Input

int

None
Specify the method to standardize variables.

Option list:

  • 0:None

Data are not standardized.

  • 1:Columns

Columns are standardized with zero mean and unit standard deviation.

  • 2:Rows

Rows are standardized with zero mean and unit standard deviation.

Log2 Transform log2

Input

int

0
Specify whether to perform log2 transform.
Cluster cluster

Input

int

2
Specify the dimension to cluster data.

Option list:

  • 0:Columns

Perform Hierarchical Cluster Analysis along rows and cluster columns.

  • 1:Rows

Perform Hierarchical Cluster Analysis along columns and cluster rows.

  • 2:Both

Perform Hierarchical Cluster Analysis along rows and cluster columns, then along columns and cluster rows.

Cluster Columns trcol

Input

TreeNode

<unassigned>
Specify settings to cluster columns.
Cluster Rows trrow

Input

TreeNode

<unassigned>
Specify settings to cluster rows.
Plot Data od

Output

Worksheet

[<new>]<new>!
Specify the worksheet for heatmap plot data.

trcol

The trcol treenode specifies settings to cluster columns.

Syntax: trcol.Treenode:= <value>

Example: trcol.nc:=2

Treenode Label Type Default Description
link Cluster Method int 2 Specify the linkage method to calculate the distance between a cluster and a new cluster. See cluster method options in hcluster X-Function.
dist Distance Type int 0 Specify a distance type to calculate the distance between two columns. See distance type options in hcluster X-Function.
nc Number of Clusters int 1 Specify the number of clusters. The value should be greater than 0 and no more than the number of columns.

trrow

The trrow treenode specifies settings to cluster rows.

Syntax: trrow.Treenode:= <value>

Example: trrow.nc:=2

Treenode Label Type Default Description
link Cluster Method int 2 Specify the linkage method to calculate the distance between a cluster and a new cluster. See cluster method options in hcluster X-Function.
dist Distance Type int 0 Specify a distance type to calculate the distance between two rows. See distance type options in hcluster X-Function.
nc Number of Clusters int 1 Specify the number of clusters. The value should be greater than 0 and no more than the number of rows.