visunet: VisuNet: an interactive tool for network visualization of...

In komorowskilab/VisuNet: An interactive tool for network visualization of rule-based models in R

Description

VisuNet is an interactive tool for network visualization of complex rule-based classifiers. See the documentation.

Usage

visunet(
  ruleSet,
  type = "RDF",
  NodeColorType = "DL",
  NodeSize = "DC",
  CustObjectNodes = list(),
  CustObjectEdges = list()
)

Arguments

ruleSet	the appropriately formatted set of rules: R.ROSETTA data frame - the rules data frame that is the output of R.ROSETTA can be directly imported in VisuNet. See rosetta for details. "Line by line" file format - input data should be in a data frame format that contains the following columns: features - the left-hand side of the rule corresponding to comma-separated attributes and their values, of type, type "factor" decision - the right-hand side of the rule corresponding to the decision value, of type "factor" accuracyRHS - the rule accuracy, of type "numeric" supportRHS - the rule support, of type "numeric" decisionCoverage or coverageRHS - the fraction of correcly classfied objects, of type "numeric"
type	a character string specifying the type of the input data: "RDF" - the R.ROSETTA output (see rosetta) "L" - the "Line by line" file format (see saveLineByLine)
NodeColorType	a character string specifying the color of nodes: "DL" - feature discretization levels, option is available for data discretized into three levels: 1, 2 and 3. In the case of gene expression, data discretization levels correspond to: 1 - under-expressed gene, 2 - no change gene expression and 3 - over-expressed gene. "A" - color of nodes defined by the mean accuracy value for the node. The default is "DL".
NodeSize	a character string specifying the size of nodes: "DC" - the mean decision coverage for the feature "S" - the mean support for the feature If the decision coverage value is unavailable, the support is taken by default.
CustObjectNodes	a list that contains the customized VisuNet output for nodes. The list needs to contain two variables: nodes - a customized VisuNet output for nodes CustCol - the names of variables added/changed in the VisuNet output for nodes. See visNodes for details.
CustObjectEdges	a list that contains customized VisuNet output for edges. The list needs to contain two variables: edges - a customized VisuNet output for edges CustCol - the names of variables added/changed in the VisuNet output for edges. See visEdges for details.

Value

Rule Network Object - a collection of lists corresponding to decision variables and an additional list for the combined decision ‘all’. The lists contain information required to reproduce the rule network, i.e. data frames for nodes, edges and RulesSetPerNode - a list that shows rules for each node.

Structure of the data frame for nodes:

• id - a unique node id, based on attribute value and left-hand side value of the rule set

• label - the attribute variable without the ‘=value’ part from the left-hand side of the rule set

• DiscState - the attribute value

• color.background - the node color

• value - the node size

• color.border - the color of the node border

• meanAcc - the mean accuracy value of all rules that contain the node

• meanSupp - the mean support value of all rules that contain the node

• NRules - the number of rules that contain the node

• PrecRules - fraction of rules that contain the node

• NodeConnection - the total connection value obtained from the rules that contain the node

• title - information visible on the tooltip

• group - the decision value that occurs most frequently (>50 otherwise group contains all comma-separated decision values corresponding to rules associated with the node. group defines the content of the ‘Select by decision’ drop-down box.

Structure of the data frame for edges:

• from, to - the pair of nodes that create the edge

• conn - the connection variable obtained from the edge-associated rules.

• connNorm - the connection variable normalized according to the maximum connection variable in the rule network

• label2 - the edge id

• color - the edge color

• title - information visible on the tooltip

• width - the edge width, defined according to the normalized connection value

References

See the documentation for more details and examples.

Examples

#The R.ROSETTA output format
#the rule-based model construction using R.ROSETTA
resultsRos <- rosetta(autcon)
vis_out <- visunet(resultsRos$main, type = "RDF")
------------

#"Line by line" file format
rules <- autcon_ruleset
vis_out <- visunet(rules, type = "L")

komorowskilab/VisuNet documentation built on Feb. 18, 2022, 8:16 p.m.