consolidate_entity_attribute: removes the redundant attributes based on the mutual...

In pasculescu/ClusterJudge: Judging Quality of Clustering Methods using Mutual Information

Description

Calculates the mutual information between every pair of attributes and the uncertainty level (as defined in the reference ...) Plots the distribution of the uncertainty and the selected levels of uncertainty that are used as filteres.

Usage

consolidate_entity_attribute(entity.attribute, min.entities.per.attr, mut.inf=NULL
                           , U.limit = c(0.8, 0.6, 0.4, 0.2, 0.1, 0.01, 0.001)
                           , plot.saveRDS.file=NULL)

Arguments

entity.attribute	data frame or matrix with 2 columns The assumption is that first column represent some 'entities' like gene names or gene ids. And the second column represents ‘attributes' of entities (for example Gene Ontology ID ’GO:0007260' which is 'tyrosine phosphorylation of STAT protein') Usually this is a consolidated entity.attribute where the attributes with very low number of entities or with very low mutual information have been removed (see consolidate_entity_attribute and the definition of Uncertainty on attributes mutual information)
min.entities.per.attr	a number or NULL
mut.inf	the mutual information square matrix before applying any filteres based on the uncertainty or NULL
U.limit	a numerical vector
plot.saveRDS.file	if not NULL must be a string represented a file location where the plot will be saved as an RDS object. The plot can be then retrieved at any time using readRDS function.

Value

a data frame (if mut.inf argument is null) or a list of data frames. The data frames are the 'consolidated' entity.attribute structures. Where the consolidation of attributes is based on a minimum number of entities per attribute or on the mutual information between attributes.

Author(s)

Adrian Pasculescu

References

Gibbons, F.D. and Roth F.P., (2002) Judging the Quality of Gene Expression-Based Clustering Methods Using Gene Annotation. Genome Research, vol. 12, pp1574-1581.

Examples

data(Yeast.GO.assocs)
data(mi.GO.Yeast)

Yeast.GO.assocs.cons <- consolidate_entity_attribute(entity.attribute = Yeast.GO.assocs
                                                   , min.entities.per.attr =3
                                                   , mut.inf=mi.GO.Yeast
                                                   ,U.limit = c(0.01, 0.001)
                                                   ,plot.saveRDS.file='this_plot.rds') ### save also the plot

str(Yeast.GO.assocs.cons)
pdf('my_plot.pdf') ### place the plot saved by consolidate_entity_attribute into a pdf file
plot(readRDS('this_plot.rds')) ### 
dev.off()

pasculescu/ClusterJudge documentation built on May 29, 2019, 4:52 p.m.