findGenes: Find gene names
In cstubben/pmcXML: Tools to parse full text XML documents from PMC Open Access

Description Usage Arguments Details Value Note Author(s) Examples

Find gene names in PMC text or tables using pattern matching

1	findGenes(txt)

txt

A PMC txt or table object

Find genes names in pmcText or pmcTable output. PMC text should be split into sentences

A data.frame with id, source, gene and mention

Matches words with second and third letter lower case and fourth letter upper case. This does not find three letter gene names

Chris Stubben

## Not run: 
doc <- pmcOAI("PMC2231364" )
txt <-pmcText(doc)
y <-findGenes(txt)
table(y$gene)

## italics (inlcuding tables)
x <- gdata::trim( xpathSApply(doc, "//body//italic", xmlValue) )
## most of these are not genes...
table( x[nchar(x)==3] )

## End(Not run)