geneDef {PCAN} | R Documentation |
Basic information about genes Only genes associated to at least one OMIM disease are taken into account.
A data frame with 3265 rows and 3 columns:
Entrez gene ID.
Gene name.
Gene symbol.
These data are used to examplify the different functions of the package. More data are available in the MultiHumanPhenoDB package.
ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/xml/ClinVarFullRelease_2015-05.xml.gz
## Prerequisite data(geneByHp, hp_descendants, package="PCAN") geneByHp <- unstack(geneByHp, entrez~hp) ic <- computeHpIC(geneByHp, hp_descendants) ########################################### ## Use case: comparing a gene and a disease data(traitDef, geneDef, hp_ancestors, hpDef, package="PCAN") omim <- "612285" traitDef[which(traitDef$id==omim),] entrez <- "57545" geneDef[which(geneDef$entrez==entrez),] ## Get HP terms associated to the disease data(hpByTrait, package="PCAN") hpOfInterest <- hpByTrait$hp[which(hpByTrait$id==omim)] ## Get HP terms associated to the gene hpByGene <- unstack(stack(geneByHp), ind~values) geneHps <- hpByGene[[entrez]] ## Comparison of the two sets of HP terms compMat <- compareHPSets( hpSet1=geneHps, hpSet2=hpOfInterest, IC=ic, ancestors=hp_ancestors, method="Resnik", BPPARAM=SerialParam() ) ## Get the symmetric semantic similarity score hpSetCompSummary(compMat, method="bma", direction="symSim") bm <- hpSetCompBestMatch(compMat, "b") hpDef[match(c(bm$compared, bm$candidate), hpDef$id),]