Mapping gene symbols to KEGG pathways

mapping_symb2path.R

library(clusterProfiler)
library(org.Hs.eg.bd) 
library(KEGGREST)
library(dplyr)
library(magrittr)

# List of genes of interest
x <- c("GPX3",  "GLRX",   "LBP",   "CRYAB", "DEFB1", "HCLS1",   "SOD2",   "HSPA2",
       "ORM1",  "IGFBP1", "PTHLH", "GPC3",  "IGFBP3","TOB1",    "MITF",   "NDRG1",
       "NR1H4", "FGFR3",  "PVR",   "IL6",   "PTPRM", "ERBB2",   "NID2",   "LAMB1",
       "COMP",  "PLS3",   "MCAM",  "SPP1",  "LAMC1", "COL4A2",  "COL4A1", "MYOC",
       "ANXA4", "TFPI2",  "CST6",  "SLPI",  "TIMP2", "CPM",     "GGT1",   "NNMT",
       "MAL",   "EEF1A2", "HGD",   "TCN2",  "CDA",   "PCCA",    "CRYM",   "PDXK",
       "STC1",  "WARS",  "HMOX1", "FXYD2", "RBP4",   "SLC6A12", "KDELR3", "ITM2B")
       
# Need to specify an annotation package; here we use org.Hs.eg.bd
# Note: the interface of bitr has changed; earlier versions used AnnoDb instead of OrgDb
map_symb2entrez <- clusterProfiler::bitr(x, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = "org.Hs.eg.db")

# keggLink outputs ENTREZID of the form 'hsa:####', and so we need to remove the first four characters
map_entrez2path <- KEGGREST::keggLink("hsa", "pathway") %>%
  substr(start = 5, stop = nchar(.)) %>%
  data.frame(PATH = names(.), ENTREZID = ., 
             stringsAsFactors = FALSE)
             
# Inner join to link the two
map_gene2path <- dplyr::inner_join(map_symb2entrez, map_entrez2path, by = "ENTREZID")

# You can also get the names of each pathway
KEGGREST::keggGet(c("path:hsa00480", "path:hsa00590")) %>%
  sapply(function(query) query$NAME)