docs <- Corpus(DirSource("path of the directory containing text documents"))
    f <- content_transformer(function(x, pattern)regmatches(x, gregexpr(pattern, x, ignore.case=TRUE)))
    genes = "IL1|IL2|IL3|IL4|IL5|IL6|IL7|IL8|IL9|IL10|TNF|TGF|AP2|OLR1|OLR2"
    docs <- tm_map(docs, f, genes)