x = readLines("222.txt")

 > r=Corpus(VectorSource(x))> rA corpus with 7012 text documents

> writeCorpus(r)

> print(r)
A corpus with 7012 text documents
> summary(r)
A corpus with 7012 text documentsThe metadata consists of 2 tag-value pairs and a data frame
Available tags are:create_date creator
Available variables in the data frame are:MetaID 

> inspect(r[2:2])
  A corpus with 1 text document

The metadata consists of 2 tag-value pairs and a data frame
  Available tags are:
  create_date creator
  Available variables in the data frame are:
  MetaID

[[1]]
  Female; Genital Neoplasms, Female/*therapy; Humans

> r[[2]]
  Female; Genital Neoplasms, Female/*therapy; Humans

> dtm = DocumentTermMatrix(r)
> head(dtm)
A document-term matrix (6 documents, 16381 terms)Non-/sparse entries: 110/98176
Sparsity           : 100%
Maximal term length: 81
Weighting          : term frequency (tf)

> inspect(dtm[1:2,1:4])

> findFreqTerms(dtm,200)[1] "acute"          "adjuvant"       "advanced"       "after"         [5] "and"            "breast"         "cancer"         "cancer:"       [9] "carcinoma"      "cell"           "chemotherapy"   "clinical"
[13] "colorectal"     "factor"         "for"            "from"
[17] "group"          "growth"         "iii"            "leukemia"
[21] "lung"           "lymphoma"       "metastatic"     "non-small-cell"
[25] "oncology"       "patients"       "phase"          "plus"
[29] "prostate"       "randomized"     "receptor"       "response"
[33] "results"        "risk"           "study"          "survival"
[37] "the"            "therapy"        "treatment"      "trial"
[41] "tumor"          "with"          

inspect(removeSparseTerms(dtm, 0.4))

> findAssocs(dtm, "stem", 0.5)stem cells 1.00  0.61 

> dist_dtm <- dissimilarity(dtm, method = 'cosine')
> head(dist_dtm)
[1] 1.0000000 0.7958759 0.8567770 0.9183503 0.9139337 0.9309934

> hc <- hclust(dist_dtm, method = 'ave')
> plot(hc,xlab='')