How to build data matrix from mixed and messy CSV file?

Question

I have a huge .csv file like this :

Transcript Id   Gene Id(name)   Mirna Name  miTG score
ENST00000286800 ENSG00000156273 (BACH1) hsa-let-7a-5p   1         


        

Answer 1

You could try to structure the CSV using regular expressions:

textfile <- "ENST00000286800 ENSG00000156273 (BACH1) hsa-let-7a-5p   1
UTR3    21:30717114-30717142    0.05994568  
UTR3    21:30717414-30717442    0.13591267  
ENST00000345080 ENSG00000187772 (LIN28B)    hsa-let-7a-5p   1
UTR3    6:105526681-105526709   0.133514751"
txt <- readLines(textConnection(textfile))

sepr <- grepl("^ENST.*", txt) 
r <- rle(sepr)
r <- r$lengths[!r$values]

regex <- "(\\S+)\\s+(\\S+)\\s(\\([^)]+\\)\\s+\\S+)\\s+(\\d+)"
m <- regexec(regex, txt[sepr])
m1 <- as.data.frame(t(sapply(regmatches(txt[sepr], m), "[", 2:5)))
m1 <- m1[rep(1:nrow(m1), r),]

regex <- "(\\S+)\\s+(\\S+)\\s+(\\S+)"
m <- regexec(regex, txt[!sepr])
m2 <- as.data.frame(t(sapply(regmatches(txt[!sepr], m), "[", 2:4)))

df <- cbind(m1, m2[,-1])
names(df) <- c("Transcript Id",    "Gene Id(name)",   "Mirna Name",        "miTG score",    "UTR3",        "MRE_score"   )
rownames(df) <- NULL
df
# Transcript Id   Gene Id(name)                Mirna Name miTG score                  UTR3   MRE_score
# 1 ENST00000286800 ENSG00000156273     (BACH1) hsa-let-7a-5p          1  21:30717114-30717142  0.05994568
# 2 ENST00000286800 ENSG00000156273     (BACH1) hsa-let-7a-5p          1  21:30717414-30717442  0.13591267
# 3 ENST00000345080 ENSG00000187772 (LIN28B)    hsa-let-7a-5p          1 6:105526681-105526709 0.133514751