Menu
The matrix which I have:
> dput(head(data1))
structure(c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0,
0, 0, 1, 0, 1, 0, 0), .Dim = c(6L, 18L), .Dimnames = list(c("AT1G01050",
"AT1G01080", "AT1G01090", "AT1G01320", "AT1G01470", "AT1G01800"
), c("10", "33.95", "58.66", "84.42", "110.21", "134.16", "164.69",
"199.1", "234.35", "257.19", "361.84", "432.74", "506.34", "581.46",
"651.71", "732.59", "817.56", "896.24")))
To make it easier to explain I will show the table below:
10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
AT1G01050 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0
AT1G01080 0 0 0 0 1 0 1 0 1 0 1 0 0 1 0 1 0 1
AT1G01090 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 0
AT1G01320 0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 1 0 1
AT1G01470 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
AT1G01800 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0
As you see my table is full of 0 and 1. There is in many cases more than one 1 in each row. So what I would like to do is duplicate/triplicate the rows just to leave a single 1 in each row. So for Example take a first row:
10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
AT1G01050 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0
There are two number 1 in this row. That means I have to create one more row for this "gene". So the output should look like that. I leave first 1 (starting from the left) in the data but remove the second. To distinguish later we have to change the name of the row as well:
10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
AT1G01050_1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
Now I remove first 1 and leave the second.
10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
AT1G01050_2 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
I believe it's not easy to do but I believe that one of you may have any idea how to solve that problem.
586
Try this:
divideLine = function(u)
{
index = which(u %in% 1)
len = length(u)
if(sum(u)<=1) return(t(u))
t(mapply(function(x,y){vec=rep(0, len);vec[y]=1;vec}, 1:length(index), index))
}
lst = apply(mat,1,divideLine)
x = lapply(lst, nrow)
res = do.call(rbind, lst)
rownames(res)=unlist(Map(function(u,v) paste(v, as.character((1:u)-1), sep='_'),x, names(x)))
#> res
# 10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
#AT1G01050_0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
#AT1G01050_1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
#AT1G01080_0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0
#AT1G01080_1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0
#AT1G01080_2 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
#AT1G01080_3 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
#AT1G01080_4 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
#AT1G01080_5 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
#AT1G01080_6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1
#AT1G01090_0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
#AT1G01090_1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
#AT1G01090_2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
#AT1G01320_0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0
#AT1G01320_1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
#AT1G01320_2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
#AT1G01320_3 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1
#AT1G01470_0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#AT1G01800_0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0
#AT1G01800_1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
May be this helps:
indx <- rep(1:nrow(data1), rowSums(data1!=0))
res <- do.call(rbind, lapply(split(indx, indx), function(i) {
x1 <- data1[i,,drop=FALSE]
indx2 <- colSums(x1!=0)==nrow(x1)
x2 <- x1[,indx2]
if(is.matrix(x2)) {
x2[lower.tri(x2)|upper.tri(x2)] <- 0
}
x1[,indx2] <- x2
x1 }))
row.names(res) <- make.names(row.names(res),unique=TRUE)
RESULT:
res
# 10 33.95 58.66 84.42 110.21 134.16 164.69 199.1 234.35 257.19
#AT1G01050 0 0 0 0 0 0 0 0 1 0
#AT1G01050.1 0 0 0 0 0 0 0 0 0 0
#AT1G01080 0 0 0 0 1 0 0 0 0 0
#AT1G01080.1 0 0 0 0 0 0 1 0 0 0
#AT1G01080.2 0 0 0 0 0 0 0 0 1 0
#AT1G01080.3 0 0 0 0 0 0 0 0 0 0
#AT1G01080.4 0 0 0 0 0 0 0 0 0 0
#AT1G01080.5 0 0 0 0 0 0 0 0 0 0
#AT1G01080.6 0 0 0 0 0 0 0 0 0 0
#AT1G01090 0 0 0 0 0 0 0 0 0 0
#AT1G01090.1 0 0 0 0 0 0 0 0 0 0
#AT1G01090.2 0 0 0 0 0 0 0 0 0 0
#AT1G01320 0 0 0 0 0 0 0 0 0 0
#AT1G01320.1 0 0 0 0 0 0 0 0 0 0
#AT1G01320.2 0 0 0 0 0 0 0 0 0 0
#AT1G01320.3 0 0 0 0 0 0 0 0 0 0
#AT1G01470 0 0 0 1 0 0 0 0 0 0
#AT1G01800 0 0 0 1 0 0 0 0 0 0
#AT1G01800.1 0 0 0 0 0 0 0 0 0 1
# 361.84 432.74 506.34 581.46 651.71 732.59 817.56 896.24
#AT1G01050 0 0 0 0 0 0 0 0
#AT1G01050.1 0 0 0 1 0 0 0 0
#AT1G01080 0 0 0 0 0 0 0 0
#AT1G01080.1 0 0 0 0 0 0 0 0
#AT1G01080.2 0 0 0 0 0 0 0 0
#AT1G01080.3 1 0 0 0 0 0 0 0
#AT1G01080.4 0 0 0 1 0 0 0 0
#AT1G01080.5 0 0 0 0 0 1 0 0
#AT1G01080.6 0 0 0 0 0 0 0 1
#AT1G01090 1 0 0 0 0 0 0 0
#AT1G01090.1 0 0 0 1 0 0 0 0
#AT1G01090.2 0 0 0 0 0 1 0 0
#AT1G01320 0 1 0 0 0 0 0 0
#AT1G01320.1 0 0 0 1 0 0 0 0
#AT1G01320.2 0 0 0 0 0 1 0 0
#AT1G01320.3 0 0 0 0 0 0 0 1
#AT1G01470 0 0 0 0 0 0 0 0
#AT1G01800 0 0 0 0 0 0 0 0
#AT1G01800.1 0 0 0 0 0 0 0 0
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
