Implementation of PreMSIm in R

Question

[a.basitkhan1990]

I am trying to use this R package on my data: https://github.com/WangX-Lab/PreMSIm

I generated a normalized counts file similar to example.txt in their example, except I used gene symbol instead of ID for row name.

When I run their sample code:

> library(PreMSIm)
> path = system.file("extdata", "example.txt", package = "PreMSIm", mustWork = TRUE)
> data_pre(path, type = "ID")
            DDX27  EPM2AIP1    HENMT1      LYG1      MLH1       MSH4    NHLRC1     NOL4L      RNLS    RPL22L1      RTF2   SHROOM4     SMAP1    TTC30A    ZSWIM3
Sample1 1.0000000 1.0000000 1.0000000 1.0000000 1.0000000 1.00000000 1.0000000 0.8761449 0.6029301 0.38125416 0.7734447 0.4684460 1.0000000 1.0000000 0.8196170
Sample2 0.2852962 0.7504918 0.9708924 0.8308378 0.9230994 0.29193800 0.6069412 0.2505053 1.0000000 0.32136905 0.0000000 1.0000000 0.7811169 0.5892737 0.8997000
Sample3 0.2925261 0.1905731 0.7926025 0.0000000 0.4826125 0.00000000 0.0628135 0.0000000 0.6856571 0.77711488 0.3534438 0.6395017 0.2431263 0.5991998 0.0000000
Sample4 0.3222120 0.3382536 0.0000000 0.0862332 0.9683453 0.00000000 0.0000000 0.1510892 0.2734307 0.08064167 0.6204359 0.0000000 0.6643792 0.2502177 0.2724272
Sample5 0.0000000 0.4358840 0.9106778 0.3425521 0.5230118 0.64636639 0.4365995 0.5848757 0.5989048 1.00000000 0.5013767 0.8444353 0.0000000 0.8413705 0.7055393
Sample6 0.9668400 0.0000000 0.7920770 0.3549156 0.0000000 0.16837552 0.1753813 1.0000000 0.0000000 0.00000000 1.0000000 0.2707480 0.6189015 0.0000000 1.0000000
Sample7 0.4824578 0.6602128 0.2860993 0.4002768 0.9693666 0.00000000 0.3152340 0.1379430 0.6548660 0.47439889 0.3435690 0.3907255 0.7911855 0.3374053 0.6464399
Sample8 0.7822241 0.7414237 0.4892138 0.2692035 0.7416527 0.08086024 0.5234921 0.6141626 0.7411251 0.53954477 0.3647259 0.4272453 0.7269801 0.6572230 0.4564439
library(PreMSIm)
path = system.file("extdata", "example.txt", package = "PreMSIm", mustWork = TRUE)
input_data = data_pre(path, type = "ID")
msi_pre(input_data)

I get the correct result:

   Sample MSI_status
1 Sample1          0
2 Sample2          0
3 Sample3          1
4 Sample4          0
5 Sample5          1
6 Sample6          0
7 Sample7          0
8 Sample8          0

When I load my file from CSV or excel into R and then try to run mine I get this error:

> X <- read_excel("~/Desktop/Research/PatelMeningioma/SmokerDEG/countpremsim.xlsx")                                                                                                                                                
> input_data = data_pre(X, type = "symbol")
Error in data_pre(X, type = "symbol") : 
  'input.path' is missing or incorrect

When I check the function it looks like the input needs to be a character:

> data_pre
function (input.path, type = c("Symbol", "ID")) 
{
    if (missing(input.path) || class(input.path) != "character") 
        stop("'input.path' is missing or incorrect")
    type <- match.arg(type)
    a <- read.table(input.path, stringsAsFactors = FALSE, header = TRUE, 
        row.names = 1, sep = "\t", check.names = FALSE)
    if (TRUE %in% is.na(match(feature[, type], rownames(a)))) {
        if (sum(!is.na(match(feature[, type], rownames(a)))) >= 
            5) {
            feature <- feature[!is.na(match(feature[, type], 
                rownames(a))), ]
            rownames(feature) <- NULL
        }
        else {
            stop("Some features of the current test set are missing!")
        }
    }
    a <- a[match(feature[, type], rownames(a)), , drop = FALSE]
    if (FALSE %in% complete.cases(a)) 
        stop("Predictor variables with missing values are presented in the current test set")
    if (dim(a)[2] != 1) {
        a <- apply(t(a), 2, function(x) {
            (x - min(x))/(max(x) - min(x))
        })
        a[is.nan(a)] <- 1
    }
    else {
        a <- t(a)
    }
    if (type == "ID") {
        colnames(a) <- as.character(feature[, "Symbol"])
    }
    return(a)
}
<bytecode: 0x7f82451af3b0>
<environment: namespace:PreMSIm>

So I use this:

> input_data = data_pre(as.character(X), type = "Symbol")

But now I get this error:

Error in file(file, "rt") : invalid 'description' argument

All help is greatly appreciated