Skip to content

Fixed bug in getTissueType; updated unit test #67

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
katehoffshutta merged 1 commit into from
Mar 26, 2025
Merged

Fixed bug in getTissueType; updated unit test #67

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions R/NetworkDataCompanion.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,20 +547,22 @@ NetworkDataCompanion=setRefClass("NetworkDataCompanion",
},

# return tissue type given an input barcode
getTissueType = function(TCGA_barcode)
getTissueType = function(TCGA_barcodes)
{
this_sample = substr(str_split(TCGA_barcode,"-",simplify=T)[1,4],1,2)
if(!this_sample%in% sample_type_mapping$numcode)
these_samples = extractSampleType(TCGA_barcodes)
if(length(setdiff(these_samples,sample_type_mapping$numcode)>0))
{
print(paste("[NetworkDataCompanion::getTissueType()] Error: unknown sample type:",this_sample))
return(NA)
print(paste("[NetworkDataCompanion::getTissueType()] Error: unknown sample type(s):",setdiff(these_samples,sample_type_mapping$numcode)))
return(NULL)
}

this_map = data.frame("TCGA_barcode"=TCGA_barcode)
row.names(this_map) = TCGA_barcode
this_match = sample_type_mapping[which(as.numeric(sample_type_mapping$numcode) == as.numeric(this_sample)),]

return(cbind.data.frame(this_map,this_match))
this_map = data.frame("TCGA_barcode" = TCGA_barcodes,
"numcode" = these_samples,
row.names = TCGA_barcodes)

out_map = this_map %>% left_join(sample_type_mapping, by="numcode") %>%
dplyr::select("TCGA_barcode","description")
return(out_map)
},
## access sample type map
getSampleTypeMap = function(){
Expand Down
132 changes: 81 additions & 51 deletions tests/testthat/test_getTissueType.R
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,59 +1,89 @@
context("[NetworkDataCompanion] Testing getTissueType function ... ")

test_that("Testing getTissueType",{
numcodes <- c(
"01",
"02",
"03",
"04",
"05",
"06",
"07",
"08",
"09",
"10",
"11",
"12",
"13",
"14",
"15",
"16",
"20",
"40",
"50",
"60",
"61",
"99"
)

descriptions <- c(
"Primary Solid Tumor",
"Recurrent Solid Tumor",
"Primary Blood Derived Cancer - Peripheral Blood",
"Recurrent Blood Derived Cancer - Bone Marrow",
"Additional - New Primary",
"Metastatic",
"Additional Metastatic",
"Human Tumor Original Cells",
"Primary Blood Derived Cancer - Bone Marrow",
"Blood Derived Normal",
"Solid Tissue Normal",
"Buccal Cell Normal",
"EBV Immortalized Normal",
"Bone Marrow Normal",
"sample type 15",
"sample type 16",
"Control Analyte",
"Recurrent Blood Derived Cancer - Peripheral Blood",
"Cell Lines",
"Primary Xenograft Tissue",
"Cell Line Derived Xenograft Tissue",
"sample type 99"
)
my_friend = NetworkDataCompanion::CreateNetworkDataCompanionObject()

test_that("Testing getTissueType for a single TCGA barcode",{

my_friend = NetworkDataCompanion::CreateNetworkDataCompanionObject()
numcodes <- c(
"01",
"02",
"03",
"04",
"05",
"06",
"07",
"08",
"09",
"10",
"11",
"12",
"13",
"14",
"15",
"16",
"20",
"40",
"50",
"60",
"61",
"99"
)
descriptions <- c(
"Primary Solid Tumor",
"Recurrent Solid Tumor",
"Primary Blood Derived Cancer - Peripheral Blood",
"Recurrent Blood Derived Cancer - Bone Marrow",
"Additional - New Primary",
"Metastatic",
"Additional Metastatic",
"Human Tumor Original Cells",
"Primary Blood Derived Cancer - Bone Marrow",
"Blood Derived Normal",
"Solid Tissue Normal",
"Buccal Cell Normal",
"EBV Immortalized Normal",
"Bone Marrow Normal",
"sample type 15",
"sample type 16",
"Control Analyte",
"Recurrent Blood Derived Cancer - Peripheral Blood",
"Cell Lines",
"Primary Xenograft Tissue",
"Cell Line Derived Xenograft Tissue",
"sample type 99"
)
barcode = "TCGA-A1-1234-"
for(numcode in numcodes){
expect_equal(as.character(my_friend$getTissueType(paste0(barcode, numcode))['description']), descriptions[numcodes == numcode])
}
expect_true(is.na(as.character(my_friend$getTissueType(paste0(barcode, "53"))['description'])))
expect_true(is.null(my_friend$getTissueType(paste0(barcode, "53"))))
})

test_that("Testing getTissueType vectorizes properly",{

barcode1 = "TCGA-A1-1234-01A"
barcode2 = "TCGA-A1-1234-10A"
barcode3 = "TCGA-A1-1234-10B"
barcode4 = "TCGA-A1-1234-02A"
barcodes = c(barcode1,
barcode2,
barcode3,
barcode4)

expect_equal(my_friend$getTissueType(c(barcode1,
barcode2,
barcode3,
barcode4))$description,
c(descriptions[1],
descriptions[10],
descriptions[10],
descriptions[2]))
})

test_that("Testing getTissueType is not bamboozled by extra suffix items",{

barcode = "TCGA-A1-1234-01A-1989"
expect_equal(my_friend$getTissueType(barcode)$description,descriptions[1])

})