From eb17a1dbae0deb53b75b9904ed76465168b49f5c Mon Sep 17 00:00:00 2001
From: Alexey Sergushichev <alsergbox@gmail.com>
Date: Wed, 28 Aug 2024 13:37:26 -0500
Subject: [PATCH] readGct support for duplicate column names

---
 DESCRIPTION               | 4 ++--
 R/gct.R                   | 8 ++++++++
 tests/testthat/test-gct.R | 6 +++++-
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 1cd2a4e..9ca574a 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: phantasusLite
 Type: Package
 Title: Loading and annotation RNA-seq counts matrices 
-Version: 1.3.2
+Version: 1.3.3
 Authors@R: c(person("Rita", "Sablina", role = "aut"),        
              person("Maxim", "Kleverov", role = "aut"),        
              person("Alexey", "Sergushichev", email = "alsergbox@gmail.com", role = c("aut", "cre")))
@@ -22,7 +22,7 @@ biocViews: GeneExpression, Transcriptomics, RNASeq
 License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Suggests: 
     testthat (>= 3.0.0), 
     knitr, 
diff --git a/R/gct.R b/R/gct.R
index 4fab695..c72a508 100644
--- a/R/gct.R
+++ b/R/gct.R
@@ -55,6 +55,14 @@ readGct <- function(gct) {
     exp <- as.matrix(t[, exp.cols, with=FALSE])
     rownames(exp) <- rn
 
+    cn <- colnames(exp)
+    if (any(duplicated(cn))) {
+        warning(sprintf("duplicated row IDs: %s; they were renamed",
+                        paste0(cn[head(which(duplicated(cn)))], collapse = " ")))
+        cn <- make.unique(cn)
+        colnames(exp) <- cn
+    }
+    
 
 
     fdata <- makeAnnotated(t[, seq_len(ann.row + 1), with=FALSE])
diff --git a/tests/testthat/test-gct.R b/tests/testthat/test-gct.R
index bf43576..66a2d1e 100644
--- a/tests/testthat/test-gct.R
+++ b/tests/testthat/test-gct.R
@@ -20,10 +20,14 @@ test_that("readGct works with gct #1.2", {
     expect_true(ncol(t) == 4)
 })
 
-test_that("readGct works with duplicate row names", {
+test_that("readGct works with duplicate row or column names", {
     gctFile <- system.file("extdata/testdata/gct/test_dup.gct", package="phantasusLite")
     expect_warning(t <- readGct(gctFile), "duplicate")
     expect_true(!is.null(t))
+    
+    gctFile <- system.file("extdata/testdata/gct/test_dupcol.gct", package="phantasusLite")
+    expect_warning(t <- readGct(gctFile), "duplicate")
+    expect_true(!is.null(t))
 })
 
 test_that("writeGct and readGct work", {