From 6e3a2de61519a450822ceee7cbf6944615f557ae Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 15 Nov 2023 15:15:12 -0500
Subject: [PATCH 1/2] fix: sort deeptools plots by file basenames

otherwise, it uses the full filepath which may contain the workdir random hash
---
 modules/local/deeptools.nf           | 5 +++--
 subworkflows/local/deeptools/main.nf | 6 +++---
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/modules/local/deeptools.nf b/modules/local/deeptools.nf
index a2d139f7..aa2758ed 100644
--- a/modules/local/deeptools.nf
+++ b/modules/local/deeptools.nf
@@ -81,9 +81,10 @@ process BIGWIG_SUM {
         path("bigWigSum.npz"), emit: array
 
     script:
+    // sort files on basenames, otherwise uses full file path
     """
     multiBigwigSummary bins \\
-      -b ${bigwigs.join(' ')} \\
+      -b ${bigwigs.sort({ a, b -> a.baseName <=> b.baseName }).join(' ')} \\
       --smartLabels \\
       -o bigWigSum.npz
     """
@@ -257,7 +258,7 @@ process COMPUTE_MATRIX {
   """
   echo "$mattype" > file.txt
   computeMatrix ${cmd} \\
-    -S ${bigwigs.sort().join(' ')} \\
+    -S ${bigwigs.sort({ a, b -> a.baseName <=> b.baseName }).join(' ')} \\
     -R ${bed} \\
     -p ${task.cpus} \\
     -o ${meta.id}.${bed.baseName}.${mattype}.mat.gz \\
diff --git a/subworkflows/local/deeptools/main.nf b/subworkflows/local/deeptools/main.nf
index a3742c28..fdd45b2e 100644
--- a/subworkflows/local/deeptools/main.nf
+++ b/subworkflows/local/deeptools/main.nf
@@ -23,8 +23,8 @@ workflow DEEPTOOLS {
             .set { bigwigs }
 
         bigwigs
-            .map{ meta, bigwig -> bigwig } // sort files on basenames, otherwise uses full file path
-            .toSortedList( { a, b -> a.baseName <=> b.baseName } ) | BIGWIG_SUM
+            .map{ meta, bigwig -> bigwig }
+            .collect() | BIGWIG_SUM
         bw_array = BIGWIG_SUM.out.array
         bw_array.combine(Channel.of('heatmap', 'scatterplot')) | PLOT_CORRELATION
         bw_array | PLOT_PCA
@@ -63,7 +63,7 @@ workflow DEEPTOOLS {
         ch_all_bigwigs = Channel.value([ id: 'inputnorm' ])
             .combine(bigwigs_norm)
             .mix(bigwigs_raw)
-            .groupTuple()
+            .groupTuple() // sort files on basenames, otherwise uses full file path
             .combine(beds)
             .combine(Channel.of('metagene','TSS'))
         COMPUTE_MATRIX(ch_all_bigwigs)

From 4e13d3eb72f341292d2293163ecb0702bc02ba4e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly-sovacool@users.noreply.github.com>
Date: Wed, 15 Nov 2023 15:17:39 -0500
Subject: [PATCH 2/2] chore: add #150 to changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4e0d624b..84da69f5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,7 @@
   - Per sample fingerprint plots instead of per replicate
   - Input normalized profile plots
   - Protein-coding-only versions of plots
+  - Ensure sample IDs are sorted (#150)
 
 ## CHAMPAGNE 0.2.1