From 4f981058f29dd679d36abf7a17a8fb18a3718109 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 21 Nov 2023 16:43:30 -0500
Subject: [PATCH 01/47] feat: add consensus peaks process [wip]

---
 modules/CCBR/custom/consensuspeaks/main.nf    |  37 +++++++
 modules/CCBR/custom/consensuspeaks/meta.yml   |  55 +++++++++
 .../templates/get_consensus_peaks.py          | 104 ++++++++++++++++++
 tests/config/pytest_modules.yml               |   4 +
 .../CCBR/custom/consensuspeaks/main.nf        |  15 +++
 .../custom/consensuspeaks/nextflow.config     |   5 +
 .../CCBR/custom/consensuspeaks/test.yml       |  12 ++
 7 files changed, 232 insertions(+)
 create mode 100644 modules/CCBR/custom/consensuspeaks/main.nf
 create mode 100644 modules/CCBR/custom/consensuspeaks/meta.yml
 create mode 100755 modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
 create mode 100644 tests/modules/CCBR/custom/consensuspeaks/main.nf
 create mode 100644 tests/modules/CCBR/custom/consensuspeaks/nextflow.config
 create mode 100644 tests/modules/CCBR/custom/consensuspeaks/test.yml

diff --git a/modules/CCBR/custom/consensuspeaks/main.nf b/modules/CCBR/custom/consensuspeaks/main.nf
new file mode 100644
index 0000000..345ca67
--- /dev/null
+++ b/modules/CCBR/custom/consensuspeaks/main.nf
@@ -0,0 +1,37 @@
+process CUSTOM_CONSENSUSPEAKS {
+    tag "${meta.id}.${meta.group}"
+    label 'process_single'
+
+    container 'nciccbr/ccbr_ucsc:v1'
+
+    input:
+    tuple val(meta), path(peaks)
+
+    output:
+    // TODO nf-core: Named file extensions MUST be emitted for ALL output channels
+    tuple val(meta), path("*.consensus_peaks.bed"), emit: peaks
+    path "versions.yml"                           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    peakfiles = "${peaks.join(' ')}"
+    outbed = "${meta.id}.${meta.group}.consensus_peaks.bed"
+    filter = 0.5
+    nofilter = false
+    if (peaks.size() > 1) {
+        template 'get_consensus_peaks.py'
+    } else { // just copy the input if there's only one peak file
+        """
+        cp ${peakfiles} ${outbed}
+        """
+    }
+
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bed versions.yml
+    """
+}
diff --git a/modules/CCBR/custom/consensuspeaks/meta.yml b/modules/CCBR/custom/consensuspeaks/meta.yml
new file mode 100644
index 0000000..8477c5a
--- /dev/null
+++ b/modules/CCBR/custom/consensuspeaks/meta.yml
@@ -0,0 +1,55 @@
+---
+name: "custom_consensuspeaks"
+## TODO nf-core: Add a description of the module and list keywords
+description: write your description here
+keywords:
+  - peaks
+  - chipseq
+  - normalization
+  - consensus
+tools:
+  - "custom":
+      ## TODO nf-core: Add a description and other details for the software below
+      description: ""
+      homepage: ""
+      documentation: ""
+      tool_dev_url: ""
+      doi: ""
+      licence: ""
+
+## TODO nf-core: Add a description of all of the variables used as input
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  ## TODO nf-core: Delete / customise this example input
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  ## TODO nf-core: Delete / customise this example output
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
new file mode 100755
index 0000000..c0edf28
--- /dev/null
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+"""
+adapted from https://github.com/CCBR/ASPEN/blob/55f909d76500c3502c1c397ef3000908649b0284/workflow/scripts/ccbr_get_consensus_peaks.py
+"""
+import os
+import uuid
+import pandas
+
+
+def main(peakfiles, outbed, filter, nofilter):
+    deleteFiles = []
+
+    rand_name = str(uuid.uuid4())
+
+    # concat
+    cmd = "cat"
+    for p in peakfiles:
+        cmd += " " + p
+    cmd += " | cut -f1-3 > " + rand_name + ".concat.bed"
+
+    deleteFiles.append(rand_name + ".concat.bed")
+    print(cmd)
+    os.system(cmd)
+
+    # sort and merge
+    cmd = (
+        "bedSort "
+        + rand_name
+        + ".concat.bed "
+        + rand_name
+        + ".concat.bed && bedtools merge -i "
+        + rand_name
+        + ".concat.bed > "
+        + rand_name
+        + ".merged.bed"
+    )
+
+    deleteFiles.append(rand_name + ".merged.bed")
+    print(cmd)
+    os.system(cmd)
+
+    # check merged count
+    npeaks = len(open(rand_name + ".merged.bed").readlines())
+    if npeaks == 0:
+        exit("Number of merged peaks = 0")
+
+    count = 0
+    for p in peakfiles:
+        count += 1
+        sortedfile = p + ".sorted." + rand_name
+        countfile = p + ".counts." + rand_name
+        cmd = (
+            "cut -f1-3 "
+            + p
+            + " > "
+            + sortedfile
+            + " && bedSort "
+            + sortedfile
+            + " "
+            + sortedfile
+        )
+        print(cmd)
+        os.system(cmd)
+        cmd = (
+            "bedmap --delim '\t' --echo-ref-name --count "
+            + rand_name
+            + ".merged.bed "
+            + sortedfile
+            + "|awk -F'\t' -v OFS='\t' '{if ($2>1){$2=1}{print}}' > "
+            + countfile
+        )
+        print(cmd)
+        os.system(cmd)
+        deleteFiles.append(countfile)
+        deleteFiles.append(sortedfile)
+        if count == 1:
+            df = pandas.read_csv(countfile, delimiter="\t")
+            df.columns = ["peakid", countfile]
+        else:
+            dfx = pandas.read_csv(countfile, delimiter="\t")
+            dfx.columns = ["peakid", countfile]
+            df = df.merge(dfx, on="peakid")
+
+    df = df.set_index("peakid")
+    df = df.sum(axis=1) / len(df.columns)
+    df = pandas.DataFrame({"peakid": df.index, "score": df.values})
+
+    with open(outbed, "w") as out:
+        for index, row in df.iterrows():
+            chrom, coords = row["peakid"].split(":")
+            start, end = coords.split("-")
+            if nofilter or float(row["score"]) > filter:
+                out.write(
+                    "%s\t%s\t%s\t%s\t%.3f\t.\tNA\tNA\tNA\n"
+                    % (chrom, start, end, row["peakid"], float(row["score"]))
+                )
+
+    for f in deleteFiles:
+        os.remove(f)
+
+
+if __name__ == "__main__":
+    # arguments filled in via nextflow template
+    main("${peakfiles}".split(), "${outbed}", float("${filter}"), bool("${nofilter}"))
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 773b44c..682aafe 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -10,6 +10,10 @@ custom/bam2fastq:
   - modules/CCBR/custom/bam2fastq/**
   - tests/modules/CCBR/custom/bam2fastq/**
 
+custom/consensuspeaks:
+  - modules/CCBR/custom/consensuspeaks/**
+  - tests/modules/CCBR/custom/consensuspeaks/**
+
 custom/countfastq:
   - modules/CCBR/custom/countfastq/**
   - tests/modules/CCBR/custom/countfastq/**
diff --git a/tests/modules/CCBR/custom/consensuspeaks/main.nf b/tests/modules/CCBR/custom/consensuspeaks/main.nf
new file mode 100644
index 0000000..f7bbbf9
--- /dev/null
+++ b/tests/modules/CCBR/custom/consensuspeaks/main.nf
@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CUSTOM_CONSENSUSPEAKS } from '../../../../../modules/CCBR/custom/consensuspeaks/main.nf'
+
+workflow test_custom_consensuspeaks {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+    ]
+
+    CUSTOM_CONSENSUSPEAKS ( input )
+}
diff --git a/tests/modules/CCBR/custom/consensuspeaks/nextflow.config b/tests/modules/CCBR/custom/consensuspeaks/nextflow.config
new file mode 100644
index 0000000..8730f1c
--- /dev/null
+++ b/tests/modules/CCBR/custom/consensuspeaks/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
diff --git a/tests/modules/CCBR/custom/consensuspeaks/test.yml b/tests/modules/CCBR/custom/consensuspeaks/test.yml
new file mode 100644
index 0000000..72f775d
--- /dev/null
+++ b/tests/modules/CCBR/custom/consensuspeaks/test.yml
@@ -0,0 +1,12 @@
+## TODO nf-core: Please run the following command to build this file:
+#                nf-core modules create-test-yml /consensuspeaks
+- name: "custom consensuspeaks"
+  command: nextflow run ./tests/modules/CCBR/custom/consensuspeaks -entry test_custom_consensuspeaks -c ./tests/config/nextflow.config
+  tags:
+    - "custom"
+    - "custom/consensuspeaks"
+  files:
+    - path: "output/custom/test.bam"
+      md5sum: e667c7caad0bc4b7ac383fd023c654fc
+    - path: "output/custom/versions.yml"
+      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b

From f0360dd446053cd05cb9ca9cf56e8db1f9f6ca7e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 09:47:16 -0500
Subject: [PATCH 02/47] fix: escape backslashes for nextflow template script

---
 .../consensuspeaks/templates/get_consensus_peaks.py    | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
index c0edf28..4a6dc18 100755
--- a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -62,11 +62,11 @@ def main(peakfiles, outbed, filter, nofilter):
         print(cmd)
         os.system(cmd)
         cmd = (
-            "bedmap --delim '\t' --echo-ref-name --count "
+            "bedmap --delim '\\t' --echo-ref-name --count "
             + rand_name
             + ".merged.bed "
             + sortedfile
-            + "|awk -F'\t' -v OFS='\t' '{if ($2>1){$2=1}{print}}' > "
+            + "|awk -F'\\t' -v OFS='\\t' '{if ($2>1){$2=1}{print}}' > "
             + countfile
         )
         print(cmd)
@@ -74,10 +74,10 @@ def main(peakfiles, outbed, filter, nofilter):
         deleteFiles.append(countfile)
         deleteFiles.append(sortedfile)
         if count == 1:
-            df = pandas.read_csv(countfile, delimiter="\t")
+            df = pandas.read_csv(countfile, delimiter="\\t")
             df.columns = ["peakid", countfile]
         else:
-            dfx = pandas.read_csv(countfile, delimiter="\t")
+            dfx = pandas.read_csv(countfile, delimiter="\\t")
             dfx.columns = ["peakid", countfile]
             df = df.merge(dfx, on="peakid")
 
@@ -91,7 +91,7 @@ def main(peakfiles, outbed, filter, nofilter):
             start, end = coords.split("-")
             if nofilter or float(row["score"]) > filter:
                 out.write(
-                    "%s\t%s\t%s\t%s\t%.3f\t.\tNA\tNA\tNA\n"
+                    "%s\\t%s\\t%s\\t%s\\t%.3f\\t.\\tNA\\tNA\\tNA\\n"
                     % (chrom, start, end, row["peakid"], float(row["score"]))
                 )
 

From 18ff6af698973fd6013796e5d25edb6c2a075524 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 10:36:37 -0500
Subject: [PATCH 03/47] fix: escape dollar signs for nf template

---
 .../CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
index 4a6dc18..8ca5034 100755
--- a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -66,7 +66,7 @@ def main(peakfiles, outbed, filter, nofilter):
             + rand_name
             + ".merged.bed "
             + sortedfile
-            + "|awk -F'\\t' -v OFS='\\t' '{if ($2>1){$2=1}{print}}' > "
+            + "|awk -F'\\t' -v OFS='\\t' '{if (\$2>1){\$2=1}{print}}' > "
             + countfile
         )
         print(cmd)

From 5e6f65dd40e2b1e08eca366eec2988efa1795ed0 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 10:37:20 -0500
Subject: [PATCH 04/47] test: use macs2 peaks as test data

---
 tests/modules/CCBR/custom/consensuspeaks/main.nf         | 6 ++++--
 tests/modules/CCBR/custom/consensuspeaks/nextflow.config | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/tests/modules/CCBR/custom/consensuspeaks/main.nf b/tests/modules/CCBR/custom/consensuspeaks/main.nf
index f7bbbf9..0b33660 100644
--- a/tests/modules/CCBR/custom/consensuspeaks/main.nf
+++ b/tests/modules/CCBR/custom/consensuspeaks/main.nf
@@ -7,8 +7,10 @@ include { CUSTOM_CONSENSUSPEAKS } from '../../../../../modules/CCBR/custom/conse
 workflow test_custom_consensuspeaks {
 
     input = [
-        [ id:'test', single_end:false ], // meta map
-        file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true)
+        [ id: 'test', group: 'macs_broad' ], // meta map
+        [ file(params.test_data['macs_peaks_1'], checkIfExists: true),
+          file(params.test_data['macs_peaks_2'], checkIfExists: true),
+        ]
     ]
 
     CUSTOM_CONSENSUSPEAKS ( input )
diff --git a/tests/modules/CCBR/custom/consensuspeaks/nextflow.config b/tests/modules/CCBR/custom/consensuspeaks/nextflow.config
index 8730f1c..a652b2d 100644
--- a/tests/modules/CCBR/custom/consensuspeaks/nextflow.config
+++ b/tests/modules/CCBR/custom/consensuspeaks/nextflow.config
@@ -3,3 +3,5 @@ process {
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
 }
+
+includeConfig '../../../../config/test_data_CCBR.config'

From d7b2f07577cdbe200cdc0f3dc01a715432974e0b Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 10:53:23 -0500
Subject: [PATCH 05/47] fix: metadata for consensuspeaks

---
 modules/CCBR/custom/consensuspeaks/main.nf  |  2 +-
 modules/CCBR/custom/consensuspeaks/meta.yml | 55 ++++++++++++---------
 2 files changed, 32 insertions(+), 25 deletions(-)

diff --git a/modules/CCBR/custom/consensuspeaks/main.nf b/modules/CCBR/custom/consensuspeaks/main.nf
index 345ca67..3a08bad 100644
--- a/modules/CCBR/custom/consensuspeaks/main.nf
+++ b/modules/CCBR/custom/consensuspeaks/main.nf
@@ -8,7 +8,6 @@ process CUSTOM_CONSENSUSPEAKS {
     tuple val(meta), path(peaks)
 
     output:
-    // TODO nf-core: Named file extensions MUST be emitted for ALL output channels
     tuple val(meta), path("*.consensus_peaks.bed"), emit: peaks
     path "versions.yml"                           , emit: versions
 
@@ -25,6 +24,7 @@ process CUSTOM_CONSENSUSPEAKS {
     } else { // just copy the input if there's only one peak file
         """
         cp ${peakfiles} ${outbed}
+        touch versions.yml
         """
     }
 
diff --git a/modules/CCBR/custom/consensuspeaks/meta.yml b/modules/CCBR/custom/consensuspeaks/meta.yml
index 8477c5a..4c86fa5 100644
--- a/modules/CCBR/custom/consensuspeaks/meta.yml
+++ b/modules/CCBR/custom/consensuspeaks/meta.yml
@@ -1,55 +1,62 @@
 ---
 name: "custom_consensuspeaks"
-## TODO nf-core: Add a description of the module and list keywords
-description: write your description here
+description: Find consensus peaks from two or more peak files.
 keywords:
   - peaks
   - chipseq
   - normalization
   - consensus
 tools:
-  - "custom":
-      ## TODO nf-core: Add a description and other details for the software below
-      description: ""
-      homepage: ""
-      documentation: ""
-      tool_dev_url: ""
-      doi: ""
-      licence: ""
+  - Python:
+      description: |
+        The Python Programming Language
+      homepage: https://www.python.org/
+      licence: ["Python License 2.0"]
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/
+      licence: ["MIT"]
+  - bedops:
+      description: |
+        fast, highly scalable and easily-parallelizable genome analysis toolkit
+      documentation: https://bedops.readthedocs.io/
+      tool_dev_url: https://github.com/bedops/bedops
+      licence: ["GPLv2"]
+      doi: 10.1093/bioinformatics/bts277
+  - bedSort:
+    description: |
+      UCSC Genome Browser tool for sorting .bed files by chrom,chromStart.
+    documentation: https://www.encodeproject.org/software/bedsort/
 
-## TODO nf-core: Add a description of all of the variables used as input
 input:
-  # Only when we have meta
   - meta:
       type: map
       description: |
         Groovy Map containing sample information
         e.g. `[ id:'test', single_end:false ]`
 
-  ## TODO nf-core: Delete / customise this example input
-  - bam:
+  - peaks:
       type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+      description: Peak files
+      pattern: "*.{broadPeak,narrowPeak,bed}"
 
-## TODO nf-core: Add a description of all of the variables used as output
 output:
-  #Only when we have meta
   - meta:
       type: map
       description: |
         Groovy Map containing sample information
         e.g. `[ id:'test', single_end:false ]`
-
+  - peaks:
+      type: file
+      description: A single consensus peak file
+      pattern: "*.{broadPeak,narrowPeak,bed}"
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  ## TODO nf-core: Delete / customise this example output
-  - bam:
-      type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
 
 authors:
   - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"

From 1a5554b1b8e8638f0b9ab181285bd269cd5d85b9 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 11:28:19 -0500
Subject: [PATCH 06/47] test: add real md5sums for custom/consensuspeaks

---
 tests/modules/CCBR/custom/consensuspeaks/test.yml | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tests/modules/CCBR/custom/consensuspeaks/test.yml b/tests/modules/CCBR/custom/consensuspeaks/test.yml
index 72f775d..4161ee4 100644
--- a/tests/modules/CCBR/custom/consensuspeaks/test.yml
+++ b/tests/modules/CCBR/custom/consensuspeaks/test.yml
@@ -6,7 +6,6 @@
     - "custom"
     - "custom/consensuspeaks"
   files:
-    - path: "output/custom/test.bam"
-      md5sum: e667c7caad0bc4b7ac383fd023c654fc
+    - path: "output/custom/test.macs_broad.consensus_peaks.bed"
+      md5sum: 4d684a948335bbed948704e4be9f1abe
     - path: "output/custom/versions.yml"
-      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b

From 3aca9c5126cf0113ba4cbe1d6927d1d845fda40f Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 11:39:44 -0500
Subject: [PATCH 07/47] fix: meta syntax

---
 modules/CCBR/custom/consensuspeaks/meta.yml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/modules/CCBR/custom/consensuspeaks/meta.yml b/modules/CCBR/custom/consensuspeaks/meta.yml
index 4c86fa5..52fa43e 100644
--- a/modules/CCBR/custom/consensuspeaks/meta.yml
+++ b/modules/CCBR/custom/consensuspeaks/meta.yml
@@ -25,9 +25,9 @@ tools:
       licence: ["GPLv2"]
       doi: 10.1093/bioinformatics/bts277
   - bedSort:
-    description: |
-      UCSC Genome Browser tool for sorting .bed files by chrom,chromStart.
-    documentation: https://www.encodeproject.org/software/bedsort/
+      description: |
+        UCSC Genome Browser tool for sorting .bed files by chrom,chromStart.
+      documentation: https://www.encodeproject.org/software/bedsort/
 
 input:
   - meta:

From c538767391c3cea4bb3f4c4a0bbe746f3af0fc29 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 11:41:31 -0500
Subject: [PATCH 08/47] fix: write versions

---
 .../custom/consensuspeaks/templates/get_consensus_peaks.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
index 8ca5034..1a0ee4b 100755
--- a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -99,6 +99,13 @@ def main(peakfiles, outbed, filter, nofilter):
         os.remove(f)
 
 
+def write_versions():
+    with open("versions.yml", "w") as outfile:
+        outfile.write('"${task.process}":\\n')
+        outfile.write(f'  Python: "{platform.python_version()}"\\n')
+
+
 if __name__ == "__main__":
+    write_versions()
     # arguments filled in via nextflow template
     main("${peakfiles}".split(), "${outbed}", float("${filter}"), bool("${nofilter}"))

From 861460f9ccbc0f6a262018545327c6a5fd74e664 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 11:54:03 -0500
Subject: [PATCH 09/47] feat: adapt bedtools modules from nf-core

---
 modules/CCBR/bedtools/map/main.nf             | 58 +++++++++++++++++++
 modules/CCBR/bedtools/map/meta.yml            | 53 +++++++++++++++++
 modules/CCBR/bedtools/merge/main.nf           | 47 +++++++++++++++
 modules/CCBR/bedtools/merge/meta.yml          | 41 +++++++++++++
 modules/CCBR/bedtools/sort/main.nf            | 54 +++++++++++++++++
 modules/CCBR/bedtools/sort/meta.yml           | 50 ++++++++++++++++
 tests/config/pytest_modules.yml               | 12 ++++
 tests/modules/CCBR/bedtools/map/main.nf       | 27 +++++++++
 .../modules/CCBR/bedtools/map/nextflow.config | 13 +++++
 tests/modules/CCBR/bedtools/map/test.yml      | 21 +++++++
 tests/modules/CCBR/bedtools/merge/main.nf     | 13 +++++
 .../CCBR/bedtools/merge/nextflow.config       |  9 +++
 tests/modules/CCBR/bedtools/merge/test.yml    |  8 +++
 tests/modules/CCBR/bedtools/sort/main.nf      | 22 +++++++
 .../CCBR/bedtools/sort/nextflow.config        | 10 ++++
 tests/modules/CCBR/bedtools/sort/test.yml     | 19 ++++++
 16 files changed, 457 insertions(+)
 create mode 100644 modules/CCBR/bedtools/map/main.nf
 create mode 100644 modules/CCBR/bedtools/map/meta.yml
 create mode 100644 modules/CCBR/bedtools/merge/main.nf
 create mode 100644 modules/CCBR/bedtools/merge/meta.yml
 create mode 100644 modules/CCBR/bedtools/sort/main.nf
 create mode 100644 modules/CCBR/bedtools/sort/meta.yml
 create mode 100644 tests/modules/CCBR/bedtools/map/main.nf
 create mode 100644 tests/modules/CCBR/bedtools/map/nextflow.config
 create mode 100644 tests/modules/CCBR/bedtools/map/test.yml
 create mode 100644 tests/modules/CCBR/bedtools/merge/main.nf
 create mode 100644 tests/modules/CCBR/bedtools/merge/nextflow.config
 create mode 100644 tests/modules/CCBR/bedtools/merge/test.yml
 create mode 100644 tests/modules/CCBR/bedtools/sort/main.nf
 create mode 100644 tests/modules/CCBR/bedtools/sort/nextflow.config
 create mode 100644 tests/modules/CCBR/bedtools/sort/test.yml

diff --git a/modules/CCBR/bedtools/map/main.nf b/modules/CCBR/bedtools/map/main.nf
new file mode 100644
index 0000000..846d5ba
--- /dev/null
+++ b/modules/CCBR/bedtools/map/main.nf
@@ -0,0 +1,58 @@
+process BEDTOOLS_MAP {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::bedtools=2.31.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
+        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+
+    input:
+    tuple val(meta), path(intervals1), path(intervals2)
+    tuple val(meta2), path(chrom_sizes)
+
+    output:
+    tuple val(meta), path("*.${extension}"), emit: map
+    path  "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    extension = intervals1.getExtension()
+    def sizes = chrom_sizes ? "-g ${chrom_sizes}" : ''
+    if ("$intervals1" == "${prefix}.${extension}" ||
+        "$intervals2" == "${prefix}.${extension}")
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    bedtools \\
+        map \\
+        -a $intervals1 \\
+        -b $intervals2 \\
+        $args \\
+        $sizes \\
+        > ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    extension = intervals1.getExtension()
+    if ("$intervals1" == "${prefix}.${extension}" ||
+        "$intervals2" == "${prefix}.${extension}")
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    touch ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/bedtools/map/meta.yml b/modules/CCBR/bedtools/map/meta.yml
new file mode 100644
index 0000000..51f4fdc
--- /dev/null
+++ b/modules/CCBR/bedtools/map/meta.yml
@@ -0,0 +1,53 @@
+name: bedtools_map
+description: Allows one to screen for overlaps between two sets of genomic features. Adapted from https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools
+keywords:
+  - bed
+  - vcf
+  - gff
+  - map
+  - bedtools
+tools:
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/en/latest/content/tools/map.html
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - intervals1:
+      type: file
+      description: BAM/BED/GFF/VCF
+      pattern: "*.{bed|gff|vcf}"
+  - intervals2:
+      type: file
+      description: BAM/BED/GFF/VCF
+      pattern: "*.{bed|gff|vcf}"
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing reference chromosome sizes
+        e.g. [ id:'test' ]
+  - chrom_sizes:
+      type: file
+      description: Chromosome sizes file
+      pattern: "*{.sizes,.txt}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - map:
+      type: file
+      description: File containing the description of overlaps found between the features in A and the features in B, with statistics
+      pattern: "*.${extension}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@ekushele"
diff --git a/modules/CCBR/bedtools/merge/main.nf b/modules/CCBR/bedtools/merge/main.nf
new file mode 100644
index 0000000..6868d39
--- /dev/null
+++ b/modules/CCBR/bedtools/merge/main.nf
@@ -0,0 +1,47 @@
+process BEDTOOLS_MERGE {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::bedtools=2.31.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
+        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+
+    input:
+    tuple val(meta), path(bed)
+
+    output:
+    tuple val(meta), path('*.bed'), emit: bed
+    path  "versions.yml"          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if ("$bed" == "${prefix}.bed") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    bedtools \\
+        merge \\
+        -i $bed \\
+        $args \\
+        > ${prefix}.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/bedtools/merge/meta.yml b/modules/CCBR/bedtools/merge/meta.yml
new file mode 100644
index 0000000..ee8e165
--- /dev/null
+++ b/modules/CCBR/bedtools/merge/meta.yml
@@ -0,0 +1,41 @@
+name: bedtools_merge
+description: combines overlapping or “book-ended” features in an interval file into a single feature which spans all of the combined features. Adapted from https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools
+keywords:
+  - bed
+  - merge
+  - bedtools
+  - overlapped bed
+tools:
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/en/latest/content/tools/merge.html
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: Input BED file
+      pattern: "*.{bed}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bed:
+      type: file
+      description: Overlapped bed file with combined features
+      pattern: "*.{bed}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@Emiller88"
+  - "@sruthipsuresh"
+  - "@drpatelh"
diff --git a/modules/CCBR/bedtools/sort/main.nf b/modules/CCBR/bedtools/sort/main.nf
new file mode 100644
index 0000000..df372bc
--- /dev/null
+++ b/modules/CCBR/bedtools/sort/main.nf
@@ -0,0 +1,54 @@
+process BEDTOOLS_SORT {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::bedtools=2.31.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
+        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+
+    input:
+    tuple val(meta), path(intervals)
+    path genome_file
+
+    output:
+    tuple val(meta), path("*.${extension}"), emit: sorted
+    path  "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args       = task.ext.args   ?: ''
+    def prefix     = task.ext.prefix ?: "${meta.id}"
+    def genome_cmd = genome_file     ?  "-g $genome_file" : ""
+    extension      = task.ext.suffix ?: intervals.extension
+    if ("$intervals" == "${prefix}.${extension}") {
+        error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    }
+    """
+    bedtools \\
+        sort \\
+        -i $intervals \\
+        $genome_cmd \\
+        $args \\
+        > ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    extension      = task.ext.suffix ?: intervals.extension
+    """
+    touch ${prefix}.${extension}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/bedtools/sort/meta.yml b/modules/CCBR/bedtools/sort/meta.yml
new file mode 100644
index 0000000..80c16f3
--- /dev/null
+++ b/modules/CCBR/bedtools/sort/meta.yml
@@ -0,0 +1,50 @@
+name: bedtools_sort
+description: Sorts a feature file by chromosome and other criteria. Adapted from https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools
+keywords:
+  - bed
+  - sort
+  - bedtools
+  - chromosome
+tools:
+  - bedtools:
+      description: |
+        A set of tools for genomic analysis tasks, specifically enabling genome arithmetic (merge, count, complement) on various file types.
+      documentation: https://bedtools.readthedocs.io/en/latest/content/tools/sort.html
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - intervals:
+      type: file
+      description: BED/BEDGRAPH
+      pattern: "*.{bed|bedGraph}"
+  - genome_file:
+      type: file
+      description: |
+        Optional reference genome 2 column file that defines the expected chromosome order.
+      pattern: "*.{fai,txt,chromsizes}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - sorted:
+      type: file
+      description: Sorted output file
+      pattern: "*.${extension}"
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@Emiller88"
+  - "@sruthipsuresh"
+  - "@drpatelh"
+  - "@chris-cheshire"
+  - "@adamrtalbot"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index b866f18..05d3f2f 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -1,3 +1,15 @@
+bedtools/map:
+  - modules/CCBR/bedtools/map/**
+  - tests/modules/CCBR/bedtools/map/**
+
+bedtools/merge:
+  - modules/CCBR/bedtools/merge/**
+  - tests/modules/CCBR/bedtools/merge/**
+
+bedtools/sort:
+  - modules/CCBR/bedtools/sort/**
+  - tests/modules/CCBR/bedtools/sort/**
+
 bwa/index:
   - modules/CCBR/bwa/index/**
   - tests/modules/CCBR/bwa/index/**
diff --git a/tests/modules/CCBR/bedtools/map/main.nf b/tests/modules/CCBR/bedtools/map/main.nf
new file mode 100644
index 0000000..0d42cac
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/map/main.nf
@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_MAP                           } from '../../../../../modules/nf-core/bedtools/map/main.nf'
+include { BEDTOOLS_MAP as BEDTOOLS_MAP_VCF } from '../../../../../modules/nf-core/bedtools/map/main.nf'
+
+workflow test_bedtools_map {
+    input = [
+        [ id:'test' ],
+        file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true),
+        file(params.test_data['sarscov2']['genome']['test2_bed'], checkIfExists: true)
+    ]
+
+
+    BEDTOOLS_MAP ( input, [[:],[]] )
+}
+
+workflow test_bedtools_map_vcf {
+    input = [
+        [ id:'test' ],
+        file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+    ]
+
+    BEDTOOLS_MAP_VCF ( input, [[:],[]] )
+}
diff --git a/tests/modules/CCBR/bedtools/map/nextflow.config b/tests/modules/CCBR/bedtools/map/nextflow.config
new file mode 100644
index 0000000..730638c
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/map/nextflow.config
@@ -0,0 +1,13 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BEDTOOLS_MAP {
+        ext.prefix = { "${meta.id}_out" }
+    }
+
+     withName: BEDTOOLS_MAP_VCF {
+		ext.prefix = { "${meta.id}_out" }
+    }
+
+}
diff --git a/tests/modules/CCBR/bedtools/map/test.yml b/tests/modules/CCBR/bedtools/map/test.yml
new file mode 100644
index 0000000..e06ddc3
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/map/test.yml
@@ -0,0 +1,21 @@
+- name: bedtools map test_bedtools_map
+  command: nextflow run ./tests/modules/nf-core/bedtools/map -entry test_bedtools_map -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/map/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/map
+  files:
+    - path: output/bedtools/test_out.bed
+      md5sum: d3aeb1ec7b90e0d5a6d1b9a4614ab96a
+    - path: output/bedtools/versions.yml
+      md5sum: 6c219404bf848cd4bd672a934dd4ed56
+
+- name: bedtools map test_bedtools_map_vcf
+  command: nextflow run ./tests/modules/nf-core/bedtools/map -entry test_bedtools_map_vcf -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/map/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/map
+  files:
+    - path: output/bedtools/test_out.bed
+      md5sum: cabd34d1132834581e31f53dfa66ec03
+    - path: output/bedtools/versions.yml
+      md5sum: ab927c219959af17dc370b0b8eda78bd
diff --git a/tests/modules/CCBR/bedtools/merge/main.nf b/tests/modules/CCBR/bedtools/merge/main.nf
new file mode 100644
index 0000000..4941193
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/merge/main.nf
@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_MERGE } from '../../../../../modules/nf-core/bedtools/merge/main.nf'
+
+workflow test_bedtools_merge {
+    input = [ [ id:'test'],
+              file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+            ]
+
+    BEDTOOLS_MERGE ( input )
+}
diff --git a/tests/modules/CCBR/bedtools/merge/nextflow.config b/tests/modules/CCBR/bedtools/merge/nextflow.config
new file mode 100644
index 0000000..545a523
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/merge/nextflow.config
@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BEDTOOLS_MERGE {
+        ext.prefix = { "${meta.id}_out" }
+    }
+
+}
diff --git a/tests/modules/CCBR/bedtools/merge/test.yml b/tests/modules/CCBR/bedtools/merge/test.yml
new file mode 100644
index 0000000..bee9b75
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/merge/test.yml
@@ -0,0 +1,8 @@
+- name: bedtools merge
+  command: nextflow run ./tests/modules/nf-core/bedtools/merge -entry test_bedtools_merge -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/merge/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/merge
+  files:
+    - path: ./output/bedtools/test_out.bed
+      md5sum: 0cf6ed2b6f470cd44a247da74ca4fe4e
diff --git a/tests/modules/CCBR/bedtools/sort/main.nf b/tests/modules/CCBR/bedtools/sort/main.nf
new file mode 100644
index 0000000..0cf0daf
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/sort/main.nf
@@ -0,0 +1,22 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_SORT } from '../../../../../modules/nf-core/bedtools/sort/main.nf'
+
+workflow test_bedtools_sort {
+    input = [ [ id:'test'],
+              file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+            ]
+
+    BEDTOOLS_SORT ( input, [] )
+}
+
+workflow test_bedtools_sort_with_genome {
+    input = [ [ id:'test'],
+              file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true)
+            ]
+    fai = Channel.of(file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true))
+
+    BEDTOOLS_SORT ( input, [] )
+}
diff --git a/tests/modules/CCBR/bedtools/sort/nextflow.config b/tests/modules/CCBR/bedtools/sort/nextflow.config
new file mode 100644
index 0000000..27b09ba
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/sort/nextflow.config
@@ -0,0 +1,10 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: BEDTOOLS_SORT {
+        ext.prefix = { "${meta.id}_out" }
+        ext.suffix = "testtext"
+    }
+
+}
diff --git a/tests/modules/CCBR/bedtools/sort/test.yml b/tests/modules/CCBR/bedtools/sort/test.yml
new file mode 100644
index 0000000..8a96bbb
--- /dev/null
+++ b/tests/modules/CCBR/bedtools/sort/test.yml
@@ -0,0 +1,19 @@
+- name: bedtools sort test_bedtools_sort
+  command: nextflow run ./tests/modules/nf-core/bedtools/sort -entry test_bedtools_sort -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/sort/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/sort
+  files:
+    - path: output/bedtools/test_out.testtext
+      md5sum: fe4053cf4de3aebbdfc3be2efb125a74
+    - path: output/bedtools/versions.yml
+
+- name: bedtools sort test_bedtools_sort_with_genome
+  command: nextflow run ./tests/modules/nf-core/bedtools/sort -entry test_bedtools_sort_with_genome -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/sort/nextflow.config
+  tags:
+    - bedtools
+    - bedtools/sort
+  files:
+    - path: output/bedtools/test_out.testtext
+      md5sum: fe4053cf4de3aebbdfc3be2efb125a74
+    - path: output/bedtools/versions.yml

From 4f0e5a2794701cee145e5823cbd50608fcb1e46f Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 11:58:13 -0500
Subject: [PATCH 10/47] refactor: minor cosmetic changes

---
 modules/CCBR/bedtools/map/main.nf    | 18 ++++++++----------
 modules/CCBR/bedtools/map/meta.yml   |  4 +++-
 modules/CCBR/bedtools/merge/main.nf  | 10 ++++------
 modules/CCBR/bedtools/merge/meta.yml |  6 +++---
 modules/CCBR/bedtools/sort/main.nf   | 12 +++++-------
 modules/CCBR/bedtools/sort/meta.yml  |  8 +++-----
 6 files changed, 26 insertions(+), 32 deletions(-)

diff --git a/modules/CCBR/bedtools/map/main.nf b/modules/CCBR/bedtools/map/main.nf
index 846d5ba..5f09d6a 100644
--- a/modules/CCBR/bedtools/map/main.nf
+++ b/modules/CCBR/bedtools/map/main.nf
@@ -1,11 +1,9 @@
 process BEDTOOLS_MAP {
-    tag "$meta.id"
+    tag { meta.id }
     label 'process_single'
 
     conda "bioconda::bedtools=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
-        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
 
     input:
     tuple val(meta), path(intervals1), path(intervals2)
@@ -29,10 +27,10 @@ process BEDTOOLS_MAP {
     """
     bedtools \\
         map \\
-        -a $intervals1 \\
-        -b $intervals2 \\
-        $args \\
-        $sizes \\
+        -a ${intervals1} \\
+        -b ${intervals2} \\
+        ${args} \\
+        ${sizes} \\
         > ${prefix}.${extension}
 
     cat <<-END_VERSIONS > versions.yml
@@ -44,8 +42,8 @@ process BEDTOOLS_MAP {
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
     extension = intervals1.getExtension()
-    if ("$intervals1" == "${prefix}.${extension}" ||
-        "$intervals2" == "${prefix}.${extension}")
+    if ("${intervals1}" == "${prefix}.${extension}" ||
+        "${intervals2}" == "${prefix}.${extension}")
         error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
     """
     touch ${prefix}.${extension}
diff --git a/modules/CCBR/bedtools/map/meta.yml b/modules/CCBR/bedtools/map/meta.yml
index 51f4fdc..0eb2581 100644
--- a/modules/CCBR/bedtools/map/meta.yml
+++ b/modules/CCBR/bedtools/map/meta.yml
@@ -50,4 +50,6 @@ output:
       description: File containing software versions
       pattern: "versions.yml"
 authors:
-  - "@ekushele"
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/bedtools/merge/main.nf b/modules/CCBR/bedtools/merge/main.nf
index 6868d39..5ef567c 100644
--- a/modules/CCBR/bedtools/merge/main.nf
+++ b/modules/CCBR/bedtools/merge/main.nf
@@ -1,11 +1,9 @@
 process BEDTOOLS_MERGE {
-    tag "$meta.id"
+    tag { meta.id }
     label 'process_single'
 
     conda "bioconda::bedtools=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
-        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
 
     input:
     tuple val(meta), path(bed)
@@ -24,8 +22,8 @@ process BEDTOOLS_MERGE {
     """
     bedtools \\
         merge \\
-        -i $bed \\
-        $args \\
+        -i ${bed} \\
+        ${args} \\
         > ${prefix}.bed
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/CCBR/bedtools/merge/meta.yml b/modules/CCBR/bedtools/merge/meta.yml
index ee8e165..cec9bf6 100644
--- a/modules/CCBR/bedtools/merge/meta.yml
+++ b/modules/CCBR/bedtools/merge/meta.yml
@@ -36,6 +36,6 @@ output:
       description: File containing software versions
       pattern: "versions.yml"
 authors:
-  - "@Emiller88"
-  - "@sruthipsuresh"
-  - "@drpatelh"
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/bedtools/sort/main.nf b/modules/CCBR/bedtools/sort/main.nf
index df372bc..677e328 100644
--- a/modules/CCBR/bedtools/sort/main.nf
+++ b/modules/CCBR/bedtools/sort/main.nf
@@ -1,11 +1,9 @@
 process BEDTOOLS_SORT {
-    tag "$meta.id"
+    tag { meta.id }
     label 'process_single'
 
     conda "bioconda::bedtools=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bedtools:2.31.0--hf5e1c6e_2' :
-        'biocontainers/bedtools:2.31.0--hf5e1c6e_2' }"
+    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
 
     input:
     tuple val(meta), path(intervals)
@@ -29,9 +27,9 @@ process BEDTOOLS_SORT {
     """
     bedtools \\
         sort \\
-        -i $intervals \\
-        $genome_cmd \\
-        $args \\
+        -i ${intervals} \\
+        ${genome_cmd} \\
+        ${args} \\
         > ${prefix}.${extension}
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/CCBR/bedtools/sort/meta.yml b/modules/CCBR/bedtools/sort/meta.yml
index 80c16f3..d19a88b 100644
--- a/modules/CCBR/bedtools/sort/meta.yml
+++ b/modules/CCBR/bedtools/sort/meta.yml
@@ -43,8 +43,6 @@ output:
       description: File containing software versions
       pattern: "versions.yml"
 authors:
-  - "@Emiller88"
-  - "@sruthipsuresh"
-  - "@drpatelh"
-  - "@chris-cheshire"
-  - "@adamrtalbot"
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"

From 01855f7f07cfc9d03c5ed3e8bef69922f064b4a5 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 22 Nov 2023 17:04:44 -0500
Subject: [PATCH 11/47] chore: update changelog

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

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6b9831e..710c83b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,7 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 - bwa/mem
   - also runs samtools sort & outputs index in bai format. (#12)
 - custom/bam2fastq (#14,#22)
+- custom/consensuspeaks (#37)
 - custom/convertsicer (#36)
 - custom/countfastq (#32)
 - cutadapt (#11)

From 514ebfd0dc9f45a2702803dccc0ad14e8d8d0aab Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 12:55:03 -0500
Subject: [PATCH 12/47] fix: import platform

---
 .../CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py  | 1 +
 1 file changed, 1 insertion(+)

diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
index 1a0ee4b..089f213 100755
--- a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -5,6 +5,7 @@
 import os
 import uuid
 import pandas
+import platform
 
 
 def main(peakfiles, outbed, filter, nofilter):

From 2d0ddb3292893caa02be96dea4e1cf07a18b5266 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 12:55:17 -0500
Subject: [PATCH 13/47] fix: switch nf-core -> ccbr

---
 tests/modules/CCBR/bedtools/map/main.nf    | 4 ++--
 tests/modules/CCBR/bedtools/map/test.yml   | 4 ++--
 tests/modules/CCBR/bedtools/merge/main.nf  | 2 +-
 tests/modules/CCBR/bedtools/merge/test.yml | 2 +-
 tests/modules/CCBR/bedtools/sort/main.nf   | 2 +-
 tests/modules/CCBR/bedtools/sort/test.yml  | 4 ++--
 6 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tests/modules/CCBR/bedtools/map/main.nf b/tests/modules/CCBR/bedtools/map/main.nf
index 0d42cac..cb81d1d 100644
--- a/tests/modules/CCBR/bedtools/map/main.nf
+++ b/tests/modules/CCBR/bedtools/map/main.nf
@@ -2,8 +2,8 @@
 
 nextflow.enable.dsl = 2
 
-include { BEDTOOLS_MAP                           } from '../../../../../modules/nf-core/bedtools/map/main.nf'
-include { BEDTOOLS_MAP as BEDTOOLS_MAP_VCF } from '../../../../../modules/nf-core/bedtools/map/main.nf'
+include { BEDTOOLS_MAP                           } from '../../../../../modules/CCBR/bedtools/map/main.nf'
+include { BEDTOOLS_MAP as BEDTOOLS_MAP_VCF } from '../../../../../modules/CCBR/bedtools/map/main.nf'
 
 workflow test_bedtools_map {
     input = [
diff --git a/tests/modules/CCBR/bedtools/map/test.yml b/tests/modules/CCBR/bedtools/map/test.yml
index e06ddc3..0e5f78a 100644
--- a/tests/modules/CCBR/bedtools/map/test.yml
+++ b/tests/modules/CCBR/bedtools/map/test.yml
@@ -1,5 +1,5 @@
 - name: bedtools map test_bedtools_map
-  command: nextflow run ./tests/modules/nf-core/bedtools/map -entry test_bedtools_map -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/map/nextflow.config
+  command: nextflow run ./tests/modules/CCBR/bedtools/map -entry test_bedtools_map -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/map/nextflow.config
   tags:
     - bedtools
     - bedtools/map
@@ -10,7 +10,7 @@
       md5sum: 6c219404bf848cd4bd672a934dd4ed56
 
 - name: bedtools map test_bedtools_map_vcf
-  command: nextflow run ./tests/modules/nf-core/bedtools/map -entry test_bedtools_map_vcf -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/map/nextflow.config
+  command: nextflow run ./tests/modules/CCBR/bedtools/map -entry test_bedtools_map_vcf -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/map/nextflow.config
   tags:
     - bedtools
     - bedtools/map
diff --git a/tests/modules/CCBR/bedtools/merge/main.nf b/tests/modules/CCBR/bedtools/merge/main.nf
index 4941193..e0576e2 100644
--- a/tests/modules/CCBR/bedtools/merge/main.nf
+++ b/tests/modules/CCBR/bedtools/merge/main.nf
@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { BEDTOOLS_MERGE } from '../../../../../modules/nf-core/bedtools/merge/main.nf'
+include { BEDTOOLS_MERGE } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
 
 workflow test_bedtools_merge {
     input = [ [ id:'test'],
diff --git a/tests/modules/CCBR/bedtools/merge/test.yml b/tests/modules/CCBR/bedtools/merge/test.yml
index bee9b75..63d2aa9 100644
--- a/tests/modules/CCBR/bedtools/merge/test.yml
+++ b/tests/modules/CCBR/bedtools/merge/test.yml
@@ -1,5 +1,5 @@
 - name: bedtools merge
-  command: nextflow run ./tests/modules/nf-core/bedtools/merge -entry test_bedtools_merge -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/merge/nextflow.config
+  command: nextflow run ./tests/modules/CCBR/bedtools/merge -entry test_bedtools_merge -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/merge/nextflow.config
   tags:
     - bedtools
     - bedtools/merge
diff --git a/tests/modules/CCBR/bedtools/sort/main.nf b/tests/modules/CCBR/bedtools/sort/main.nf
index 0cf0daf..c03bc98 100644
--- a/tests/modules/CCBR/bedtools/sort/main.nf
+++ b/tests/modules/CCBR/bedtools/sort/main.nf
@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { BEDTOOLS_SORT } from '../../../../../modules/nf-core/bedtools/sort/main.nf'
+include { BEDTOOLS_SORT } from '../../../../../modules/CCBR/bedtools/sort/main.nf'
 
 workflow test_bedtools_sort {
     input = [ [ id:'test'],
diff --git a/tests/modules/CCBR/bedtools/sort/test.yml b/tests/modules/CCBR/bedtools/sort/test.yml
index 8a96bbb..a40820b 100644
--- a/tests/modules/CCBR/bedtools/sort/test.yml
+++ b/tests/modules/CCBR/bedtools/sort/test.yml
@@ -1,5 +1,5 @@
 - name: bedtools sort test_bedtools_sort
-  command: nextflow run ./tests/modules/nf-core/bedtools/sort -entry test_bedtools_sort -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/sort/nextflow.config
+  command: nextflow run ./tests/modules/CCBR/bedtools/sort -entry test_bedtools_sort -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/sort/nextflow.config
   tags:
     - bedtools
     - bedtools/sort
@@ -9,7 +9,7 @@
     - path: output/bedtools/versions.yml
 
 - name: bedtools sort test_bedtools_sort_with_genome
-  command: nextflow run ./tests/modules/nf-core/bedtools/sort -entry test_bedtools_sort_with_genome -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/bedtools/sort/nextflow.config
+  command: nextflow run ./tests/modules/CCBR/bedtools/sort -entry test_bedtools_sort_with_genome -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/sort/nextflow.config
   tags:
     - bedtools
     - bedtools/sort

From 73a74a6f34f880c6c4dfb303ead85cba9d4b96d3 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 13:15:31 -0500
Subject: [PATCH 14/47] fix: use ccbr base docker

---
 modules/CCBR/bedtools/map/main.nf   | 3 +--
 modules/CCBR/bedtools/merge/main.nf | 3 +--
 modules/CCBR/bedtools/sort/main.nf  | 3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/modules/CCBR/bedtools/map/main.nf b/modules/CCBR/bedtools/map/main.nf
index 5f09d6a..6f457ac 100644
--- a/modules/CCBR/bedtools/map/main.nf
+++ b/modules/CCBR/bedtools/map/main.nf
@@ -2,8 +2,7 @@ process BEDTOOLS_MAP {
     tag { meta.id }
     label 'process_single'
 
-    conda "bioconda::bedtools=2.31.0"
-    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
     input:
     tuple val(meta), path(intervals1), path(intervals2)
diff --git a/modules/CCBR/bedtools/merge/main.nf b/modules/CCBR/bedtools/merge/main.nf
index 5ef567c..ecb4dda 100644
--- a/modules/CCBR/bedtools/merge/main.nf
+++ b/modules/CCBR/bedtools/merge/main.nf
@@ -2,8 +2,7 @@ process BEDTOOLS_MERGE {
     tag { meta.id }
     label 'process_single'
 
-    conda "bioconda::bedtools=2.31.0"
-    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
     input:
     tuple val(meta), path(bed)
diff --git a/modules/CCBR/bedtools/sort/main.nf b/modules/CCBR/bedtools/sort/main.nf
index 677e328..0b1a49e 100644
--- a/modules/CCBR/bedtools/sort/main.nf
+++ b/modules/CCBR/bedtools/sort/main.nf
@@ -2,8 +2,7 @@ process BEDTOOLS_SORT {
     tag { meta.id }
     label 'process_single'
 
-    conda "bioconda::bedtools=2.31.0"
-    container 'biocontainers/bedtools:2.31.0--hf5e1c6e_2'
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
     input:
     tuple val(meta), path(intervals)

From 707b09361c46e75926d481d41a37d6f9e7a49415 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 13:16:43 -0500
Subject: [PATCH 15/47] test: don't check md5sum of versions file

---
 tests/modules/CCBR/bedtools/map/test.yml | 2 --
 1 file changed, 2 deletions(-)

diff --git a/tests/modules/CCBR/bedtools/map/test.yml b/tests/modules/CCBR/bedtools/map/test.yml
index 0e5f78a..9f94eba 100644
--- a/tests/modules/CCBR/bedtools/map/test.yml
+++ b/tests/modules/CCBR/bedtools/map/test.yml
@@ -7,7 +7,6 @@
     - path: output/bedtools/test_out.bed
       md5sum: d3aeb1ec7b90e0d5a6d1b9a4614ab96a
     - path: output/bedtools/versions.yml
-      md5sum: 6c219404bf848cd4bd672a934dd4ed56
 
 - name: bedtools map test_bedtools_map_vcf
   command: nextflow run ./tests/modules/CCBR/bedtools/map -entry test_bedtools_map_vcf -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/bedtools/map/nextflow.config
@@ -18,4 +17,3 @@
     - path: output/bedtools/test_out.bed
       md5sum: cabd34d1132834581e31f53dfa66ec03
     - path: output/bedtools/versions.yml
-      md5sum: ab927c219959af17dc370b0b8eda78bd

From 73705dbfa3462472489317d2468bc80f7d961a8d Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 13:29:28 -0500
Subject: [PATCH 16/47] test: stub for custom/consensuspeaks module

---
 modules/CCBR/custom/consensuspeaks/main.nf        |  3 +--
 tests/modules/CCBR/custom/consensuspeaks/test.yml | 10 +++++++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/modules/CCBR/custom/consensuspeaks/main.nf b/modules/CCBR/custom/consensuspeaks/main.nf
index 3a08bad..9b7d1c7 100644
--- a/modules/CCBR/custom/consensuspeaks/main.nf
+++ b/modules/CCBR/custom/consensuspeaks/main.nf
@@ -30,8 +30,7 @@ process CUSTOM_CONSENSUSPEAKS {
 
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${prefix}.bed versions.yml
+    touch ${meta.id}.${meta.group}.consensus_peaks.bed versions.yml
     """
 }
diff --git a/tests/modules/CCBR/custom/consensuspeaks/test.yml b/tests/modules/CCBR/custom/consensuspeaks/test.yml
index 4161ee4..0ecb8eb 100644
--- a/tests/modules/CCBR/custom/consensuspeaks/test.yml
+++ b/tests/modules/CCBR/custom/consensuspeaks/test.yml
@@ -7,5 +7,13 @@
     - "custom/consensuspeaks"
   files:
     - path: "output/custom/test.macs_broad.consensus_peaks.bed"
-      md5sum: 4d684a948335bbed948704e4be9f1abe
+      md5sum: 417447a3080df9d4ffa294b876dde640
+    - path: "output/custom/versions.yml"
+- name: "custom consensuspeaks stub"
+  command: nextflow run ./tests/modules/CCBR/custom/consensuspeaks -entry test_custom_consensuspeaks -c ./tests/config/nextflow.config -stub
+  tags:
+    - "custom"
+    - "custom/consensuspeaks"
+  files:
+    - path: "output/custom/test.macs_broad.consensus_peaks.bed"
     - path: "output/custom/versions.yml"

From b716bcad88d7cf470c3d2a54711ab5c9c285f14e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 13:31:01 -0500
Subject: [PATCH 17/47] docs: add bedtools modules

---
 CHANGELOG.md | 3 +++
 README.md    | 1 +
 2 files changed, 4 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 710c83b..5e1f550 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,9 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 
 ### New modules
 
+- bedtools/map (#37)
+- bedtools/merge (#37)
+- bedtools/sort (#37)
 - bwa/index
 - bwa/mem
   - also runs samtools sort & outputs index in bai format. (#12)
diff --git a/README.md b/README.md
index a8dc88d..d5df77d 100644
--- a/README.md
+++ b/README.md
@@ -46,6 +46,7 @@ Want to **contribute** to this project? Check out the [contributing guidelines](
 Many of the modules and subworkflows in this project reuse and adapt code from [nf-core/modules](https://github.com/nf-core/modules).
 In those cases, credit is noted in the `meta.yml` file of the module/subworkflow and also listed here:
 
+- [bedtools](modules/CCBR/bedtools) adapts the [nf-core bedtools module](https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools)
 - [bwa](modules/CCBR/bwa) adapts the [nf-core bwa module](https://github.com/nf-core/chipseq/tree/51eba00b32885c4d0bec60db3cb0a45eb61e34c5/modules/nf-core/modules/bwa)
 - [cutadapt](modules/CCBR/cutadapt) adapts the [nf-core cutadapt module](https://github.com/nf-core/modules/tree/ef007b1ce5316506b8c27c3e7a62482409c6153c/modules/nf-core/cutadapt)
 - [khmer](modules/CCBR/khmer) adapts the [nf-core khmer module](https://github.com/nf-core/modules/tree/b48a1efc8e067502e1a9bafbac788c1e0abdfc6a/modules/nf-core/khmer)

From cbf2d59570be6c2cdc35502c2ab4756ec3fbb422 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Mon, 27 Nov 2023 14:19:03 -0500
Subject: [PATCH 18/47] feat: add cat modules

---
 CHANGELOG.md                                 |  2 +
 README.md                                    |  1 +
 modules/CCBR/cat/cat/main.nf                 | 59 ++++++++++++++
 modules/CCBR/cat/cat/meta.yml                | 38 +++++++++
 modules/CCBR/cat/fastq/main.nf               | 77 ++++++++++++++++++
 modules/CCBR/cat/fastq/meta.yml              | 41 ++++++++++
 tests/config/pytest_modules.yml              |  8 ++
 tests/modules/CCBR/cat/cat/main.nf           | 61 +++++++++++++++
 tests/modules/CCBR/cat/cat/nextflow.config   | 12 +++
 tests/modules/CCBR/cat/cat/test.yml          | 81 +++++++++++++++++++
 tests/modules/CCBR/cat/fastq/main.nf         | 58 ++++++++++++++
 tests/modules/CCBR/cat/fastq/nextflow.config |  5 ++
 tests/modules/CCBR/cat/fastq/test.yml        | 82 ++++++++++++++++++++
 13 files changed, 525 insertions(+)
 create mode 100644 modules/CCBR/cat/cat/main.nf
 create mode 100644 modules/CCBR/cat/cat/meta.yml
 create mode 100644 modules/CCBR/cat/fastq/main.nf
 create mode 100644 modules/CCBR/cat/fastq/meta.yml
 create mode 100644 tests/modules/CCBR/cat/cat/main.nf
 create mode 100644 tests/modules/CCBR/cat/cat/nextflow.config
 create mode 100644 tests/modules/CCBR/cat/cat/test.yml
 create mode 100644 tests/modules/CCBR/cat/fastq/main.nf
 create mode 100644 tests/modules/CCBR/cat/fastq/nextflow.config
 create mode 100644 tests/modules/CCBR/cat/fastq/test.yml

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5e1f550..31c3aff 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,8 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 - bwa/index
 - bwa/mem
   - also runs samtools sort & outputs index in bai format. (#12)
+- cat/cat (#37)
+- cat/fastq (#37)
 - custom/bam2fastq (#14,#22)
 - custom/consensuspeaks (#37)
 - custom/convertsicer (#36)
diff --git a/README.md b/README.md
index d5df77d..bfa7051 100644
--- a/README.md
+++ b/README.md
@@ -48,6 +48,7 @@ In those cases, credit is noted in the `meta.yml` file of the module/subworkflow
 
 - [bedtools](modules/CCBR/bedtools) adapts the [nf-core bedtools module](https://github.com/nf-core/modules/tree/fff2c3fc7cdcb81a2a37c3263b8ace9b353af407/modules/nf-core/bedtools)
 - [bwa](modules/CCBR/bwa) adapts the [nf-core bwa module](https://github.com/nf-core/chipseq/tree/51eba00b32885c4d0bec60db3cb0a45eb61e34c5/modules/nf-core/modules/bwa)
+- [cat](modules/cat) adapts the [nf-core cat module](https://github.com/nf-core/modules/tree/9326d73af3fbe2ee90d9ce0a737461a727c5118e/modules/nf-core/cat)
 - [cutadapt](modules/CCBR/cutadapt) adapts the [nf-core cutadapt module](https://github.com/nf-core/modules/tree/ef007b1ce5316506b8c27c3e7a62482409c6153c/modules/nf-core/cutadapt)
 - [khmer](modules/CCBR/khmer) adapts the [nf-core khmer module](https://github.com/nf-core/modules/tree/b48a1efc8e067502e1a9bafbac788c1e0abdfc6a/modules/nf-core/khmer)
 - [picard/samtofastq](modules/picard/samtofastq) adapts the [nf-core gatk4 samtofastq module](https://github.com/nf-core/modules/tree/ef007b1ce5316506b8c27c3e7a62482409c6153c/modules/nf-core/gatk4/samtofastq)
diff --git a/modules/CCBR/cat/cat/main.nf b/modules/CCBR/cat/cat/main.nf
new file mode 100644
index 0000000..57cf950
--- /dev/null
+++ b/modules/CCBR/cat/cat/main.nf
@@ -0,0 +1,59 @@
+process CAT_CAT {
+    tag { meta.id }
+    label 'process_low'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v5'
+
+    input:
+    tuple val(meta), path(files_in)
+
+    output:
+    tuple val(meta), path("${prefix}"), emit: file_out
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def file_list = files_in.collect { it.toString() }
+
+    // | input     | output     | command1 | command2 |
+    // |-----------|------------|----------|----------|
+    // | gzipped   | gzipped    | cat      |          |
+    // | ungzipped | ungzipped  | cat      |          |
+    // | gzipped   | ungzipped  | zcat     |          |
+    // | ungzipped | gzipped    | cat      | pigz     |
+
+    // Use input file ending as default
+    prefix   = task.ext.prefix ?: "${meta.id}${file_list[0].substring(file_list[0].lastIndexOf('.'))}"
+    out_zip  = prefix.endsWith('.gz')
+    in_zip   = file_list[0].endsWith('.gz')
+    command1 = (in_zip && !out_zip) ? 'zcat' : 'cat'
+    command2 = (!in_zip && out_zip) ? "| pigz -c -p $task.cpus $args2" : ''
+    """
+    $command1 \\
+        $args \\
+        ${file_list.join(' ')} \\
+        $command2 \\
+        > ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
+
+    stub:
+    def file_list = files_in.collect { it.toString() }
+    prefix   = task.ext.prefix ?: "${meta.id}${file_list[0].substring(file_list[0].lastIndexOf('.'))}"
+    """
+    touch $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/cat/cat/meta.yml b/modules/CCBR/cat/cat/meta.yml
new file mode 100644
index 0000000..320d5c0
--- /dev/null
+++ b/modules/CCBR/cat/cat/meta.yml
@@ -0,0 +1,38 @@
+name: cat_cat
+description: A module for concatenation of gzipped or uncompressed files. Adapted from the nf-core cat module https://github.com/nf-core/modules/tree/9326d73af3fbe2ee90d9ce0a737461a727c5118e/modules/nf-core/cat
+keywords:
+  - concatenate
+  - gzip
+  - cat
+tools:
+  - cat:
+      description: Just concatenation
+
+      documentation: https://man7.org/linux/man-pages/man1/cat.1.html
+
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - files_in:
+      type: file
+      description: List of compressed / uncompressed files
+      pattern: "*"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - file_out:
+      type: file
+      description: Concatenated file. Will be gzipped if file_out ends with ".gz"
+      pattern: "${file_out}"
+
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/cat/fastq/main.nf b/modules/CCBR/cat/fastq/main.nf
new file mode 100644
index 0000000..0f7ee10
--- /dev/null
+++ b/modules/CCBR/cat/fastq/main.nf
@@ -0,0 +1,77 @@
+process CAT_FASTQ {
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v5'
+
+    input:
+    tuple val(meta), path(reads, stageAs: "input*/*")
+
+    output:
+    tuple val(meta), path("*.merged.fastq.gz"), emit: reads
+    path "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def readList = reads instanceof List ? reads.collect{ it.toString() } : [reads.toString()]
+    if (meta.single_end) {
+        if (readList.size >= 1) {
+            """
+            cat ${readList.join(' ')} > ${prefix}.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    } else {
+        if (readList.size >= 2) {
+            def read1 = []
+            def read2 = []
+            readList.eachWithIndex{ v, ix -> ( ix & 1 ? read2 : read1 ) << v }
+            """
+            cat ${read1.join(' ')} > ${prefix}_1.merged.fastq.gz
+            cat ${read2.join(' ')} > ${prefix}_2.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    }
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def readList = reads instanceof List ? reads.collect{ it.toString() } : [reads.toString()]
+    if (meta.single_end) {
+        if (readList.size > 1) {
+            """
+            touch ${prefix}.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    } else {
+        if (readList.size > 2) {
+            """
+            touch ${prefix}_1.merged.fastq.gz
+            touch ${prefix}_2.merged.fastq.gz
+
+            cat <<-END_VERSIONS > versions.yml
+            "${task.process}":
+                cat: \$(echo \$(cat --version 2>&1) | sed 's/^.*coreutils) //; s/ .*\$//')
+            END_VERSIONS
+            """
+        }
+    }
+
+}
diff --git a/modules/CCBR/cat/fastq/meta.yml b/modules/CCBR/cat/fastq/meta.yml
new file mode 100644
index 0000000..d2546af
--- /dev/null
+++ b/modules/CCBR/cat/fastq/meta.yml
@@ -0,0 +1,41 @@
+name: cat_fastq
+description: Concatenates fastq files. Adapted from the nf-core cat module https://github.com/nf-core/modules/tree/9326d73af3fbe2ee90d9ce0a737461a727c5118e/modules/nf-core/cat
+keywords:
+  - cat
+  - fastq
+  - concatenate
+tools:
+  - cat:
+      description: |
+        The cat utility reads files sequentially, writing them to the standard output.
+      documentation: https://www.gnu.org/software/coreutils/manual/html_node/cat-invocation.html
+      licence: ["GPL-3.0-or-later"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files to be concatenated.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: Merged fastq file
+      pattern: "*.{merged.fastq.gz}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 05d3f2f..e47b8fd 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -18,6 +18,14 @@ bwa/mem:
   - modules/CCBR/bwa/mem/**
   - tests/modules/CCBR/bwa/mem/**
 
+cat/cat:
+  - modules/CCBR/cat/cat/**
+  - tests/modules/CCBR/cat/cat/**
+
+cat/fastq:
+  - modules/CCBR/cat/fastq/**
+  - tests/modules/CCBR/cat/fastq/**
+
 custom/bam2fastq:
   - modules/CCBR/custom/bam2fastq/**
   - tests/modules/CCBR/custom/bam2fastq/**
diff --git a/tests/modules/CCBR/cat/cat/main.nf b/tests/modules/CCBR/cat/cat/main.nf
new file mode 100644
index 0000000..e490b9b
--- /dev/null
+++ b/tests/modules/CCBR/cat/cat/main.nf
@@ -0,0 +1,61 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_CAT                        } from '../../../../../modules/CCBR/cat/cat/main.nf'
+include { CAT_CAT as CAT_UNZIPPED_ZIPPED } from '../../../../../modules/CCBR/cat/cat/main.nf'
+include { CAT_CAT as CAT_ZIPPED_UNZIPPED } from '../../../../../modules/CCBR/cat/cat/main.nf'
+
+workflow test_cat_unzipped_unzipped {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['sarscov2']['genome']['genome_sizes'], checkIfExists: true) ]
+    ]
+
+    CAT_CAT ( input )
+}
+
+workflow test_cat_zipped_zipped {
+
+    input = [
+         [ id:'test', single_end:true ], // meta map
+        [file(params.test_data['sarscov2']['genome']['genome_gff3_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['genome']['contigs_genome_maf_gz'], checkIfExists: true)]
+    ]
+
+    CAT_CAT ( input )
+}
+
+workflow test_cat_zipped_unzipped {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [file(params.test_data['sarscov2']['genome']['genome_gff3_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['genome']['contigs_genome_maf_gz'], checkIfExists: true)]
+    ]
+
+    CAT_ZIPPED_UNZIPPED ( input )
+}
+
+workflow test_cat_unzipped_zipped {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+        file(params.test_data['sarscov2']['genome']['genome_sizes'], checkIfExists: true)]
+    ]
+
+    CAT_UNZIPPED_ZIPPED ( input )
+}
+
+workflow test_cat_one_file_unzipped_zipped {
+
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    ]
+
+    CAT_UNZIPPED_ZIPPED ( input )
+}
diff --git a/tests/modules/CCBR/cat/cat/nextflow.config b/tests/modules/CCBR/cat/cat/nextflow.config
new file mode 100644
index 0000000..8916a29
--- /dev/null
+++ b/tests/modules/CCBR/cat/cat/nextflow.config
@@ -0,0 +1,12 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: CAT_UNZIPPED_ZIPPED {
+        ext.prefix = 'cat.txt.gz'
+    }
+
+    withName: CAT_ZIPPED_UNZIPPED {
+        ext.prefix = 'cat.txt'
+    }
+}
diff --git a/tests/modules/CCBR/cat/cat/test.yml b/tests/modules/CCBR/cat/cat/test.yml
new file mode 100644
index 0000000..6567048
--- /dev/null
+++ b/tests/modules/CCBR/cat/cat/test.yml
@@ -0,0 +1,81 @@
+- name: cat unzipped unzipped
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_unzipped_unzipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/test.fasta
+      md5sum: f44b33a0e441ad58b2d3700270e2dbe2
+
+- name: cat unzipped unzipped stub
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_unzipped_unzipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/test.fasta
+
+- name: cat zipped zipped
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_zipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/test.gz
+
+- name: cat zipped zipped stub
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_zipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/test.gz
+
+- name: cat zipped unzipped
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_zipped_unzipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt
+      md5sum: c439d3b60e7bc03e8802a451a0d9a5d9
+
+- name: cat zipped unzipped stub
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_zipped_unzipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt
+
+- name: cat unzipped zipped
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_unzipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt.gz
+
+- name: cat unzipped zipped stub
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_unzipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt.gz
+
+- name: cat one file unzipped zipped
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_one_file_unzipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt.gz
+
+- name: cat one file unzipped zipped stub
+  command: nextflow run ./tests/modules/CCBR/cat/cat -entry test_cat_one_file_unzipped_zipped -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/cat/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/cat
+  files:
+    - path: output/cat/cat.txt.gz
diff --git a/tests/modules/CCBR/cat/fastq/main.nf b/tests/modules/CCBR/cat/fastq/main.nf
new file mode 100644
index 0000000..48582e5
--- /dev/null
+++ b/tests/modules/CCBR/cat/fastq/main.nf
@@ -0,0 +1,58 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_FASTQ } from '../../../../../modules/CCBR/cat/fastq/main.nf'
+
+workflow test_cat_fastq_single_end {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test2_1_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_paired_end {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test2_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test2_2_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_single_end_same_name {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_paired_end_same_name {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+        file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+    ]
+
+    CAT_FASTQ ( input )
+}
+
+workflow test_cat_fastq_single_end_single_file {
+    input = [
+        [ id:'test', single_end:true ], // meta map
+        [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)]
+    ]
+
+    CAT_FASTQ ( input )
+}
diff --git a/tests/modules/CCBR/cat/fastq/nextflow.config b/tests/modules/CCBR/cat/fastq/nextflow.config
new file mode 100644
index 0000000..8730f1c
--- /dev/null
+++ b/tests/modules/CCBR/cat/fastq/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
diff --git a/tests/modules/CCBR/cat/fastq/test.yml b/tests/modules/CCBR/cat/fastq/test.yml
new file mode 100644
index 0000000..28d206d
--- /dev/null
+++ b/tests/modules/CCBR/cat/fastq/test.yml
@@ -0,0 +1,82 @@
+- name: cat fastq single-end
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_single_end -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test.merged.fastq.gz
+      md5sum: f9cf5e375f7de81a406144a2c70cc64d
+
+- name: cat fastq fastqc_paired_end
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test_2.merged.fastq.gz
+      md5sum: 77c8e966e130d8c6b6ec9be52fcb2bda
+    - path: ./output/cat/test_1.merged.fastq.gz
+      md5sum: f9cf5e375f7de81a406144a2c70cc64d
+
+- name: cat fastq single-end-same-name
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_single_end_same_name -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test.merged.fastq.gz
+      md5sum: 63f817db7a29a03eb538104495556f66
+
+- name: cat fastq fastqc_paired_end_same_name
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_paired_end_same_name -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test_1.merged.fastq.gz
+      md5sum: 63f817db7a29a03eb538104495556f66
+    - path: ./output/cat/test_2.merged.fastq.gz
+      md5sum: fe9f266f43a6fc3dcab690a18419a56e
+
+- name: cat fastq single-end-single-file
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_single_end_single_file -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test.merged.fastq.gz
+      md5sum: e325ef7deb4023447a1f074e285761af
+
+- name: cat fastq single-end stub
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_single_end -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test.merged.fastq.gz
+
+- name: cat fastq fastqc_paired_end stub
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test_2.merged.fastq.gz
+    - path: ./output/cat/test_1.merged.fastq.gz
+
+- name: cat fastq single-end-same-name stub
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_single_end_same_name -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test.merged.fastq.gz
+
+- name: cat fastq fastqc_paired_end_same_name stub
+  command: nextflow run ./tests/modules/CCBR/cat/fastq -entry test_cat_fastq_paired_end_same_name -c ./tests/config/nextflow.config -c ./tests/modules/CCBR/cat/fastq/nextflow.config -stub-run
+  tags:
+    - cat
+    - cat/fastq
+  files:
+    - path: ./output/cat/test_1.merged.fastq.gz
+    - path: ./output/cat/test_2.merged.fastq.gz

From 075450e8744d0056e0cec3dae23487e1cfff71c0 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 09:12:37 -0500
Subject: [PATCH 19/47] feat: add bedops/bedmap module

---
 CHANGELOG.md                                  |  1 +
 modules/CCBR/bedops/bedmap/main.nf            | 37 +++++++++++++
 modules/CCBR/bedops/bedmap/meta.yml           | 55 +++++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 tests/modules/CCBR/bedops/bedmap/main.nf      | 26 +++++++++
 .../CCBR/bedops/bedmap/nextflow.config        |  7 +++
 tests/modules/CCBR/bedops/bedmap/test.yml     | 12 ++++
 7 files changed, 142 insertions(+)
 create mode 100644 modules/CCBR/bedops/bedmap/main.nf
 create mode 100644 modules/CCBR/bedops/bedmap/meta.yml
 create mode 100644 tests/modules/CCBR/bedops/bedmap/main.nf
 create mode 100644 tests/modules/CCBR/bedops/bedmap/nextflow.config
 create mode 100644 tests/modules/CCBR/bedops/bedmap/test.yml

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 31c3aff..af92ebf 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,7 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 
 ### New modules
 
+- bedops/bedmap (#37)
 - bedtools/map (#37)
 - bedtools/merge (#37)
 - bedtools/sort (#37)
diff --git a/modules/CCBR/bedops/bedmap/main.nf b/modules/CCBR/bedops/bedmap/main.nf
new file mode 100644
index 0000000..e58b63e
--- /dev/null
+++ b/modules/CCBR/bedops/bedmap/main.nf
@@ -0,0 +1,37 @@
+process BEDOPS_BEDMAP {
+    tag { meta.id }
+    label 'process_single'
+    container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
+
+    input:
+    tuple val(meta1), path(refbed)
+    tuple val(meta2), path(mapbed)
+
+    output:
+    tuple val(meta2), path("*.mapped.bed"), emit: bed
+    path "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    bedmap \\
+        --delim '\t' \\
+        --echo-ref-name \\
+        --count \\
+        ${refbed} \\
+        ${mapbed} \\
+        > ${meta2.id}.mapped.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedops: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch ${meta2.id}.mapped.bed versions.yml
+    """
+}
diff --git a/modules/CCBR/bedops/bedmap/meta.yml b/modules/CCBR/bedops/bedmap/meta.yml
new file mode 100644
index 0000000..de83591
--- /dev/null
+++ b/modules/CCBR/bedops/bedmap/meta.yml
@@ -0,0 +1,55 @@
+---
+name: "bedops_bedmap"
+description: The bedmap program is used to retrieve and process signal or other features over regions of interest in BED files
+keywords:
+  - bedops
+  - bedmap
+  - bed
+  - intervals
+tools:
+  - bedops:
+      description: |
+        fast, highly scalable and easily-parallelizable genome analysis toolkit
+      documentation: https://bedops.readthedocs.io/
+      tool_dev_url: https://github.com/bedops/bedops
+      licence: ["GPLv2"]
+      doi: 10.1093/bioinformatics/bts277
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - refbed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+  - mapbed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - mapped_bed:
+      type: file
+      description: BED file
+      pattern: "*.bed"
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index e47b8fd..1475144 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -1,3 +1,7 @@
+bedops/bedmap:
+  - modules/CCBR/bedops/bedmap/**
+  - tests/modules/CCBR/bedops/bedmap/**
+
 bedtools/map:
   - modules/CCBR/bedtools/map/**
   - tests/modules/CCBR/bedtools/map/**
diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
new file mode 100644
index 0000000..e0d321d
--- /dev/null
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -0,0 +1,26 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_CAT                    } from '../../../../../modules/CCBR/cat/cat/main.nf'
+include { BEDOPS_BEDMAP              } from '../../../../../modules/CCBR/bedops/bedmap/main.nf'
+include { BEDTOOLS_SORT as SORT_CAT
+          BEDTOOLS_SORT as SORT_PEAK } from '../../../../../modules/CCBR/bedtools/sort/main.nf'
+include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
+
+workflow test_bedops_bedmap {
+
+    ch_peaks = [
+        [ id: 'test', group: 'macs_broad' ], // meta map
+        [ file(params.test_data['macs_peaks_1'], checkIfExists: true),
+          file(params.test_data['macs_peaks_2'], checkIfExists: true),
+        ]
+    ]
+
+    ch_peaks.collect() | CAT_CAT
+    CAT_CAT.out.file_out | SORT_CAT
+    SORT_CAT.out.sorted | BEDTOOLS_MERGE
+
+    ch_peaks | SORT_PEAK
+    BEDOPS_BEDMAP( BEDTOOLS_MERGE.out.bed, SORT_PEAK.out.sorted )
+}
diff --git a/tests/modules/CCBR/bedops/bedmap/nextflow.config b/tests/modules/CCBR/bedops/bedmap/nextflow.config
new file mode 100644
index 0000000..a652b2d
--- /dev/null
+++ b/tests/modules/CCBR/bedops/bedmap/nextflow.config
@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
+
+includeConfig '../../../../config/test_data_CCBR.config'
diff --git a/tests/modules/CCBR/bedops/bedmap/test.yml b/tests/modules/CCBR/bedops/bedmap/test.yml
new file mode 100644
index 0000000..3c4418a
--- /dev/null
+++ b/tests/modules/CCBR/bedops/bedmap/test.yml
@@ -0,0 +1,12 @@
+## TODO nf-core: Please run the following command to build this file:
+#                nf-core modules create-test-yml /bedmap
+- name: "bedops bedmap"
+  command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config
+  tags:
+    - "bedops"
+    - "bedops/bedmap"
+  files:
+    - path: "output/bedops/test.bam"
+      md5sum: e667c7caad0bc4b7ac383fd023c654fc
+    - path: "output/bedops/versions.yml"
+      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b

From 624f56ce1f6cfd9d4577acb96cbab94f1f1fb7d6 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 10:26:45 -0500
Subject: [PATCH 20/47] style: align includes

---
 tests/modules/CCBR/bedtools/map/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/modules/CCBR/bedtools/map/main.nf b/tests/modules/CCBR/bedtools/map/main.nf
index cb81d1d..f1cf128 100644
--- a/tests/modules/CCBR/bedtools/map/main.nf
+++ b/tests/modules/CCBR/bedtools/map/main.nf
@@ -2,7 +2,7 @@
 
 nextflow.enable.dsl = 2
 
-include { BEDTOOLS_MAP                           } from '../../../../../modules/CCBR/bedtools/map/main.nf'
+include { BEDTOOLS_MAP                     } from '../../../../../modules/CCBR/bedtools/map/main.nf'
 include { BEDTOOLS_MAP as BEDTOOLS_MAP_VCF } from '../../../../../modules/CCBR/bedtools/map/main.nf'
 
 workflow test_bedtools_map {

From dff08c96430770edab6e097c5c2ab864494ceac2 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 10:31:55 -0500
Subject: [PATCH 21/47] test: add test for bedops/bedmap

---
 modules/CCBR/bedops/bedmap/main.nf            |  2 +-
 tests/modules/CCBR/bedops/bedmap/main.nf      | 20 +++++-----
 .../CCBR/bedops/bedmap/nextflow.config        |  5 +++
 tests/modules/CCBR/bedops/bedmap/test.yml     | 40 ++++++++++++++-----
 4 files changed, 47 insertions(+), 20 deletions(-)

diff --git a/modules/CCBR/bedops/bedmap/main.nf b/modules/CCBR/bedops/bedmap/main.nf
index e58b63e..c592a82 100644
--- a/modules/CCBR/bedops/bedmap/main.nf
+++ b/modules/CCBR/bedops/bedmap/main.nf
@@ -1,5 +1,5 @@
 process BEDOPS_BEDMAP {
-    tag { meta.id }
+    tag { meta2.id }
     label 'process_single'
     container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
index e0d321d..a6ac739 100644
--- a/tests/modules/CCBR/bedops/bedmap/main.nf
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -10,17 +10,17 @@ include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtool
 
 workflow test_bedops_bedmap {
 
-    ch_peaks = [
-        [ id: 'test', group: 'macs_broad' ], // meta map
-        [ file(params.test_data['macs_peaks_1'], checkIfExists: true),
-          file(params.test_data['macs_peaks_2'], checkIfExists: true),
-        ]
-    ]
-
-    ch_peaks.collect() | CAT_CAT
-    CAT_CAT.out.file_out | SORT_CAT
+    ch_peaks = Channel.fromPath([file(params.test_data['macs_peaks_1'], checkIfExists: true),
+                                 file(params.test_data['macs_peaks_2'], checkIfExists: true)])
+        .map { peak ->
+            [ [ id: 'test', group: 'macs_broad' ], peak ]
+        }
+    // prepare reference
+    CAT_CAT(ch_peaks.groupTuple())
+    SORT_CAT(CAT_CAT.out.file_out, [])
     SORT_CAT.out.sorted | BEDTOOLS_MERGE
 
-    ch_peaks | SORT_PEAK
+    // map peaks to reference
+    SORT_PEAK(ch_peaks, [])
     BEDOPS_BEDMAP( BEDTOOLS_MERGE.out.bed, SORT_PEAK.out.sorted )
 }
diff --git a/tests/modules/CCBR/bedops/bedmap/nextflow.config b/tests/modules/CCBR/bedops/bedmap/nextflow.config
index a652b2d..8e6be37 100644
--- a/tests/modules/CCBR/bedops/bedmap/nextflow.config
+++ b/tests/modules/CCBR/bedops/bedmap/nextflow.config
@@ -2,6 +2,11 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
+    withName: BEDTOOLS_SORT {
+        ext.prefix = { "${meta.id}_out" }
+        ext.suffix = "testtext"
+    }
+
 }
 
 includeConfig '../../../../config/test_data_CCBR.config'
diff --git a/tests/modules/CCBR/bedops/bedmap/test.yml b/tests/modules/CCBR/bedops/bedmap/test.yml
index 3c4418a..fbf48ad 100644
--- a/tests/modules/CCBR/bedops/bedmap/test.yml
+++ b/tests/modules/CCBR/bedops/bedmap/test.yml
@@ -1,12 +1,34 @@
-## TODO nf-core: Please run the following command to build this file:
-#                nf-core modules create-test-yml /bedmap
-- name: "bedops bedmap"
+- name: bedops bedmap test_bedops_bedmap
   command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config
   tags:
-    - "bedops"
-    - "bedops/bedmap"
+    - bedops/bedmap
+    - bedops
   files:
-    - path: "output/bedops/test.bam"
-      md5sum: e667c7caad0bc4b7ac383fd023c654fc
-    - path: "output/bedops/versions.yml"
-      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b
+    - path: output/bedops/test.mapped.bed
+      contains:
+        - "chrI:229492-230276"
+    - path: output/bedops/versions.yml
+    - path: output/bedtools/test.bed
+      md5sum: d67c8c15b99b310ec5aa0ec363dcd147
+    - path: output/bedtools/versions.yml
+    - path: output/cat/test.broadPeak
+      md5sum: c5d73e727a10d2a32b139efcdd369f59
+    - path: output/cat/versions.yml
+    - path: output/sort/test_out.testtext
+      md5sum: b412285368f1698634177087e7ea4103
+    - path: output/sort/versions.yml
+
+- name: bedops bedmap test_bedops_bedmap stub
+  command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config -stub
+  tags:
+    - bedops/bedmap
+    - bedops
+  files:
+    - path: output/bedops/test.mapped.bed
+    - path: output/bedops/versions.yml
+    - path: output/bedtools/test.bed
+    - path: output/bedtools/versions.yml
+    - path: output/cat/test.broadPeak
+    - path: output/cat/versions.yml
+    - path: output/sort/test_out.testtext
+    - path: output/sort/versions.yml

From b45f529cfecd73abd67e770fa9736a21816fb60c Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 10:39:03 -0500
Subject: [PATCH 22/47] feat: set default prefixes for bedtools processes

prevent the need to set task.ext.prefix in most cases
---
 modules/CCBR/bedtools/map/main.nf   | 4 ++--
 modules/CCBR/bedtools/merge/main.nf | 4 ++--
 modules/CCBR/bedtools/sort/main.nf  | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/modules/CCBR/bedtools/map/main.nf b/modules/CCBR/bedtools/map/main.nf
index 6f457ac..7ebb336 100644
--- a/modules/CCBR/bedtools/map/main.nf
+++ b/modules/CCBR/bedtools/map/main.nf
@@ -17,7 +17,7 @@ process BEDTOOLS_MAP {
 
     script:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}.mapped"
     extension = intervals1.getExtension()
     def sizes = chrom_sizes ? "-g ${chrom_sizes}" : ''
     if ("$intervals1" == "${prefix}.${extension}" ||
@@ -39,7 +39,7 @@ process BEDTOOLS_MAP {
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}.mapped"
     extension = intervals1.getExtension()
     if ("${intervals1}" == "${prefix}.${extension}" ||
         "${intervals2}" == "${prefix}.${extension}")
diff --git a/modules/CCBR/bedtools/merge/main.nf b/modules/CCBR/bedtools/merge/main.nf
index ecb4dda..bdeb79b 100644
--- a/modules/CCBR/bedtools/merge/main.nf
+++ b/modules/CCBR/bedtools/merge/main.nf
@@ -16,7 +16,7 @@ process BEDTOOLS_MERGE {
 
     script:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}.merged"
     if ("$bed" == "${prefix}.bed") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
     """
     bedtools \\
@@ -32,7 +32,7 @@ process BEDTOOLS_MERGE {
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}.merged"
     """
     touch ${prefix}.bed
 
diff --git a/modules/CCBR/bedtools/sort/main.nf b/modules/CCBR/bedtools/sort/main.nf
index 0b1a49e..90b2b70 100644
--- a/modules/CCBR/bedtools/sort/main.nf
+++ b/modules/CCBR/bedtools/sort/main.nf
@@ -17,7 +17,7 @@ process BEDTOOLS_SORT {
 
     script:
     def args       = task.ext.args   ?: ''
-    def prefix     = task.ext.prefix ?: "${meta.id}"
+    def prefix     = task.ext.prefix ?: "${meta.id}.sorted"
     def genome_cmd = genome_file     ?  "-g $genome_file" : ""
     extension      = task.ext.suffix ?: intervals.extension
     if ("$intervals" == "${prefix}.${extension}") {
@@ -38,8 +38,8 @@ process BEDTOOLS_SORT {
     """
 
     stub:
-    def prefix = task.ext.prefix ?: "${meta.id}"
-    extension      = task.ext.suffix ?: intervals.extension
+    def prefix = task.ext.prefix ?: "${meta.id}.sorted"
+    extension  = task.ext.suffix ?: intervals.extension
     """
     touch ${prefix}.${extension}
 

From 35157e01e16c8410160cb52abc141e5bbb7f4e74 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 11:05:39 -0500
Subject: [PATCH 23/47] fix: propagate metadata correctly

---
 modules/CCBR/bedops/bedmap/main.nf            | 20 +++++---
 tests/modules/CCBR/bedops/bedmap/main.nf      | 12 +++--
 .../CCBR/bedops/bedmap/nextflow.config        |  7 +--
 tests/modules/CCBR/bedops/bedmap/test.yml     | 50 +++++++++++--------
 4 files changed, 52 insertions(+), 37 deletions(-)

diff --git a/modules/CCBR/bedops/bedmap/main.nf b/modules/CCBR/bedops/bedmap/main.nf
index c592a82..102529a 100644
--- a/modules/CCBR/bedops/bedmap/main.nf
+++ b/modules/CCBR/bedops/bedmap/main.nf
@@ -1,15 +1,14 @@
 process BEDOPS_BEDMAP {
-    tag { meta2.id }
+    tag { meta.id }
     label 'process_single'
     container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
     input:
-    tuple val(meta1), path(refbed)
-    tuple val(meta2), path(mapbed)
+    tuple val(meta), path(mapbed), path(refbed)
 
     output:
-    tuple val(meta2), path("*.mapped.bed"), emit: bed
-    path "versions.yml"                   , emit: versions
+    tuple val(meta), path("*.mapped.bed"), emit: bed
+    path "versions.yml"                  , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,16 +21,21 @@ process BEDOPS_BEDMAP {
         --count \\
         ${refbed} \\
         ${mapbed} \\
-        > ${meta2.id}.mapped.bed
+        > ${meta.id}.mapped.bed
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        bedops: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' ))
+        bedops: \$(echo \$(bedops --version 2>&1 | grep version | sed 's/version: //'))
     END_VERSIONS
     """
 
     stub:
     """
-    touch ${meta2.id}.mapped.bed versions.yml
+    touch ${meta.id}.mapped.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bedops: \$(echo \$(bedops --version 2>&1 | grep version | sed 's/version: //'))
+    END_VERSIONS
     """
 }
diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
index a6ac739..b35406b 100644
--- a/tests/modules/CCBR/bedops/bedmap/main.nf
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -13,14 +13,20 @@ workflow test_bedops_bedmap {
     ch_peaks = Channel.fromPath([file(params.test_data['macs_peaks_1'], checkIfExists: true),
                                  file(params.test_data['macs_peaks_2'], checkIfExists: true)])
         .map { peak ->
-            [ [ id: 'test', group: 'macs_broad' ], peak ]
+            [ [id: peak.baseName, group: 'macs_broad'], peak ]
         }
     // prepare reference
-    CAT_CAT(ch_peaks.groupTuple())
+    ch_peaks
+        .map{ meta, peak ->
+            [ [id: 'test', group: 'macs_broad'], peak ]
+        }
+        .groupTuple() | CAT_CAT
     SORT_CAT(CAT_CAT.out.file_out, [])
     SORT_CAT.out.sorted | BEDTOOLS_MERGE
+    map_bed = BEDTOOLS_MERGE.out.bed.map{ meta, bed -> bed }
 
     // map peaks to reference
     SORT_PEAK(ch_peaks, [])
-    BEDOPS_BEDMAP( BEDTOOLS_MERGE.out.bed, SORT_PEAK.out.sorted )
+    SORT_PEAK.out.sorted | view
+    BEDOPS_BEDMAP( SORT_PEAK.out.sorted.combine(map_bed) )
 }
diff --git a/tests/modules/CCBR/bedops/bedmap/nextflow.config b/tests/modules/CCBR/bedops/bedmap/nextflow.config
index 8e6be37..e942eb5 100644
--- a/tests/modules/CCBR/bedops/bedmap/nextflow.config
+++ b/tests/modules/CCBR/bedops/bedmap/nextflow.config
@@ -1,11 +1,6 @@
 process {
 
-    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
-    withName: BEDTOOLS_SORT {
-        ext.prefix = { "${meta.id}_out" }
-        ext.suffix = "testtext"
-    }
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].toLowerCase()}" }
 
 }
 
diff --git a/tests/modules/CCBR/bedops/bedmap/test.yml b/tests/modules/CCBR/bedops/bedmap/test.yml
index fbf48ad..8e039b4 100644
--- a/tests/modules/CCBR/bedops/bedmap/test.yml
+++ b/tests/modules/CCBR/bedops/bedmap/test.yml
@@ -1,34 +1,44 @@
-- name: bedops bedmap test_bedops_bedmap
+- name: test_bedops_bedmap
   command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config
   tags:
     - bedops/bedmap
     - bedops
   files:
-    - path: output/bedops/test.mapped.bed
-      contains:
-        - "chrI:229492-230276"
-    - path: output/bedops/versions.yml
-    - path: output/bedtools/test.bed
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.mapped.bed
+      md5sum: a46e2f78e8534ecdc882fff22f0baa87
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.mapped.bed
+      md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/test.merged.bed
       md5sum: d67c8c15b99b310ec5aa0ec363dcd147
-    - path: output/bedtools/versions.yml
-    - path: output/cat/test.broadPeak
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/test.broadPeak
       md5sum: c5d73e727a10d2a32b139efcdd369f59
-    - path: output/cat/versions.yml
-    - path: output/sort/test_out.testtext
+    - path: output/cat_cat/versions.yml
+    - path: output/sort_cat/test.sorted.broadPeak
       md5sum: b412285368f1698634177087e7ea4103
-    - path: output/sort/versions.yml
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+      md5sum: 03b87e9021f85db1c8e07f5c0b4d7347
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+      md5sum: d3216918f24ced4b76b8eed6e38aa5c6
+    - path: output/sort_peak/versions.yml
 
-- name: bedops bedmap test_bedops_bedmap stub
+- name: test_bedops_bedmap stub
   command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config -stub
   tags:
     - bedops/bedmap
     - bedops
   files:
-    - path: output/bedops/test.mapped.bed
-    - path: output/bedops/versions.yml
-    - path: output/bedtools/test.bed
-    - path: output/bedtools/versions.yml
-    - path: output/cat/test.broadPeak
-    - path: output/cat/versions.yml
-    - path: output/sort/test_out.testtext
-    - path: output/sort/versions.yml
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.mapped.bed
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/test.merged.bed
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/test.broadPeak
+    - path: output/cat_cat/versions.yml
+    - path: output/sort_cat/test.sorted.broadPeak
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+    - path: output/sort_peak/versions.yml

From 8664362d5177cda16a632a6cc64da6d84306c15d Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 12:13:32 -0500
Subject: [PATCH 24/47] test: update test data config paths

---
 tests/modules/CCBR/bedops/bedmap/main.nf         | 4 ++--
 tests/modules/CCBR/custom/consensuspeaks/main.nf | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
index b35406b..6f14a23 100644
--- a/tests/modules/CCBR/bedops/bedmap/main.nf
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -10,8 +10,8 @@ include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtool
 
 workflow test_bedops_bedmap {
 
-    ch_peaks = Channel.fromPath([file(params.test_data['macs_peaks_1'], checkIfExists: true),
-                                 file(params.test_data['macs_peaks_2'], checkIfExists: true)])
+    ch_peaks = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+                                 file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])
         .map { peak ->
             [ [id: peak.baseName, group: 'macs_broad'], peak ]
         }
diff --git a/tests/modules/CCBR/custom/consensuspeaks/main.nf b/tests/modules/CCBR/custom/consensuspeaks/main.nf
index 0b33660..5288576 100644
--- a/tests/modules/CCBR/custom/consensuspeaks/main.nf
+++ b/tests/modules/CCBR/custom/consensuspeaks/main.nf
@@ -8,8 +8,8 @@ workflow test_custom_consensuspeaks {
 
     input = [
         [ id: 'test', group: 'macs_broad' ], // meta map
-        [ file(params.test_data['macs_peaks_1'], checkIfExists: true),
-          file(params.test_data['macs_peaks_2'], checkIfExists: true),
+        [ file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+          file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true),
         ]
     ]
 

From d46e529b8ca9232c9964814f54d3d302d7bf57a8 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 12:38:16 -0500
Subject: [PATCH 25/47] refactor: fix ref bed name

---
 tests/modules/CCBR/bedops/bedmap/main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
index 6f14a23..f1f13d2 100644
--- a/tests/modules/CCBR/bedops/bedmap/main.nf
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -23,10 +23,10 @@ workflow test_bedops_bedmap {
         .groupTuple() | CAT_CAT
     SORT_CAT(CAT_CAT.out.file_out, [])
     SORT_CAT.out.sorted | BEDTOOLS_MERGE
-    map_bed = BEDTOOLS_MERGE.out.bed.map{ meta, bed -> bed }
+    ref_bed = BEDTOOLS_MERGE.out.bed.map{ meta, bed -> bed }
 
     // map peaks to reference
     SORT_PEAK(ch_peaks, [])
     SORT_PEAK.out.sorted | view
-    BEDOPS_BEDMAP( SORT_PEAK.out.sorted.combine(map_bed) )
+    BEDOPS_BEDMAP( SORT_PEAK.out.sorted.combine(ref_bed) )
 }

From 8e31f3432b8c0a2caff472f556fe752927d6b908 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Tue, 28 Nov 2023 15:23:43 -0500
Subject: [PATCH 26/47] refactor: don't delete intermediate files

---
 .../custom/consensuspeaks/templates/get_consensus_peaks.py  | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
index 089f213..cec8a0e 100755
--- a/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
+++ b/modules/CCBR/custom/consensuspeaks/templates/get_consensus_peaks.py
@@ -11,7 +11,7 @@
 def main(peakfiles, outbed, filter, nofilter):
     deleteFiles = []
 
-    rand_name = str(uuid.uuid4())
+    rand_name = ""  # str(uuid.uuid4())
 
     # concat
     cmd = "cat"
@@ -96,8 +96,8 @@ def main(peakfiles, outbed, filter, nofilter):
                     % (chrom, start, end, row["peakid"], float(row["score"]))
                 )
 
-    for f in deleteFiles:
-        os.remove(f)
+    # for f in deleteFiles:
+    #    os.remove(f)
 
 
 def write_versions():

From dbc2219505802630bc7012d1dc74950cea972b13 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 10:46:02 -0500
Subject: [PATCH 27/47] feat: keep ref meta.id in bedmap outfiles

---
 modules/CCBR/bedops/bedmap/main.nf        |  8 ++++----
 tests/modules/CCBR/bedops/bedmap/main.nf  |  4 +---
 tests/modules/CCBR/bedops/bedmap/test.yml | 16 ++++++++--------
 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/modules/CCBR/bedops/bedmap/main.nf b/modules/CCBR/bedops/bedmap/main.nf
index 102529a..84289be 100644
--- a/modules/CCBR/bedops/bedmap/main.nf
+++ b/modules/CCBR/bedops/bedmap/main.nf
@@ -1,10 +1,10 @@
 process BEDOPS_BEDMAP {
-    tag { meta.id }
+    tag "${meta.id}.${refmeta.id}"
     label 'process_single'
     container 'nciccbr/ccbr_ubuntu_base_20.04:v6.1'
 
     input:
-    tuple val(meta), path(mapbed), path(refbed)
+    tuple val(meta), path(mapbed), val(refmeta), path(refbed)
 
     output:
     tuple val(meta), path("*.mapped.bed"), emit: bed
@@ -21,7 +21,7 @@ process BEDOPS_BEDMAP {
         --count \\
         ${refbed} \\
         ${mapbed} \\
-        > ${meta.id}.mapped.bed
+        > ${meta.id}.${refmeta.id}.mapped.bed
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -31,7 +31,7 @@ process BEDOPS_BEDMAP {
 
     stub:
     """
-    touch ${meta.id}.mapped.bed
+    touch ${meta.id}.${refmeta.id}.mapped.bed
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/tests/modules/CCBR/bedops/bedmap/main.nf b/tests/modules/CCBR/bedops/bedmap/main.nf
index f1f13d2..f04badd 100644
--- a/tests/modules/CCBR/bedops/bedmap/main.nf
+++ b/tests/modules/CCBR/bedops/bedmap/main.nf
@@ -23,10 +23,8 @@ workflow test_bedops_bedmap {
         .groupTuple() | CAT_CAT
     SORT_CAT(CAT_CAT.out.file_out, [])
     SORT_CAT.out.sorted | BEDTOOLS_MERGE
-    ref_bed = BEDTOOLS_MERGE.out.bed.map{ meta, bed -> bed }
 
     // map peaks to reference
     SORT_PEAK(ch_peaks, [])
-    SORT_PEAK.out.sorted | view
-    BEDOPS_BEDMAP( SORT_PEAK.out.sorted.combine(ref_bed) )
+    SORT_PEAK.out.sorted.combine(BEDTOOLS_MERGE.out.bed) | BEDOPS_BEDMAP
 }
diff --git a/tests/modules/CCBR/bedops/bedmap/test.yml b/tests/modules/CCBR/bedops/bedmap/test.yml
index 8e039b4..9965749 100644
--- a/tests/modules/CCBR/bedops/bedmap/test.yml
+++ b/tests/modules/CCBR/bedops/bedmap/test.yml
@@ -1,12 +1,12 @@
-- name: test_bedops_bedmap
+- name: bedops bedmap test_bedops_bedmap
   command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config
   tags:
-    - bedops/bedmap
     - bedops
+    - bedops/bedmap
   files:
-    - path: output/bedops_bedmap/SPT5_T0_1_peaks.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
       md5sum: a46e2f78e8534ecdc882fff22f0baa87
-    - path: output/bedops_bedmap/SPT5_T0_2_peaks.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.test.mapped.bed
       md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
     - path: output/bedops_bedmap/versions.yml
     - path: output/bedtools_merge/test.merged.bed
@@ -24,14 +24,14 @@
       md5sum: d3216918f24ced4b76b8eed6e38aa5c6
     - path: output/sort_peak/versions.yml
 
-- name: test_bedops_bedmap stub
+- name: bedops bedmap test_bedops_bedmap stub
   command: nextflow run ./tests/modules/CCBR/bedops/bedmap -entry test_bedops_bedmap -c ./tests/config/nextflow.config -stub
   tags:
-    - bedops/bedmap
     - bedops
+    - bedops/bedmap
   files:
-    - path: output/bedops_bedmap/SPT5_T0_1_peaks.mapped.bed
-    - path: output/bedops_bedmap/SPT5_T0_2_peaks.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.test.mapped.bed
     - path: output/bedops_bedmap/versions.yml
     - path: output/bedtools_merge/test.merged.bed
     - path: output/bedtools_merge/versions.yml

From e11988dbe754e1ddd208a988f2caf2f06f3dd05f Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 11:48:06 -0500
Subject: [PATCH 28/47] feat: create custom/combinepeaks module for consensus
 subwf

---
 modules/CCBR/custom/combinepeaks/main.nf      | 43 +++++++++++++++
 modules/CCBR/custom/combinepeaks/meta.yml     | 55 +++++++++++++++++++
 .../combinepeaks/templates/combine_peaks.R    | 28 ++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 .../modules/CCBR/custom/combinepeaks/main.nf  | 38 +++++++++++++
 .../CCBR/custom/combinepeaks/nextflow.config  |  7 +++
 .../modules/CCBR/custom/combinepeaks/test.yml |  0
 7 files changed, 175 insertions(+)
 create mode 100644 modules/CCBR/custom/combinepeaks/main.nf
 create mode 100644 modules/CCBR/custom/combinepeaks/meta.yml
 create mode 100644 modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
 create mode 100644 tests/modules/CCBR/custom/combinepeaks/main.nf
 create mode 100644 tests/modules/CCBR/custom/combinepeaks/nextflow.config
 create mode 100644 tests/modules/CCBR/custom/combinepeaks/test.yml

diff --git a/modules/CCBR/custom/combinepeaks/main.nf b/modules/CCBR/custom/combinepeaks/main.nf
new file mode 100644
index 0000000..a8c95bb
--- /dev/null
+++ b/modules/CCBR/custom/combinepeaks/main.nf
@@ -0,0 +1,43 @@
+process CUSTOM_COMBINEPEAKS {
+    """
+    A helper script for the consensus_peaks subworkflow
+    """
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/spacesavers2:0.1.1'
+
+    input:
+    tuple val(meta), path(peakcounts)
+
+    output:
+    tuple val(meta), path("*.consensus.bed"), emit: bed
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def outfile = "${prefix}.consensus.bed"
+    def count_files = peakcounts.join(' ')
+    """
+    template 'combine_peaks.R'
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        : \$(echo \$(R --version | grep 'R version' | sed 's/R version //; s/ (.*//'))
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.consensus.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        : \$(echo \$(R --version | grep 'R version' | sed 's/R version //; s/ (.*//'))
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/custom/combinepeaks/meta.yml b/modules/CCBR/custom/combinepeaks/meta.yml
new file mode 100644
index 0000000..3df21a4
--- /dev/null
+++ b/modules/CCBR/custom/combinepeaks/meta.yml
@@ -0,0 +1,55 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
+name: "custom_combinepeaks"
+## TODO nf-core: Add a description of the module and list keywords
+description: write your description here
+keywords:
+  - sort
+  - example
+  - genomics
+tools:
+  - "custom":
+      ## TODO nf-core: Add a description and other details for the software below
+      description: ""
+      homepage: ""
+      documentation: ""
+      tool_dev_url: ""
+      doi: ""
+      licence: ""
+
+## TODO nf-core: Add a description of all of the variables used as input
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  ## TODO nf-core: Delete / customise this example input
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  ## TODO nf-core: Delete / customise this example output
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
new file mode 100644
index 0000000..ae3e7fa
--- /dev/null
+++ b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
@@ -0,0 +1,28 @@
+library(dplyr)
+library(purrr)
+library(stringr)
+library(readr)
+library(tidyr)
+
+main <- function() {
+  dat <- combine_peaks(unlist(str_split("${count_files}", " ")))
+  write_tsv(dat, "${outfile}", col_names = FALSE)
+}
+
+combine_peaks <- function(count_files) {
+  count_dat <- count_files %>%
+    map(function(file) {
+      dat <- read_tsv(file, col_names = FALSE)
+      colnames(dat) <- c("peakID", "count")
+      return(dat %>% mutate(file = file))
+    }) %>%
+    list_rbind() %>%
+    group_by(peakID) %>%
+    summarize(score = sum(count) / length(count_files)) %>%
+    separate_wider_delim(peakID, ":", names = c("chrom", "coords"), cols_remove = FALSE) %>%
+    separate_wider_delim(coords, "-", names = c("start", "end")) %>%
+    mutate(strand = ".", signal = NA, pvalue = NA, qvalue = NA)
+  return(count_dat)
+}
+
+main()
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 1475144..21b2cf8 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -34,6 +34,10 @@ custom/bam2fastq:
   - modules/CCBR/custom/bam2fastq/**
   - tests/modules/CCBR/custom/bam2fastq/**
 
+custom/combinepeaks:
+  - modules/CCBR/custom/combinepeaks/**
+  - tests/modules/CCBR/custom/combinepeaks/**
+
 custom/consensuspeaks:
   - modules/CCBR/custom/consensuspeaks/**
   - tests/modules/CCBR/custom/consensuspeaks/**
diff --git a/tests/modules/CCBR/custom/combinepeaks/main.nf b/tests/modules/CCBR/custom/combinepeaks/main.nf
new file mode 100644
index 0000000..f40cebf
--- /dev/null
+++ b/tests/modules/CCBR/custom/combinepeaks/main.nf
@@ -0,0 +1,38 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_CAT                    } from '../../../../../modules/CCBR/cat/cat/main.nf'
+include { BEDOPS_BEDMAP              } from '../../../../../modules/CCBR/bedops/bedmap/main.nf'
+include { BEDTOOLS_SORT as SORT_CAT
+          BEDTOOLS_SORT as SORT_PEAK } from '../../../../../modules/CCBR/bedtools/sort/main.nf'
+include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
+include { CUSTOM_COMBINEPEAKS        } from '../../../../../modules/CCBR/custom/combinepeaks/main.nf'
+
+workflow test_custom_combinepeaks {
+
+    ch_peaks = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+                                 file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])
+        .map { peak ->
+            [ [id: peak.baseName, group: 'macs_broad'], peak ]
+        }
+    // prepare reference
+    ch_peaks
+        .map{ meta, peak ->
+            [ [id: 'test', group: 'macs_broad'], peak ]
+        }
+        .groupTuple() | CAT_CAT
+    SORT_CAT(CAT_CAT.out.file_out, [])
+    SORT_CAT.out.sorted | BEDTOOLS_MERGE
+
+    // map peaks to reference
+    SORT_PEAK(ch_peaks, [])
+    SORT_PEAK.out.sorted.combine(BEDTOOLS_MERGE.out.bed) | BEDOPS_BEDMAP
+
+    BEDOPS_BEDMAP.out.bed
+        .map { meta, bed ->
+            [ [id: meta.group], bed ]
+        }
+        .groupTuple() |
+        CUSTOM_COMBINEPEAKS
+}
diff --git a/tests/modules/CCBR/custom/combinepeaks/nextflow.config b/tests/modules/CCBR/custom/combinepeaks/nextflow.config
new file mode 100644
index 0000000..e942eb5
--- /dev/null
+++ b/tests/modules/CCBR/custom/combinepeaks/nextflow.config
@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].toLowerCase()}" }
+
+}
+
+includeConfig '../../../../config/test_data_CCBR.config'
diff --git a/tests/modules/CCBR/custom/combinepeaks/test.yml b/tests/modules/CCBR/custom/combinepeaks/test.yml
new file mode 100644
index 0000000..e69de29

From ed45eb8ba032d943a2071e230b8b8fdb7a6323c5 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 12:11:52 -0500
Subject: [PATCH 29/47] fix: template is nxf command, not bash

---
 modules/CCBR/custom/combinepeaks/main.nf | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/modules/CCBR/custom/combinepeaks/main.nf b/modules/CCBR/custom/combinepeaks/main.nf
index a8c95bb..391c207 100644
--- a/modules/CCBR/custom/combinepeaks/main.nf
+++ b/modules/CCBR/custom/combinepeaks/main.nf
@@ -21,9 +21,8 @@ process CUSTOM_COMBINEPEAKS {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def outfile = "${prefix}.consensus.bed"
     def count_files = peakcounts.join(' ')
-    """
     template 'combine_peaks.R'
-
+    """
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         : \$(echo \$(R --version | grep 'R version' | sed 's/R version //; s/ (.*//'))

From 09f789824136aa5c4cdb6537ae5217f8b6d1c13e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 12:37:35 -0500
Subject: [PATCH 30/47] fix: define vars for Rscript template

---
 modules/CCBR/custom/combinepeaks/main.nf             | 12 +++---------
 .../custom/combinepeaks/templates/combine_peaks.R    |  9 ++++++++-
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/modules/CCBR/custom/combinepeaks/main.nf b/modules/CCBR/custom/combinepeaks/main.nf
index 391c207..334688e 100644
--- a/modules/CCBR/custom/combinepeaks/main.nf
+++ b/modules/CCBR/custom/combinepeaks/main.nf
@@ -18,16 +18,10 @@ process CUSTOM_COMBINEPEAKS {
     task.ext.when == null || task.ext.when
 
     script:
-    def prefix = task.ext.prefix ?: "${meta.id}"
-    def outfile = "${prefix}.consensus.bed"
-    def count_files = peakcounts.join(' ')
+    prefix = task.ext.prefix ?: "${meta.id}"
+    outfile = "${prefix}.consensus.bed"
+    count_files = "${peakcounts.join(',')}"
     template 'combine_peaks.R'
-    """
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        : \$(echo \$(R --version | grep 'R version' | sed 's/R version //; s/ (.*//'))
-    END_VERSIONS
-    """
 
     stub:
     def prefix = task.ext.prefix ?: "${meta.id}"
diff --git a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
index ae3e7fa..c0b387e 100644
--- a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
+++ b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
@@ -1,3 +1,4 @@
+#!/usr/bin/env Rscript
 library(dplyr)
 library(purrr)
 library(stringr)
@@ -5,10 +6,16 @@ library(readr)
 library(tidyr)
 
 main <- function() {
-  dat <- combine_peaks(unlist(str_split("${count_files}", " ")))
+  write_lines(get_version(), "versions.yml")
+  print("${peakcounts}")
+  dat <- combine_peaks(unlist(str_split("${count_files}", ",")))
   write_tsv(dat, "${outfile}", col_names = FALSE)
 }
 
+get_version <- function() {
+  return(paste0(R.version[["major"]], ".", R.version[["minor"]]))
+}
+
 combine_peaks <- function(count_files) {
   count_dat <- count_files %>%
     map(function(file) {

From 9f5040ae8938b0cc838f9afd10c9f320fcdc1edb Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 12:51:35 -0500
Subject: [PATCH 31/47] feat: sort bed file to match original
 custom/consensuspeaks.py

---
 .../CCBR/custom/combinepeaks/templates/combine_peaks.R    | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
index c0b387e..8c23b96 100644
--- a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
+++ b/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
@@ -25,10 +25,14 @@ combine_peaks <- function(count_files) {
     }) %>%
     list_rbind() %>%
     group_by(peakID) %>%
-    summarize(score = sum(count) / length(count_files)) %>%
+    summarize(score = format(sum(count) / length(count_files), nsmall = 3)) %>%
     separate_wider_delim(peakID, ":", names = c("chrom", "coords"), cols_remove = FALSE) %>%
     separate_wider_delim(coords, "-", names = c("start", "end")) %>%
-    mutate(strand = ".", signal = NA, pvalue = NA, qvalue = NA)
+    mutate(
+      start = as.numeric(start), end = as.numeric(end),
+      strand = ".", signal = NA, pvalue = NA, qvalue = NA
+    ) %>%
+    arrange(chrom, start, end)
   return(count_dat)
 }
 

From 9639bb7878df2a70142a83d3d1bdfe066d58182e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 12:52:03 -0500
Subject: [PATCH 32/47] test: create test yml for custom/combinepeaks

---
 .../modules/CCBR/custom/combinepeaks/test.yml | 49 +++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/tests/modules/CCBR/custom/combinepeaks/test.yml b/tests/modules/CCBR/custom/combinepeaks/test.yml
index e69de29..62229de 100644
--- a/tests/modules/CCBR/custom/combinepeaks/test.yml
+++ b/tests/modules/CCBR/custom/combinepeaks/test.yml
@@ -0,0 +1,49 @@
+- name: custom combinepeaks test_custom_combinepeaks
+  command: nextflow run ./tests/modules/CCBR/custom/combinepeaks -entry test_custom_combinepeaks -c ./tests/config/nextflow.config
+  tags:
+    - custom
+    - custom/combinepeaks
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
+      md5sum: a46e2f78e8534ecdc882fff22f0baa87
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.test.mapped.bed
+      md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/test.merged.bed
+      md5sum: d67c8c15b99b310ec5aa0ec363dcd147
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/test.broadPeak
+      md5sum: c5d73e727a10d2a32b139efcdd369f59
+    - path: output/cat_cat/versions.yml
+    - path: output/custom_combinepeaks/macs_broad.consensus.bed
+      md5sum: 600f5c2dfeae440ada8c412c153a677e
+    - path: output/custom_combinepeaks/versions.yml
+    - path: output/sort_cat/test.sorted.broadPeak
+      md5sum: b412285368f1698634177087e7ea4103
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+      md5sum: 03b87e9021f85db1c8e07f5c0b4d7347
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+      md5sum: d3216918f24ced4b76b8eed6e38aa5c6
+    - path: output/sort_peak/versions.yml
+
+- name: custom combinepeaks test_custom_combinepeaks stub
+  command: nextflow run ./tests/modules/CCBR/custom/combinepeaks -entry test_custom_combinepeaks -c ./tests/config/nextflow.config -stub
+  tags:
+    - custom
+    - custom/combinepeaks
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.test.mapped.bed
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/test.merged.bed
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/test.broadPeak
+    - path: output/cat_cat/versions.yml
+    - path: output/custom_combinepeaks/macs_broad.consensus.bed
+    - path: output/custom_combinepeaks/versions.yml
+    - path: output/sort_cat/test.sorted.broadPeak
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+    - path: output/sort_peak/versions.yml

From 1d65a57f0f41b3af3d5beb5a4af6a631848448cf Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 13:09:23 -0500
Subject: [PATCH 33/47] refactor: rename 'combinepeaks' -> 'combinepeakcounts'

---
 CHANGELOG.md                                  |  1 +
 .../main.nf                                   |  6 +++---
 .../meta.yml                                  |  2 +-
 .../templates/combine_peaks.R                 |  9 ++++++++-
 tests/config/pytest_modules.yml               |  6 +++---
 .../main.nf                                   |  4 ++--
 .../nextflow.config                           |  0
 .../test.yml                                  | 20 +++++++++----------
 8 files changed, 28 insertions(+), 20 deletions(-)
 rename modules/CCBR/custom/{combinepeaks => combinepeakcounts}/main.nf (87%)
 rename modules/CCBR/custom/{combinepeaks => combinepeakcounts}/meta.yml (97%)
 rename modules/CCBR/custom/{combinepeaks => combinepeakcounts}/templates/combine_peaks.R (91%)
 rename tests/modules/CCBR/custom/{combinepeaks => combinepeakcounts}/main.nf (90%)
 rename tests/modules/CCBR/custom/{combinepeaks => combinepeakcounts}/nextflow.config (100%)
 rename tests/modules/CCBR/custom/{combinepeaks => combinepeakcounts}/test.yml (69%)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index af92ebf..9f1a943 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,7 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 - cat/cat (#37)
 - cat/fastq (#37)
 - custom/bam2fastq (#14,#22)
+- custom/combinepeakcounts (#37)
 - custom/consensuspeaks (#37)
 - custom/convertsicer (#36)
 - custom/countfastq (#32)
diff --git a/modules/CCBR/custom/combinepeaks/main.nf b/modules/CCBR/custom/combinepeakcounts/main.nf
similarity index 87%
rename from modules/CCBR/custom/combinepeaks/main.nf
rename to modules/CCBR/custom/combinepeakcounts/main.nf
index 334688e..24fd80f 100644
--- a/modules/CCBR/custom/combinepeaks/main.nf
+++ b/modules/CCBR/custom/combinepeakcounts/main.nf
@@ -1,4 +1,4 @@
-process CUSTOM_COMBINEPEAKS {
+process CUSTOM_COMBINEPEAKCOUNTS {
     """
     A helper script for the consensus_peaks subworkflow
     """
@@ -8,7 +8,7 @@ process CUSTOM_COMBINEPEAKS {
     container 'nciccbr/spacesavers2:0.1.1'
 
     input:
-    tuple val(meta), path(peakcounts)
+    tuple val(meta), path(counts)
 
     output:
     tuple val(meta), path("*.consensus.bed"), emit: bed
@@ -20,7 +20,7 @@ process CUSTOM_COMBINEPEAKS {
     script:
     prefix = task.ext.prefix ?: "${meta.id}"
     outfile = "${prefix}.consensus.bed"
-    count_files = "${peakcounts.join(',')}"
+    count_files = "${counts.join(',')}"
     template 'combine_peaks.R'
 
     stub:
diff --git a/modules/CCBR/custom/combinepeaks/meta.yml b/modules/CCBR/custom/combinepeakcounts/meta.yml
similarity index 97%
rename from modules/CCBR/custom/combinepeaks/meta.yml
rename to modules/CCBR/custom/combinepeakcounts/meta.yml
index 3df21a4..4f870a5 100644
--- a/modules/CCBR/custom/combinepeaks/meta.yml
+++ b/modules/CCBR/custom/combinepeakcounts/meta.yml
@@ -1,6 +1,6 @@
 ---
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
-name: "custom_combinepeaks"
+name: "custom_combinepeakcounts"
 ## TODO nf-core: Add a description of the module and list keywords
 description: write your description here
 keywords:
diff --git a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R b/modules/CCBR/custom/combinepeakcounts/templates/combine_peaks.R
similarity index 91%
rename from modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
rename to modules/CCBR/custom/combinepeakcounts/templates/combine_peaks.R
index 8c23b96..657c6ef 100644
--- a/modules/CCBR/custom/combinepeaks/templates/combine_peaks.R
+++ b/modules/CCBR/custom/combinepeakcounts/templates/combine_peaks.R
@@ -7,7 +7,6 @@ library(tidyr)
 
 main <- function() {
   write_lines(get_version(), "versions.yml")
-  print("${peakcounts}")
   dat <- combine_peaks(unlist(str_split("${count_files}", ",")))
   write_tsv(dat, "${outfile}", col_names = FALSE)
 }
@@ -36,4 +35,12 @@ combine_peaks <- function(count_files) {
   return(count_dat)
 }
 
+join_peaks <- function(peakfiles) {
+  return()
+}
+
+normalize_scores <- function(dat) {
+  return()
+}
+
 main()
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 21b2cf8..ee29009 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -34,9 +34,9 @@ custom/bam2fastq:
   - modules/CCBR/custom/bam2fastq/**
   - tests/modules/CCBR/custom/bam2fastq/**
 
-custom/combinepeaks:
-  - modules/CCBR/custom/combinepeaks/**
-  - tests/modules/CCBR/custom/combinepeaks/**
+custom/combinepeakcounts:
+  - modules/CCBR/custom/combinepeakcounts/**
+  - tests/modules/CCBR/custom/combinepeakcounts/**
 
 custom/consensuspeaks:
   - modules/CCBR/custom/consensuspeaks/**
diff --git a/tests/modules/CCBR/custom/combinepeaks/main.nf b/tests/modules/CCBR/custom/combinepeakcounts/main.nf
similarity index 90%
rename from tests/modules/CCBR/custom/combinepeaks/main.nf
rename to tests/modules/CCBR/custom/combinepeakcounts/main.nf
index f40cebf..51a536f 100644
--- a/tests/modules/CCBR/custom/combinepeaks/main.nf
+++ b/tests/modules/CCBR/custom/combinepeakcounts/main.nf
@@ -7,7 +7,7 @@ include { BEDOPS_BEDMAP              } from '../../../../../modules/CCBR/bedops/
 include { BEDTOOLS_SORT as SORT_CAT
           BEDTOOLS_SORT as SORT_PEAK } from '../../../../../modules/CCBR/bedtools/sort/main.nf'
 include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
-include { CUSTOM_COMBINEPEAKS        } from '../../../../../modules/CCBR/custom/combinepeaks/main.nf'
+include { CUSTOM_COMBINEPEAKCOUNTS        } from '../../../../../modules/CCBR/custom/combinepeakcounts/main.nf'
 
 workflow test_custom_combinepeaks {
 
@@ -34,5 +34,5 @@ workflow test_custom_combinepeaks {
             [ [id: meta.group], bed ]
         }
         .groupTuple() |
-        CUSTOM_COMBINEPEAKS
+        CUSTOM_COMBINEPEAKCOUNTS
 }
diff --git a/tests/modules/CCBR/custom/combinepeaks/nextflow.config b/tests/modules/CCBR/custom/combinepeakcounts/nextflow.config
similarity index 100%
rename from tests/modules/CCBR/custom/combinepeaks/nextflow.config
rename to tests/modules/CCBR/custom/combinepeakcounts/nextflow.config
diff --git a/tests/modules/CCBR/custom/combinepeaks/test.yml b/tests/modules/CCBR/custom/combinepeakcounts/test.yml
similarity index 69%
rename from tests/modules/CCBR/custom/combinepeaks/test.yml
rename to tests/modules/CCBR/custom/combinepeakcounts/test.yml
index 62229de..3951d29 100644
--- a/tests/modules/CCBR/custom/combinepeaks/test.yml
+++ b/tests/modules/CCBR/custom/combinepeakcounts/test.yml
@@ -1,8 +1,8 @@
-- name: custom combinepeaks test_custom_combinepeaks
-  command: nextflow run ./tests/modules/CCBR/custom/combinepeaks -entry test_custom_combinepeaks -c ./tests/config/nextflow.config
+- name: custom combinepeakcounts test_custom_combinepeakcounts
+  command: nextflow run ./tests/modules/CCBR/custom/combinepeakcounts -entry test_custom_combinepeakcounts -c ./tests/config/nextflow.config
   tags:
     - custom
-    - custom/combinepeaks
+    - custom/combinepeakcounts
   files:
     - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
       md5sum: a46e2f78e8534ecdc882fff22f0baa87
@@ -15,9 +15,9 @@
     - path: output/cat_cat/test.broadPeak
       md5sum: c5d73e727a10d2a32b139efcdd369f59
     - path: output/cat_cat/versions.yml
-    - path: output/custom_combinepeaks/macs_broad.consensus.bed
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
       md5sum: 600f5c2dfeae440ada8c412c153a677e
-    - path: output/custom_combinepeaks/versions.yml
+    - path: output/custom_combinepeakcounts/versions.yml
     - path: output/sort_cat/test.sorted.broadPeak
       md5sum: b412285368f1698634177087e7ea4103
     - path: output/sort_cat/versions.yml
@@ -27,11 +27,11 @@
       md5sum: d3216918f24ced4b76b8eed6e38aa5c6
     - path: output/sort_peak/versions.yml
 
-- name: custom combinepeaks test_custom_combinepeaks stub
-  command: nextflow run ./tests/modules/CCBR/custom/combinepeaks -entry test_custom_combinepeaks -c ./tests/config/nextflow.config -stub
+- name: custom combinepeakcounts test_custom_combinepeakcounts stub
+  command: nextflow run ./tests/modules/CCBR/custom/combinepeakcounts -entry test_custom_combinepeakcounts -c ./tests/config/nextflow.config -stub
   tags:
     - custom
-    - custom/combinepeaks
+    - custom/combinepeakcounts
   files:
     - path: output/bedops_bedmap/SPT5_T0_1_peaks.test.mapped.bed
     - path: output/bedops_bedmap/SPT5_T0_2_peaks.test.mapped.bed
@@ -40,8 +40,8 @@
     - path: output/bedtools_merge/versions.yml
     - path: output/cat_cat/test.broadPeak
     - path: output/cat_cat/versions.yml
-    - path: output/custom_combinepeaks/macs_broad.consensus.bed
-    - path: output/custom_combinepeaks/versions.yml
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
+    - path: output/custom_combinepeakcounts/versions.yml
     - path: output/sort_cat/test.sorted.broadPeak
     - path: output/sort_cat/versions.yml
     - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak

From 2b5f3f7d0fb9d3986376d566bbf6f2eb2c9a818d Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:44:17 -0500
Subject: [PATCH 34/47] feat: create module to normalize consensus peaks

---
 modules/CCBR/custom/normalizepeaks/main.nf    | 34 ++++++++++
 modules/CCBR/custom/normalizepeaks/meta.yml   | 50 +++++++++++++++
 .../templates/normalize_peaks.R               | 64 +++++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 .../CCBR/custom/normalizepeaks/main.nf        | 51 +++++++++++++++
 .../custom/normalizepeaks/nextflow.config     |  6 ++
 .../CCBR/custom/normalizepeaks/test.yml       | 54 ++++++++++++++++
 7 files changed, 263 insertions(+)
 create mode 100644 modules/CCBR/custom/normalizepeaks/main.nf
 create mode 100644 modules/CCBR/custom/normalizepeaks/meta.yml
 create mode 100644 modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
 create mode 100644 tests/modules/CCBR/custom/normalizepeaks/main.nf
 create mode 100644 tests/modules/CCBR/custom/normalizepeaks/nextflow.config
 create mode 100644 tests/modules/CCBR/custom/normalizepeaks/test.yml

diff --git a/modules/CCBR/custom/normalizepeaks/main.nf b/modules/CCBR/custom/normalizepeaks/main.nf
new file mode 100644
index 0000000..3ce9693
--- /dev/null
+++ b/modules/CCBR/custom/normalizepeaks/main.nf
@@ -0,0 +1,34 @@
+process CUSTOM_NORMALIZEPEAKS {
+    """
+    Normalize p-values and q-values for consensus peaks
+    """
+    tag { meta.id }
+    label 'process_single'
+
+    container 'nciccbr/spacesavers2:0.1.1'
+
+    input:
+    tuple val(meta), path(count), path(peaks)
+
+    output:
+    tuple val(meta), path("*norm.bed"), emit: bed
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    outfile = "${count.baseName}.norm.bed"
+    template 'normalize_peaks.R'
+
+    stub:
+    """
+    touch ${count.baseName}.norm.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        : \$(echo \$(R --version | grep 'R version' | sed 's/R version //; s/ (.*//'))
+    END_VERSIONS
+    """
+}
diff --git a/modules/CCBR/custom/normalizepeaks/meta.yml b/modules/CCBR/custom/normalizepeaks/meta.yml
new file mode 100644
index 0000000..65b1aab
--- /dev/null
+++ b/modules/CCBR/custom/normalizepeaks/meta.yml
@@ -0,0 +1,50 @@
+---
+name: "custom_normalizepeaks"
+description: normalize p-values and q-values of consensus peaks with the method from Corces et al. (https://doi.org/10.1126/science.aav1898)
+keywords:
+  - chipseq
+  - peaks
+  - consensus
+  - normalization
+tools:
+  - "R":
+      description: "R is a free software environment for statistical computing and graphics"
+      homepage: "https://www.r-project.org/"
+      licence: "GPL-3"
+
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+  - count:
+      type: file
+      description: consensus peak file from custom/combinepeakcounts
+      pattern: "*.bed"
+  - peaks:
+      type: file
+      description: merged and sorted peak file
+      pattern: "*.bed"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+  - peaks:
+      type: file
+      description: |
+        consensus peak file with normalized p-values and q-values
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
new file mode 100644
index 0000000..a651f0e
--- /dev/null
+++ b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
@@ -0,0 +1,64 @@
+#!/usr/bin/env Rscript
+library(dplyr)
+library(glue)
+library(purrr)
+library(stringr)
+library(readr)
+library(tidyr)
+
+main <- function() {
+  write_lines(get_version(), "versions.yml")
+  count_dat <- read_peaks("${count}")
+  peak_dat <- read_peaks("${peaks}") %>%
+    mutate(peakID = glue("{chrom}:{start}-{end}")) %>%
+    normalize() %>%
+    select(peakID, pvalue, qvalue)
+  count_dat %>%
+    select(-c(pvalue, qvalue)) %>%
+    left_join(peak_dat, by = "peakID") %>%
+    write_tsv("${outfile}", col_names = FALSE)
+}
+
+get_version <- function() {
+  return(paste0(R.version[["major"]], ".", R.version[["minor"]]))
+}
+
+read_peaks <- function(peak_file) {
+  peak_colnames <- c(
+    "chrom",
+    "start",
+    "end",
+    "peakID",
+    "score",
+    "strand",
+    "signal",
+    "pvalue",
+    "qvalue",
+    "peak"
+  )
+  peaks <- read_tsv(peak_file, col_names = FALSE)
+  colnames(peaks) <- peak_colnames[seq_len(ncol(peaks))]
+  return(peaks)
+}
+
+normalize <- function(peak_dat, norm_method = corces) {
+  return(
+    peak_dat %>%
+      group_by(peakID) %>%
+      mutate(
+        pvalue_norm = norm_method(pvalue),
+        qvalue_norm = 10^(-pvalue_norm) %>% p.adjust(method = "BH") %>% -log10(.)
+      ) %>%
+      slice_max(pvalue_norm) %>%
+      select(-c(pvalue, qvalue)) %>%
+      rename(pvalue = pvalue_norm, qvalue = qvalue_norm)
+  )
+}
+
+#' Normalize consensus peak values with the method from Corces et al.
+#' https://doi.org/10.1126/science.aav1898
+corces <- function(x) {
+  return(x / sum(x) / 10^6)
+}
+
+main()
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index ee29009..0010849 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -50,6 +50,10 @@ custom/countfastq:
   - modules/CCBR/custom/countfastq/**
   - tests/modules/CCBR/custom/countfastq/**
 
+custom/normalizepeaks:
+  - modules/CCBR/custom/normalizepeaks/**
+  - tests/modules/CCBR/custom/normalizepeaks/**
+
 cutadapt:
   - modules/CCBR/cutadapt/**
   - tests/modules/CCBR/cutadapt/**
diff --git a/tests/modules/CCBR/custom/normalizepeaks/main.nf b/tests/modules/CCBR/custom/normalizepeaks/main.nf
new file mode 100644
index 0000000..c2f0ec2
--- /dev/null
+++ b/tests/modules/CCBR/custom/normalizepeaks/main.nf
@@ -0,0 +1,51 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { CAT_CAT                    } from '../../../../../modules/CCBR/cat/cat/main.nf'
+include { BEDOPS_BEDMAP              } from '../../../../../modules/CCBR/bedops/bedmap/main.nf'
+include { BEDTOOLS_SORT as SORT_CAT
+          BEDTOOLS_SORT as SORT_PEAK } from '../../../../../modules/CCBR/bedtools/sort/main.nf'
+include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
+include { CUSTOM_COMBINEPEAKCOUNTS   } from '../../../../../modules/CCBR/custom/combinepeakcounts/main.nf'
+include { CUSTOM_NORMALIZEPEAKS      } from '../../../../../modules/CCBR/custom/normalizepeaks/main.nf'
+
+workflow test_custom_normalizepeaks {
+
+    ch_peaks = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+                                 file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])
+        .map { peak ->
+            [ [id: peak.baseName, group: 'macs_broad'], peak ]
+        }
+    // prepare reference
+    peaks_grouped = ch_peaks
+            .map{ meta, peak ->
+                [ [id: meta.group], peak ]
+            }
+            .groupTuple()
+        peaks_grouped | CAT_CAT
+    SORT_CAT(CAT_CAT.out.file_out, [])
+    SORT_CAT.out.sorted | BEDTOOLS_MERGE
+
+    // map peaks to reference
+    SORT_PEAK(ch_peaks, [])
+    SORT_PEAK.out.sorted.combine(BEDTOOLS_MERGE.out.bed) | BEDOPS_BEDMAP
+
+    counts_grouped = BEDOPS_BEDMAP.out.bed
+            .map { meta, bed ->
+                [ [id: meta.group], bed ]
+            }
+            .groupTuple()
+    counts_grouped | CUSTOM_COMBINEPEAKCOUNTS
+
+    ch_count_peak = CUSTOM_COMBINEPEAKCOUNTS.out.bed
+        .cross(SORT_CAT.out.sorted)
+        .map{ it ->
+            it.flatten()
+        }
+        .map{ meta1, count, meta2, peak ->
+            assert meta1.id == meta2.id
+            [ meta1, count, peak ]
+        }
+    ch_count_peak | CUSTOM_NORMALIZEPEAKS
+}
diff --git a/tests/modules/CCBR/custom/normalizepeaks/nextflow.config b/tests/modules/CCBR/custom/normalizepeaks/nextflow.config
new file mode 100644
index 0000000..f6762c2
--- /dev/null
+++ b/tests/modules/CCBR/custom/normalizepeaks/nextflow.config
@@ -0,0 +1,6 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].toLowerCase()}" }
+
+}
+includeConfig '../../../../config/test_data_CCBR.config'
diff --git a/tests/modules/CCBR/custom/normalizepeaks/test.yml b/tests/modules/CCBR/custom/normalizepeaks/test.yml
new file mode 100644
index 0000000..771d859
--- /dev/null
+++ b/tests/modules/CCBR/custom/normalizepeaks/test.yml
@@ -0,0 +1,54 @@
+- name: custom normalizepeaks test_custom_normalizepeaks
+  command: nextflow run ./tests/modules/CCBR/custom/normalizepeaks -entry test_custom_normalizepeaks -c ./tests/config/nextflow.config
+  tags:
+    - custom/normalizepeaks
+    - custom
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.macs_broad.mapped.bed
+      md5sum: a46e2f78e8534ecdc882fff22f0baa87
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.macs_broad.mapped.bed
+      md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/macs_broad.merged.bed
+      md5sum: d67c8c15b99b310ec5aa0ec363dcd147
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/macs_broad.broadPeak
+      md5sum: c5d73e727a10d2a32b139efcdd369f59
+    - path: output/cat_cat/versions.yml
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
+      md5sum: 600f5c2dfeae440ada8c412c153a677e
+    - path: output/custom_combinepeakcounts/versions.yml
+    - path: output/custom_normalizepeaks/macs_broad.consensus.norm.bed
+      md5sum: 91162a273adbde73bec3dfd0d87c16fd
+    - path: output/custom_normalizepeaks/versions.yml
+    - path: output/sort_cat/macs_broad.sorted.broadPeak
+      md5sum: b412285368f1698634177087e7ea4103
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+      md5sum: 03b87e9021f85db1c8e07f5c0b4d7347
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+      md5sum: d3216918f24ced4b76b8eed6e38aa5c6
+    - path: output/sort_peak/versions.yml
+
+- name: custom normalizepeaks test_custom_normalizepeaks stub
+  command: nextflow run ./tests/modules/CCBR/custom/normalizepeaks -entry test_custom_normalizepeaks -c ./tests/config/nextflow.config -stub
+  tags:
+    - custom/normalizepeaks
+    - custom
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.macs_broad.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.macs_broad.mapped.bed
+    - path: output/bedops_bedmap/versions.yml
+    - path: output/bedtools_merge/macs_broad.merged.bed
+    - path: output/bedtools_merge/versions.yml
+    - path: output/cat_cat/macs_broad.broadPeak
+    - path: output/cat_cat/versions.yml
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
+    - path: output/custom_combinepeakcounts/versions.yml
+    - path: output/custom_normalizepeaks/macs_broad.consensus.norm.bed
+    - path: output/custom_normalizepeaks/versions.yml
+    - path: output/sort_cat/macs_broad.sorted.broadPeak
+    - path: output/sort_cat/versions.yml
+    - path: output/sort_peak/SPT5_T0_1_peaks.sorted.broadPeak
+    - path: output/sort_peak/SPT5_T0_2_peaks.sorted.broadPeak
+    - path: output/sort_peak/versions.yml

From 097db63978e11213a5bd7600881ae33baa907cd6 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:47:37 -0500
Subject: [PATCH 35/47] refactor: set nxf variables as defaults

---
 .../normalizepeaks/templates/normalize_peaks.R       | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
index a651f0e..c0a6c0c 100644
--- a/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
+++ b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
@@ -6,17 +6,17 @@ library(stringr)
 library(readr)
 library(tidyr)
 
-main <- function() {
-  write_lines(get_version(), "versions.yml")
-  count_dat <- read_peaks("${count}")
-  peak_dat <- read_peaks("${peaks}") %>%
+main <- function(versionfile = "versions.yml", counfile = "${count}", peakfile = "${peaks}", outfile = "${outfile}") {
+  write_lines(get_version(), versionfile)
+  count_dat <- read_peaks(countfile)
+  peak_dat <- read_peaks(peakfile) %>%
     mutate(peakID = glue("{chrom}:{start}-{end}")) %>%
     normalize() %>%
     select(peakID, pvalue, qvalue)
   count_dat %>%
     select(-c(pvalue, qvalue)) %>%
     left_join(peak_dat, by = "peakID") %>%
-    write_tsv("${outfile}", col_names = FALSE)
+    write_tsv(outfile, col_names = FALSE)
 }
 
 get_version <- function() {
@@ -61,4 +61,4 @@ corces <- function(x) {
   return(x / sum(x) / 10^6)
 }
 
-main()
+main("versions.yml", "${count}", "${peaks}", "${outfile}")

From 01f7c4d7e64e749145f41d637bb74b70c140be4e Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:50:37 -0500
Subject: [PATCH 36/47] docs: update metadata for peak-related modules

---
 .../CCBR/custom/combinepeakcounts/meta.yml    | 44 ++++++++-----------
 modules/CCBR/custom/normalizepeaks/meta.yml   |  2 +-
 2 files changed, 19 insertions(+), 27 deletions(-)

diff --git a/modules/CCBR/custom/combinepeakcounts/meta.yml b/modules/CCBR/custom/combinepeakcounts/meta.yml
index 4f870a5..e9f8576 100644
--- a/modules/CCBR/custom/combinepeakcounts/meta.yml
+++ b/modules/CCBR/custom/combinepeakcounts/meta.yml
@@ -1,23 +1,16 @@
 ---
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
 name: "custom_combinepeakcounts"
-## TODO nf-core: Add a description of the module and list keywords
-description: write your description here
+description: combine counts into consensus peaks
 keywords:
-  - sort
-  - example
-  - genomics
+  - chipseq
+  - peaks
+  - consensus
 tools:
-  - "custom":
-      ## TODO nf-core: Add a description and other details for the software below
-      description: ""
-      homepage: ""
-      documentation: ""
-      tool_dev_url: ""
-      doi: ""
-      licence: ""
+  - "R":
+      description: "R is a free software environment for statistical computing and graphics"
+      homepage: "https://www.r-project.org/"
+      licence: "GPL-3"
 
-## TODO nf-core: Add a description of all of the variables used as input
 input:
   # Only when we have meta
   - meta:
@@ -26,30 +19,29 @@ input:
         Groovy Map containing sample information
         e.g. `[ id:'test', single_end:false ]`
 
-  ## TODO nf-core: Delete / customise this example input
-  - bam:
+  - counts:
       type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+      description: peak file from bedtools/bedmap
+      pattern: "*.bed"
 
-## TODO nf-core: Add a description of all of the variables used as output
 output:
-  #Only when we have meta
   - meta:
       type: map
       description: |
         Groovy Map containing sample information
         e.g. `[ id:'test', single_end:false ]`
 
+  - bed:
+      type: file
+      description: |
+        consensus peak file
+
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  ## TODO nf-core: Delete / customise this example output
-  - bam:
-      type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
 
 authors:
   - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/modules/CCBR/custom/normalizepeaks/meta.yml b/modules/CCBR/custom/normalizepeaks/meta.yml
index 65b1aab..aea2b2c 100644
--- a/modules/CCBR/custom/normalizepeaks/meta.yml
+++ b/modules/CCBR/custom/normalizepeaks/meta.yml
@@ -34,7 +34,7 @@ output:
       description: |
         Groovy Map containing sample information
         e.g. `[ id:'test', single_end:false ]`
-  - peaks:
+  - bed:
       type: file
       description: |
         consensus peak file with normalized p-values and q-values

From 3e97ce24af9a98b09bc8095360381a111f6d19b4 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:53:53 -0500
Subject: [PATCH 37/47] docs: fix typo

---
 modules/CCBR/custom/combinepeakcounts/meta.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/CCBR/custom/combinepeakcounts/meta.yml b/modules/CCBR/custom/combinepeakcounts/meta.yml
index e9f8576..8990f07 100644
--- a/modules/CCBR/custom/combinepeakcounts/meta.yml
+++ b/modules/CCBR/custom/combinepeakcounts/meta.yml
@@ -21,7 +21,7 @@ input:
 
   - counts:
       type: file
-      description: peak file from bedtools/bedmap
+      description: peak file from bedops/bedmap
       pattern: "*.bed"
 
 output:

From 80f9ac2ebff9df9c9ace2413f855991f039ab7ee Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:55:11 -0500
Subject: [PATCH 38/47] feat: create consensus_peaks subwf

a replacement for the custom/consensuspeaks module
---
 subworkflows/CCBR/consensus_peaks/main.nf     | 58 +++++++++++++++++++
 subworkflows/CCBR/consensus_peaks/meta.yml    | 48 +++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 .../subworkflows/CCBR/consensus_peaks/main.nf | 19 ++++++
 .../CCBR/consensus_peaks/nextflow.config      |  7 +++
 .../CCBR/consensus_peaks/test.yml             |  0
 6 files changed, 136 insertions(+)
 create mode 100644 subworkflows/CCBR/consensus_peaks/main.nf
 create mode 100644 subworkflows/CCBR/consensus_peaks/meta.yml
 create mode 100644 tests/subworkflows/CCBR/consensus_peaks/main.nf
 create mode 100644 tests/subworkflows/CCBR/consensus_peaks/nextflow.config
 create mode 100644 tests/subworkflows/CCBR/consensus_peaks/test.yml

diff --git a/subworkflows/CCBR/consensus_peaks/main.nf b/subworkflows/CCBR/consensus_peaks/main.nf
new file mode 100644
index 0000000..f501931
--- /dev/null
+++ b/subworkflows/CCBR/consensus_peaks/main.nf
@@ -0,0 +1,58 @@
+include { CAT_CAT        } from '../../../modules/CCBR/cat/cat/'
+include { BEDTOOLS_SORT  } from '../../../modules/CCBR/bedtools/sort/' // TODO use unix sort for better performance
+include { BEDTOOLS_MERGE } from '../../../modules/CCBR/bedtools/merge/'
+include { BEDOPS_BEDMAP  } from '../../../modules/CCBR/bedops/bedmap/'
+include { CUSTOM_COMBINEPEAKCOUNTS  } from '../../../modules/CCBR/custom/combinepeakcounts/'
+include { CUSTOM_NORMALIZEPEAKS     } from '../../../modules/CCBR/custom/normalizepeaks/'
+
+workflow CONSENSUS_PEAKS {
+
+    take:
+        // channel: [ val(meta), peak ]
+        // meta should contain a group variable by which the peaks will be grouped
+        // peaks should already be sorted by chromosome name then by start pos
+        ch_peaks
+        // whether to normalize p-values and q-values
+        normalize
+
+    main:
+
+        ch_versions = Channel.empty()
+
+        peaks_grouped = ch_peaks
+            .map{ meta, peak ->
+                [ [id: meta.group], peak ]
+            }
+            .groupTuple()
+        peaks_grouped | CAT_CAT
+        BEDTOOLS_SORT( CAT_CAT.out.file_out, [] )
+        peaks_cat_sorted = BEDTOOLS_SORT.out.sorted
+        peaks_cat_sorted | BEDTOOLS_MERGE
+        ch_peaks.combine(BEDTOOLS_MERGE.out.bed) | BEDOPS_BEDMAP
+
+        counts_grouped = BEDOPS_BEDMAP.out.bed
+            .map { meta, bed ->
+                [ [id: meta.group], bed ]
+            }
+            .groupTuple()
+        counts_grouped | CUSTOM_COMBINEPEAKCOUNTS
+        consensus_peaks = CUSTOM_COMBINEPEAKCOUNTS.out.bed
+
+        if (normalize) {
+            ch_count_peak = CUSTOM_COMBINEPEAKCOUNTS.out.bed
+                .cross(peaks_cat_sorted)
+                .map{ it ->
+                    it.flatten()
+                }
+                .map{ meta1, count, meta2, peak ->
+                    assert meta1.id == meta2.id
+                    [ meta1, count, peak ]
+                }
+            ch_count_peak | CUSTOM_NORMALIZEPEAKS
+            consensus_peaks = CUSTOM_NORMALIZEPEAKS.out.bed
+        }
+
+    emit:
+        peaks    = consensus_peaks
+        versions = ch_versions
+}
diff --git a/subworkflows/CCBR/consensus_peaks/meta.yml b/subworkflows/CCBR/consensus_peaks/meta.yml
new file mode 100644
index 0000000..4cfe660
--- /dev/null
+++ b/subworkflows/CCBR/consensus_peaks/meta.yml
@@ -0,0 +1,48 @@
+name: "consensus_peaks"
+description: |
+  Find consensus peaks from peak files, and optionally perform normalization.
+  This is an alternative to the custom/consensuspeaks module.
+keywords:
+  - peaks
+  - chipseq
+  - normalization
+  - consensus
+components:
+  - bedtools/sort
+  - bedtools/merge
+  - bedops/bedmap
+  - cat/cat
+  - custom/combinepeakcounts
+  - custom/normalizepeaks
+input:
+  - ch_peaks:
+      type: file
+      description: |
+        The input channel containing the peak files.
+        Structure: [ val(meta), path(peak) ].
+        Meta must contain a `group` variable by which the peaks will be grouped for consensus calling.
+      pattern: "*.{bed/narrowPeak/broadPeak}"
+  - normalize:
+      type: boolean
+      description: |
+        Whether to normalize p-values and q-values for consensus peaks.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'test', single_end:false ]`
+  - peaks:
+      type: file
+      description: A single consensus peak file for each meta.group
+      pattern: "*.{broadPeak,narrowPeak,bed}"
+  - versions:
+      type: file
+      description: |
+        File containing software versions
+        Structure: [ path(versions.yml) ]
+      pattern: "versions.yml"
+authors:
+  - "@kelly-sovacool"
+maintainers:
+  - "@kelly-sovacool"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 0010849..7a2669c 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -70,6 +70,10 @@ samtools/filteraligned:
   - modules/CCBR/samtools/filteraligned/**
   - tests/modules/CCBR/samtools/filteraligned/**
 
+subworkflows/consensus_peaks:
+  - subworkflows/CCBR/consensus_peaks/**
+  - tests/subworkflows/CCBR/consensus_peaks/**
+
 subworkflows/filter_blacklist:
   - subworkflows/CCBR/filter_blacklist/**
   - tests/subworkflows/CCBR/filter_blacklist/**
diff --git a/tests/subworkflows/CCBR/consensus_peaks/main.nf b/tests/subworkflows/CCBR/consensus_peaks/main.nf
new file mode 100644
index 0000000..0d7329e
--- /dev/null
+++ b/tests/subworkflows/CCBR/consensus_peaks/main.nf
@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { BEDTOOLS_SORT  } from '../../../modules/CCBR/bedtools/sort/'
+include { CONSENSUS_PEAKS } from '../../../../subworkflows/CCBR/consensus_peaks'
+
+workflow test_consensus_peaks_broad {
+
+    input = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+                              file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])
+        .map { peak ->
+            [ [id: peak.baseName, group: 'macs_broad'], peak ]
+        }
+    BEDTOOLS_SORT(input, [])
+    peaks = BEDTOOLS_SORT.out.sorted
+
+    CONSENSUS_PEAKS( peaks, false )
+}
diff --git a/tests/subworkflows/CCBR/consensus_peaks/nextflow.config b/tests/subworkflows/CCBR/consensus_peaks/nextflow.config
new file mode 100644
index 0000000..ca7a499
--- /dev/null
+++ b/tests/subworkflows/CCBR/consensus_peaks/nextflow.config
@@ -0,0 +1,7 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].toLowerCase()}" }
+
+}
+
+includeConfig '../../../config/test_data_CCBR.config'
diff --git a/tests/subworkflows/CCBR/consensus_peaks/test.yml b/tests/subworkflows/CCBR/consensus_peaks/test.yml
new file mode 100644
index 0000000..e69de29

From 76110b2616e615e1bc83ea6c52982e2d2a5c259c Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:58:19 -0500
Subject: [PATCH 39/47] docs: add consensus_peaks subwf to changelog

---
 CHANGELOG.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9f1a943..fef76b0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -26,4 +26,5 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 
 ### New subworkflows
 
-- custom/filter_blacklist (#17,#27)
+- consensus_peaks (#37)
+- filter_blacklist (#17,#27)

From 8692e3370ebdd691ae2a2ab2ccb783bbf6e386a1 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 14:59:07 -0500
Subject: [PATCH 40/47] docs: point users to consensus_peaks subwf from legacy
 module

---
 modules/CCBR/custom/consensuspeaks/meta.yml | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/modules/CCBR/custom/consensuspeaks/meta.yml b/modules/CCBR/custom/consensuspeaks/meta.yml
index 52fa43e..cafe661 100644
--- a/modules/CCBR/custom/consensuspeaks/meta.yml
+++ b/modules/CCBR/custom/consensuspeaks/meta.yml
@@ -1,6 +1,9 @@
 ---
 name: "custom_consensuspeaks"
-description: Find consensus peaks from two or more peak files.
+description: |
+  Find consensus peaks from two or more peak files.
+  The consensus_peaks subworkflow is a re-implementation of this module;
+  new pipelines should use the subworkflow instead.
 keywords:
   - peaks
   - chipseq

From fe9a7da7f1eb8e05623199281276e0b76c8690b6 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:03:30 -0500
Subject: [PATCH 41/47] docs: move new modules & subwfs for next dev version

---
 CHANGELOG.md | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index d6996d6..f81f5a5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,26 +2,30 @@
 
 ### New modules
 
+- bedops/bedmap (#37)
+- bedtools/map (#37)
+- bedtools/merge (#37)
+- bedtools/sort (#37)
+- cat/cat (#37)
+- cat/fastq (#37)
+- custom/combinepeakcounts (#37)
+- custom/consensuspeaks (#37)
+- custom/normalizepeaks (#37)
+
 ### New subworkflows
 
+- consensus_peaks (#37)
+
 ## nf-modules 0.1.0
 
 Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16)
 
 ### New modules
 
-- bedops/bedmap (#37)
-- bedtools/map (#37)
-- bedtools/merge (#37)
-- bedtools/sort (#37)
 - bwa/index
 - bwa/mem
   - also runs samtools sort & outputs index in bai format. (#12)
-- cat/cat (#37)
-- cat/fastq (#37)
 - custom/bam2fastq (#14,#22)
-- custom/combinepeakcounts (#37)
-- custom/consensuspeaks (#37)
 - custom/convertsicer (#36)
 - custom/countfastq (#32)
 - cutadapt (#11)
@@ -32,5 +36,4 @@ Our documentation website is now live: <https://ccbr.github.io/nf-modules/> (#16
 
 ### New subworkflows
 
-- consensus_peaks (#37)
 - filter_blacklist (#17,#27)

From f81e205c996a533cc8896ef2f7f5eb0465671ac2 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:04:59 -0500
Subject: [PATCH 42/47] docs: license must be an array

---
 modules/CCBR/custom/combinepeakcounts/meta.yml | 2 +-
 modules/CCBR/custom/normalizepeaks/meta.yml    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/CCBR/custom/combinepeakcounts/meta.yml b/modules/CCBR/custom/combinepeakcounts/meta.yml
index 8990f07..54fca8b 100644
--- a/modules/CCBR/custom/combinepeakcounts/meta.yml
+++ b/modules/CCBR/custom/combinepeakcounts/meta.yml
@@ -9,7 +9,7 @@ tools:
   - "R":
       description: "R is a free software environment for statistical computing and graphics"
       homepage: "https://www.r-project.org/"
-      licence: "GPL-3"
+      licence: ["GPL-3"]
 
 input:
   # Only when we have meta
diff --git a/modules/CCBR/custom/normalizepeaks/meta.yml b/modules/CCBR/custom/normalizepeaks/meta.yml
index aea2b2c..f237555 100644
--- a/modules/CCBR/custom/normalizepeaks/meta.yml
+++ b/modules/CCBR/custom/normalizepeaks/meta.yml
@@ -10,7 +10,7 @@ tools:
   - "R":
       description: "R is a free software environment for statistical computing and graphics"
       homepage: "https://www.r-project.org/"
-      licence: "GPL-3"
+      licence: ["GPL-3"]
 
 input:
   # Only when we have meta

From 7cbeb705bd891117af331b0728aeb9095baef784 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:11:58 -0500
Subject: [PATCH 43/47] test: creat test yml for consensus_peaks subwf

---
 .../CCBR/consensus_peaks/test.yml             | 57 +++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/tests/subworkflows/CCBR/consensus_peaks/test.yml b/tests/subworkflows/CCBR/consensus_peaks/test.yml
index e69de29..09563f7 100644
--- a/tests/subworkflows/CCBR/consensus_peaks/test.yml
+++ b/tests/subworkflows/CCBR/consensus_peaks/test.yml
@@ -0,0 +1,57 @@
+- name: consensus_peaks test_consensus_peaks_broad
+  command: nextflow run ./tests/subworkflows/CCBR/consensus_peaks -entry test_consensus_peaks_broad -c ./tests/config/nextflow.config
+  tags:
+    - bedops
+    - bedops/bedmap
+    - bedtools
+    - bedtools/merge
+    - bedtools/sort
+    - cat
+    - cat/cat
+    - custom
+    - custom/combinepeakcounts
+    - custom/normalizepeaks
+    - subworkflows
+    - subworkflows/consensus_peaks
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.macs_broad.mapped.bed
+      md5sum: a46e2f78e8534ecdc882fff22f0baa87
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.macs_broad.mapped.bed
+      md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
+    - path: output/bedtools_merge/macs_broad.merged.bed
+      md5sum: d67c8c15b99b310ec5aa0ec363dcd147
+    - path: output/bedtools_sort/SPT5_T0_1_peaks.sorted.broadPeak
+      md5sum: 03b87e9021f85db1c8e07f5c0b4d7347
+    - path: output/bedtools_sort/SPT5_T0_2_peaks.sorted.broadPeak
+      md5sum: d3216918f24ced4b76b8eed6e38aa5c6
+    - path: output/bedtools_sort/macs_broad.sorted.broadPeak
+      md5sum: 2541c1a79171d255fd0582bd7ea80493
+    - path: output/cat_cat/macs_broad.broadPeak
+      md5sum: 4c8d04c85c4782bf667297ecb23b6703
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
+      md5sum: 600f5c2dfeae440ada8c412c153a677e
+
+- name: consensus_peaks test_consensus_peaks_broad stub
+  command: nextflow run ./tests/subworkflows/CCBR/consensus_peaks -entry test_consensus_peaks_broad -c ./tests/config/nextflow.config -stub
+  tags:
+    - bedops
+    - bedops/bedmap
+    - bedtools
+    - bedtools/merge
+    - bedtools/sort
+    - cat
+    - cat/cat
+    - custom
+    - custom/combinepeakcounts
+    - custom/normalizepeaks
+    - subworkflows
+    - subworkflows/consensus_peaks
+  files:
+    - path: output/bedops_bedmap/SPT5_T0_1_peaks.macs_broad.mapped.bed
+    - path: output/bedops_bedmap/SPT5_T0_2_peaks.macs_broad.mapped.bed
+    - path: output/bedtools_merge/macs_broad.merged.bed
+    - path: output/bedtools_sort/SPT5_T0_1_peaks.sorted.broadPeak
+    - path: output/bedtools_sort/SPT5_T0_2_peaks.sorted.broadPeak
+    - path: output/bedtools_sort/macs_broad.sorted.broadPeak
+    - path: output/cat_cat/macs_broad.broadPeak
+    - path: output/custom_combinepeakcounts/macs_broad.consensus.bed

From 0773762b3d46cb809b62bb2bbc4d6d534e9a70d2 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:24:58 -0500
Subject: [PATCH 44/47] fix: typo in param name

---
 .../CCBR/custom/normalizepeaks/templates/normalize_peaks.R   | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
index c0a6c0c..8981494 100644
--- a/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
+++ b/modules/CCBR/custom/normalizepeaks/templates/normalize_peaks.R
@@ -6,7 +6,10 @@ library(stringr)
 library(readr)
 library(tidyr)
 
-main <- function(versionfile = "versions.yml", counfile = "${count}", peakfile = "${peaks}", outfile = "${outfile}") {
+main <- function(versionfile = "versions.yml",
+                 countfile = "${count}",
+                 peakfile = "${peaks}",
+                 outfile = "${outfile}") {
   write_lines(get_version(), versionfile)
   count_dat <- read_peaks(countfile)
   peak_dat <- read_peaks(peakfile) %>%

From 5dea69aa2583ba12d915f0b8c6ebe0ab3191ea6b Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:27:33 -0500
Subject: [PATCH 45/47] test: add test for normalized & mixed consensus groups

---
 .../subworkflows/CCBR/consensus_peaks/main.nf | 20 +++++++++++
 .../CCBR/consensus_peaks/test.yml             | 35 +++++++++++--------
 2 files changed, 41 insertions(+), 14 deletions(-)

diff --git a/tests/subworkflows/CCBR/consensus_peaks/main.nf b/tests/subworkflows/CCBR/consensus_peaks/main.nf
index 0d7329e..c1b1d08 100644
--- a/tests/subworkflows/CCBR/consensus_peaks/main.nf
+++ b/tests/subworkflows/CCBR/consensus_peaks/main.nf
@@ -5,6 +5,7 @@ nextflow.enable.dsl = 2
 include { BEDTOOLS_SORT  } from '../../../modules/CCBR/bedtools/sort/'
 include { CONSENSUS_PEAKS } from '../../../../subworkflows/CCBR/consensus_peaks'
 
+
 workflow test_consensus_peaks_broad {
 
     input = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
@@ -17,3 +18,22 @@ workflow test_consensus_peaks_broad {
 
     CONSENSUS_PEAKS( peaks, false )
 }
+
+workflow test_consensus_peaks_mix_norm {
+
+    broad = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
+                              file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])
+        .map { peak ->
+            [ [id: peak.baseName, group: 'macs_broad'], peak ]
+        }
+    narrow = Channel.fromPath([file(params.test_data.macs.narrow.peaks_T0_1, checkIfExists: true),
+                              file(params.test_data.macs.narrow.peaks_T0_2, checkIfExists: true)])
+        .map { peak ->
+            [ [id: peak.baseName, group: 'macs_narrow'], peak ]
+        }
+    input = broad.mix(narrow)
+    BEDTOOLS_SORT(input, [])
+    peaks = BEDTOOLS_SORT.out.sorted
+
+    CONSENSUS_PEAKS( peaks, true )
+}
diff --git a/tests/subworkflows/CCBR/consensus_peaks/test.yml b/tests/subworkflows/CCBR/consensus_peaks/test.yml
index 09563f7..0ae0da3 100644
--- a/tests/subworkflows/CCBR/consensus_peaks/test.yml
+++ b/tests/subworkflows/CCBR/consensus_peaks/test.yml
@@ -14,20 +14,6 @@
     - subworkflows
     - subworkflows/consensus_peaks
   files:
-    - path: output/bedops_bedmap/SPT5_T0_1_peaks.macs_broad.mapped.bed
-      md5sum: a46e2f78e8534ecdc882fff22f0baa87
-    - path: output/bedops_bedmap/SPT5_T0_2_peaks.macs_broad.mapped.bed
-      md5sum: c58be7ebe1f63c1cdf9eef66a41e23c1
-    - path: output/bedtools_merge/macs_broad.merged.bed
-      md5sum: d67c8c15b99b310ec5aa0ec363dcd147
-    - path: output/bedtools_sort/SPT5_T0_1_peaks.sorted.broadPeak
-      md5sum: 03b87e9021f85db1c8e07f5c0b4d7347
-    - path: output/bedtools_sort/SPT5_T0_2_peaks.sorted.broadPeak
-      md5sum: d3216918f24ced4b76b8eed6e38aa5c6
-    - path: output/bedtools_sort/macs_broad.sorted.broadPeak
-      md5sum: 2541c1a79171d255fd0582bd7ea80493
-    - path: output/cat_cat/macs_broad.broadPeak
-      md5sum: 4c8d04c85c4782bf667297ecb23b6703
     - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
       md5sum: 600f5c2dfeae440ada8c412c153a677e
 
@@ -55,3 +41,24 @@
     - path: output/bedtools_sort/macs_broad.sorted.broadPeak
     - path: output/cat_cat/macs_broad.broadPeak
     - path: output/custom_combinepeakcounts/macs_broad.consensus.bed
+
+- name: consensus_peaks test_consensus_peaks_mix_norm
+  command: nextflow run ./tests/subworkflows/CCBR/consensus_peaks -entry test_consensus_peaks_mix_norm -c ./tests/config/nextflow.config
+  tags:
+    - bedops
+    - bedops/bedmap
+    - bedtools
+    - bedtools/merge
+    - bedtools/sort
+    - cat
+    - cat/cat
+    - custom
+    - custom/combinepeakcounts
+    - custom/normalizepeaks
+    - subworkflows
+    - subworkflows/consensus_peaks
+  files:
+    - path: output/custom_normalizepeaks/macs_broad.consensus.norm.bed
+      md5sum: 9b133bf0d129a51491c9d722a7d577c0
+    - path: output/custom_normalizepeaks/macs_narrow.consensus.norm.bed
+      md5sum: 29d222c145ef196b2cc11b304c3ed2ed

From 74d899dcad73a710e522a51dad41850e2f2e8295 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:32:03 -0500
Subject: [PATCH 46/47] fix: mix process versions channel

---
 subworkflows/CCBR/consensus_peaks/main.nf | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/subworkflows/CCBR/consensus_peaks/main.nf b/subworkflows/CCBR/consensus_peaks/main.nf
index f501931..8b37b03 100644
--- a/subworkflows/CCBR/consensus_peaks/main.nf
+++ b/subworkflows/CCBR/consensus_peaks/main.nf
@@ -50,8 +50,17 @@ workflow CONSENSUS_PEAKS {
                 }
             ch_count_peak | CUSTOM_NORMALIZEPEAKS
             consensus_peaks = CUSTOM_NORMALIZEPEAKS.out.bed
+            ch_versions = ch_versions.mix(CUSTOM_NORMALIZEPEAKS.out.versions)
         }
 
+        ch_versions = ch_versions.mix(
+            CAT_CAT.out.versions,
+            BEDTOOLS_SORT.out.versions,
+            BEDTOOLS_MERGE.out.versions,
+            BEDOPS_BEDMAP.out.versions,
+            CUSTOM_COMBINEPEAKCOUNTS.out.versions
+        )
+
     emit:
         peaks    = consensus_peaks
         versions = ch_versions

From 8917fd9e6d5f1d2d9431cb8e9e36e4d8ac9ab994 Mon Sep 17 00:00:00 2001
From: Kelly Sovacool <kelly.sovacool@nih.gov>
Date: Wed, 29 Nov 2023 15:35:29 -0500
Subject: [PATCH 47/47] test: fix workflow entry name to mirrow new module name

---
 tests/modules/CCBR/custom/combinepeakcounts/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/modules/CCBR/custom/combinepeakcounts/main.nf b/tests/modules/CCBR/custom/combinepeakcounts/main.nf
index 51a536f..c93ba65 100644
--- a/tests/modules/CCBR/custom/combinepeakcounts/main.nf
+++ b/tests/modules/CCBR/custom/combinepeakcounts/main.nf
@@ -9,7 +9,7 @@ include { BEDTOOLS_SORT as SORT_CAT
 include { BEDTOOLS_MERGE             } from '../../../../../modules/CCBR/bedtools/merge/main.nf'
 include { CUSTOM_COMBINEPEAKCOUNTS        } from '../../../../../modules/CCBR/custom/combinepeakcounts/main.nf'
 
-workflow test_custom_combinepeaks {
+workflow test_custom_combinepeakcounts {
 
     ch_peaks = Channel.fromPath([file(params.test_data.macs.broad.peaks_T0_1, checkIfExists: true),
                                  file(params.test_data.macs.broad.peaks_T0_2, checkIfExists: true)])