From 2d0a990cac4bf2d194ba9c610e00cc99b1c2c4c5 Mon Sep 17 00:00:00 2001
From: Theodoro Gasperin Terra Camargo
 <98555209+tgaspe@users.noreply.github.com>
Date: Mon, 2 Sep 2024 14:41:55 +0200
Subject: [PATCH 1/3] Bedtools merge (#118)

* Initial Commit

* Script file

* strand option tests

* -bed option test

* distance option test

* all test implemented

* Update CHANGELOG.md

* Update config.vsh.yaml

* adding more links

* exit on error

* suggested changes

* working on suggested changes

---------

Co-authored-by: Jakub Majercik <57993790+jakubmajercik@users.noreply.github.com>
---
 CHANGELOG.md                                  |   1 +
 src/bedtools/bedtools_merge/config.vsh.yaml   | 160 +++++++++++++
 src/bedtools/bedtools_merge/help.txt          |  85 +++++++
 src/bedtools/bedtools_merge/script.sh         |  35 +++
 src/bedtools/bedtools_merge/test.sh           | 222 ++++++++++++++++++
 .../bedtools_merge/test_data/feature.bam      | Bin 0 -> 287 bytes
 6 files changed, 503 insertions(+)
 create mode 100644 src/bedtools/bedtools_merge/config.vsh.yaml
 create mode 100644 src/bedtools/bedtools_merge/help.txt
 create mode 100644 src/bedtools/bedtools_merge/script.sh
 create mode 100644 src/bedtools/bedtools_merge/test.sh
 create mode 100644 src/bedtools/bedtools_merge/test_data/feature.bam

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 3e9f40fc..8c1af805 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -29,6 +29,7 @@
 * `bedtools`:
   - `bedtools/bedtools_intersect`: Allows one to screen for overlaps between two sets of genomic features (PR #94).
   - `bedtools/bedtools_sort`: Sorts a feature file (bed/gff/vcf) by chromosome and other criteria (PR #98).
+  - `bedtools/bedtools_merge`: Merges overlapping BED/GFF/VCF entries into a single interval (PR #118).
   - `bedtools/bedtools_bamtofastq`: Convert BAM alignments to FASTQ files (PR #101).
   - `bedtools/bedtools_bedtobam`: Converts genomic feature records (bed/gff/vcf) to BAM format (PR #111).
  
diff --git a/src/bedtools/bedtools_merge/config.vsh.yaml b/src/bedtools/bedtools_merge/config.vsh.yaml
new file mode 100644
index 00000000..45e4a01d
--- /dev/null
+++ b/src/bedtools/bedtools_merge/config.vsh.yaml
@@ -0,0 +1,160 @@
+name: bedtools_merge
+namespace: bedtools
+description: | 
+  Merges overlapping BED/GFF/VCF entries into a single interval.
+links:
+  documentation: https://bedtools.readthedocs.io/en/latest/content/tools/merge.html
+  repository: https://github.com/arq5x/bedtools2
+  homepage: https://bedtools.readthedocs.io/en/latest/#
+  issue_tracker: https://github.com/arq5x/bedtools2/issues
+references:
+  doi: 10.1093/bioinformatics/btq033
+license: MIT
+requirements:
+  commands: [bedtools]
+authors:
+  - __merge__: /src/_authors/theodoro_gasperin.yaml
+    roles: [ author, maintainer ]
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        alternatives: -i
+        type: file
+        description: Input file (BED/GFF/VCF) to be merged.
+        required: true
+    
+  - name: Outputs
+    arguments:
+      - name: --output
+        type: file
+        direction: output
+        description: Output merged file BED to be written.
+        required: true
+
+  - name: Options
+    arguments:
+      - name: --strand
+        alternatives: -s
+        type: boolean_true
+        description: | 
+          Force strandedness. That is, only merge features
+          that are on the same strand.
+          - By default, merging is done without respect to strand.
+
+      - name: --specific_strand
+        alternatives: -S
+        type: string
+        choices: ["+", "-"]
+        description: | 
+          Force merge for one specific strand only.
+          Follow with + or - to force merge from only
+          the forward or reverse strand, respectively.
+          - By default, merging is done without respect to strand.
+
+      - name: --distance
+        alternatives: -d
+        type: integer
+        description: | 
+          Maximum distance between features allowed for features
+          to be merged.
+          - Def. 0. That is, overlapping & book-ended features are merged.
+          - (INTEGER)
+          - Note: negative values enforce the number of b.p. required for overlap.
+
+      - name: --columns
+        alternatives: -c
+        type: integer
+        description: | 
+          Specify columns from the B file to map onto intervals in A.
+          Default: 5.
+          Multiple columns can be specified in a comma-delimited list.
+
+      - name: --operation
+        alternatives: -o
+        type: string
+        description: | 
+          Specify the operation that should be applied to -c.
+          Valid operations:
+              sum, min, max, absmin, absmax,
+              mean, median, mode, antimode
+              stdev, sstdev
+              collapse (i.e., print a delimited list (duplicates allowed)), 
+              distinct (i.e., print a delimited list (NO duplicates allowed)), 
+              distinct_sort_num (as distinct, sorted numerically, ascending),
+              distinct_sort_num_desc (as distinct, sorted numerically, desscending),
+              distinct_only (delimited list of only unique values),
+              count
+              count_distinct (i.e., a count of the unique values in the column), 
+              first (i.e., just the first value in the column), 
+              last (i.e., just the last value in the column), 
+          Default: sum
+          Multiple operations can be specified in a comma-delimited list.
+
+          If there is only column, but multiple operations, all operations will be
+          applied on that column. Likewise, if there is only one operation, but
+          multiple columns, that operation will be applied to all columns.
+          Otherwise, the number of columns must match the the number of operations,
+          and will be applied in respective order.
+          E.g., "-c 5,4,6 -o sum,mean,count" will give the sum of column 5,
+          the mean of column 4, and the count of column 6.
+          The order of output columns will match the ordering given in the command.
+      
+      - name: --delimiter
+        alternatives: -delim
+        type: string
+        description: | 
+          Specify a custom delimiter for the collapse operations.
+        example: "|"
+        default: ","
+
+      - name: --precision
+        alternatives: -prec
+        type: integer
+        description: | 
+          Sets the decimal precision for output (Default: 5).
+      
+      - name: --bed
+        type: boolean_true
+        description: | 
+          If using BAM input, write output as BED.
+
+      - name: --header
+        type: boolean_true
+        description: | 
+          Print the header from the A file prior to results.
+
+      - name: --no_buffer
+        alternatives: -nobuf
+        type: boolean_true
+        description: | 
+          Disable buffered output. Using this option will cause each line
+          of output to be printed as it is generated, rather than saved
+          in a buffer. This will make printing large output files 
+          noticeably slower, but can be useful in conjunction with
+          other software tools and scripts that need to process one
+          line of bedtools output at a time.
+
+resources:
+  - type: bash_script
+    path: script.sh
+
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - path: test_data
+
+engines:
+  - type: docker
+    image: debian:stable-slim
+    setup:
+      - type: apt
+        packages: [bedtools, procps]
+      - type: docker
+        run: |
+          echo "bedtools: \"$(bedtools --version | sed -n 's/^bedtools //p')\"" > /var/software_versions.txt
+
+runners:
+  - type: executable
+  - type: nextflow
\ No newline at end of file
diff --git a/src/bedtools/bedtools_merge/help.txt b/src/bedtools/bedtools_merge/help.txt
new file mode 100644
index 00000000..bc78fc67
--- /dev/null
+++ b/src/bedtools/bedtools_merge/help.txt
@@ -0,0 +1,85 @@
+```bash
+bedtools merge
+```
+
+Tool:    bedtools merge (aka mergeBed)
+Version: v2.30.0
+Summary: Merges overlapping BED/GFF/VCF entries into a single interval.
+
+Usage:   bedtools merge [OPTIONS] -i <bed/gff/vcf>
+
+Options: 
+	-s	Force strandedness.  That is, only merge features
+		that are on the same strand.
+		- By default, merging is done without respect to strand.
+
+	-S	Force merge for one specific strand only.
+		Follow with + or - to force merge from only
+		the forward or reverse strand, respectively.
+		- By default, merging is done without respect to strand.
+
+	-d	Maximum distance between features allowed for features
+		to be merged.
+		- Def. 0. That is, overlapping & book-ended features are merged.
+		- (INTEGER)
+		- Note: negative values enforce the number of b.p. required for overlap.
+
+	-c	Specify columns from the B file to map onto intervals in A.
+		Default: 5.
+		Multiple columns can be specified in a comma-delimited list.
+
+	-o	Specify the operation that should be applied to -c.
+		Valid operations:
+		    sum, min, max, absmin, absmax,
+		    mean, median, mode, antimode
+		    stdev, sstdev
+		    collapse (i.e., print a delimited list (duplicates allowed)), 
+		    distinct (i.e., print a delimited list (NO duplicates allowed)), 
+		    distinct_sort_num (as distinct, sorted numerically, ascending),
+		    distinct_sort_num_desc (as distinct, sorted numerically, desscending),
+		    distinct_only (delimited list of only unique values),
+		    count
+		    count_distinct (i.e., a count of the unique values in the column), 
+		    first (i.e., just the first value in the column), 
+		    last (i.e., just the last value in the column), 
+		Default: sum
+		Multiple operations can be specified in a comma-delimited list.
+
+		If there is only column, but multiple operations, all operations will be
+		applied on that column. Likewise, if there is only one operation, but
+		multiple columns, that operation will be applied to all columns.
+		Otherwise, the number of columns must match the the number of operations,
+		and will be applied in respective order.
+		E.g., "-c 5,4,6 -o sum,mean,count" will give the sum of column 5,
+		the mean of column 4, and the count of column 6.
+		The order of output columns will match the ordering given in the command.
+
+
+	-delim	Specify a custom delimiter for the collapse operations.
+		- Example: -delim "|"
+		- Default: ",".
+
+	-prec	Sets the decimal precision for output (Default: 5)
+
+	-bed	If using BAM input, write output as BED.
+
+	-header	Print the header from the A file prior to results.
+
+	-nobuf	Disable buffered output. Using this option will cause each line
+		of output to be printed as it is generated, rather than saved
+		in a buffer. This will make printing large output files 
+		noticeably slower, but can be useful in conjunction with
+		other software tools and scripts that need to process one
+		line of bedtools output at a time.
+
+	-iobuf	Specify amount of memory to use for input buffer.
+		Takes an integer argument. Optional suffixes K/M/G supported.
+		Note: currently has no effect with compressed files.
+
+Notes: 
+	(1) The input file (-i) file must be sorted by chrom, then start.
+
+
+
+
+***** ERROR: No input file given. Exiting. *****
diff --git a/src/bedtools/bedtools_merge/script.sh b/src/bedtools/bedtools_merge/script.sh
new file mode 100644
index 00000000..db50dd83
--- /dev/null
+++ b/src/bedtools/bedtools_merge/script.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+# Exit on error
+set -eo pipefail
+
+# Unset parameters
+unset_if_false=(
+    par_strand
+    par_bed
+    par_header
+    par_no_buffer
+)
+
+for par in ${unset_if_false[@]}; do
+    test_val="${!par}"
+    [[ "$test_val" == "false" ]] && unset $par
+done
+
+# Execute bedtools merge with the provided arguments
+bedtools merge \
+    ${par_strand:+-s} \
+    ${par_specific_strand:+-S "$par_specific_strand"} \
+    ${par_bed:+-bed} \
+    ${par_header:+-header} \
+    ${par_no_buffer:+-nobuf} \
+    ${par_distance:+-d "$par_distance"} \
+    ${par_columns:+-c "$par_columns"} \
+    ${par_operation:+-o "$par_operation"} \
+    ${par_delimiter:+-delim "$par_delimiter"} \
+    ${par_precision:+-prec "$par_precision"} \
+    -i "$par_input" \
+    > "$par_output"
diff --git a/src/bedtools/bedtools_merge/test.sh b/src/bedtools/bedtools_merge/test.sh
new file mode 100644
index 00000000..e2b46c15
--- /dev/null
+++ b/src/bedtools/bedtools_merge/test.sh
@@ -0,0 +1,222 @@
+#!/bin/bash
+
+# exit on error
+set -eo pipefail
+
+## VIASH START
+meta_executable="target/executable/bedtools/bedtools_sort/bedtools_merge"
+meta_resources_dir="src/bedtools/bedtools_merge"
+## VIASH END
+
+# directory of the bam file
+test_data="$meta_resources_dir/test_data"
+
+#############################################
+# helper functions
+assert_file_exists() {
+  [ -f "$1" ] || { echo "File '$1' does not exist" && exit 1; }
+}
+assert_file_not_empty() {
+  [ -s "$1" ] || { echo "File '$1' is empty but shouldn't be" && exit 1; }
+}
+assert_file_contains() {
+  grep -q "$2" "$1" || { echo "File '$1' does not contain '$2'" && exit 1; }
+}
+assert_identical_content() {
+  diff -a "$2" "$1" \
+    || (echo "Files are not identical!" && exit 1)
+}
+#############################################
+
+# Create directories for tests
+echo "Creating Test Data..."
+TMPDIR=$(mktemp -d "$meta_temp_dir/XXXXXX")
+function clean_up {
+  [[ -d "$TMPDIR" ]] && rm -r "$TMPDIR"
+}
+trap clean_up EXIT
+
+# Create and populate example files
+printf "chr1\t100\t200\nchr1\t150\t250\nchr1\t300\t400\n" > "$TMPDIR/featureA.bed"
+printf "chr1\t100\t200\ta1\t1\t+\nchr1\t180\t250\ta2\t2\t+\nchr1\t250\t500\ta3\t3\t-\nchr1\t501\t1000\ta4\t4\t+\n" > "$TMPDIR/featureB.bed"
+printf "chr1\t100\t200\ta1\t1.9\t+\nchr1\t180\t250\ta2\t2.5\t+\nchr1\t250\t500\ta3\t3.3\t-\nchr1\t501\t1000\ta4\t4\t+\n" > "$TMPDIR/feature_precision.bed"
+
+# Create and populate feature.gff file
+printf "##gff-version 3\n" > "$TMPDIR/feature.gff"
+printf "chr1\t.\tgene\t1000\t2000\t.\t+\t.\tID=gene1;Name=Gene1\n" >> "$TMPDIR/feature.gff"
+printf "chr1\t.\texon\t1000\t1200\t.\t+\t.\tID=exon1;Parent=transcript1\n" >> "$TMPDIR/feature.gff"
+printf "chr1\t.\tCDS\t1000\t1200\t.\t+\t0\tID=cds1;Parent=transcript1\n" >> "$TMPDIR/feature.gff"
+printf "chr1\t.\tCDS\t1500\t1700\t.\t+\t2\tID=cds2;Parent=transcript1\n" >> "$TMPDIR/feature.gff"
+printf "chr2\t.\texon\t1500\t1700\t.\t+\t.\tID=exon2;Parent=transcript1\n" >> "$TMPDIR/feature.gff"
+printf "chr3\t.\tmRNA\t1000\t2000\t.\t+\t.\tID=transcript1;Parent=gene1\n" >> "$TMPDIR/feature.gff"
+
+# Create expected output files
+printf "chr1\t100\t250\nchr1\t300\t400\n" > "$TMPDIR/expected.bed"
+printf "chr1\t100\t250\nchr1\t250\t500\nchr1\t501\t1000\n" > "$TMPDIR/expected_strand.bed"
+printf "chr1\t100\t250\nchr1\t501\t1000\n" > "$TMPDIR/expected_specific_strand.bed"
+printf "chr1\t128\t228\nchr1\t428\t528\n" > "$TMPDIR/expected_bam.bed"
+printf "chr1\t100\t400\n" > "$TMPDIR/expected_distance.bed"
+printf "chr1\t100\t500\t2\t1\t3\nchr1\t501\t1000\t4\t4\t4\n" > "$TMPDIR/expected_operation.bed"
+printf "chr1\t100\t500\ta1|a2|a3\nchr1\t501\t1000\ta4\n" > "$TMPDIR/expected_delim.bed"
+printf "chr1\t100\t500\t2.567\nchr1\t501\t1000\t4\n" > "$TMPDIR/expected_precision.bed"
+printf "##gff-version 3\nchr1\t999\t2000\nchr2\t1499\t1700\nchr3\t999\t2000\n" > "$TMPDIR/expected_header.bed"
+
+# Test 1: Default sort on BED file
+mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
+
+echo "> Run bedtools_merge on BED file"
+"$meta_executable" \
+  --input "../featureA.bed" \
+  --output "output.bed"
+
+# # checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected.bed"
+echo "- test1 succeeded -"
+
+popd > /dev/null
+
+# Test 2: strand option
+mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
+
+echo "> Run bedtools_merge on BED file with strand option"
+"$meta_executable" \
+  --input "../featureB.bed" \
+  --output "output.bed" \
+  --strand
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_strand.bed"
+echo "- test2 succeeded -"
+
+popd > /dev/null
+
+# Test 3: specific strand option
+mkdir "$TMPDIR/test3" && pushd "$TMPDIR/test3" > /dev/null
+
+echo "> Run bedtools_merge on BED file with specific strand option"
+"$meta_executable" \
+  --input "../featureB.bed" \
+  --output "output.bed" \
+  --specific_strand "+" 
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_specific_strand.bed"
+echo "- test3 succeeded -"
+
+popd > /dev/null
+
+# Test 4: BED option
+mkdir "$TMPDIR/test4" && pushd "$TMPDIR/test4" > /dev/null
+
+echo "> Run bedtools_merge on BAM file with BED option"
+"$meta_executable" \
+  --input "$test_data/feature.bam" \
+  --output "output.bed" \
+  --bed
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_bam.bed"
+echo "- test4 succeeded -"
+
+popd > /dev/null
+
+# Test 5: distance option
+mkdir "$TMPDIR/test5" && pushd "$TMPDIR/test5" > /dev/null
+
+echo "> Run bedtools_merge on BED file with distance option"
+"$meta_executable" \
+  --input "../featureA.bed" \
+  --output "output.bed" \
+  --distance -5 
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected.bed"
+echo "- test5 succeeded -"
+
+popd > /dev/null
+
+# Test 6: columns option & operation option
+mkdir "$TMPDIR/test6" && pushd "$TMPDIR/test6" > /dev/null
+
+echo "> Run bedtools_merge on BED file with columns & operation options"
+"$meta_executable" \
+  --input "../featureB.bed" \
+  --output "output.bed" \
+  --columns 5 \
+  --operation "mean,min,max"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_operation.bed"
+echo "- test6 succeeded -"
+
+popd > /dev/null
+
+# Test 7: delimeter option
+mkdir "$TMPDIR/test7" && pushd "$TMPDIR/test7" > /dev/null
+
+echo "> Run bedtools_merge on BED file with delimeter option"
+"$meta_executable" \
+  --input "../featureB.bed" \
+  --output "output.bed" \
+  --columns 4 \
+  --operation "collapse" \
+  --delimiter "|"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_delim.bed"
+echo "- test7 succeeded -"
+
+popd > /dev/null
+
+# Test 8: precision option
+mkdir "$TMPDIR/test8" && pushd "$TMPDIR/test8" > /dev/null
+
+echo "> Run bedtools_merge on BED file with precision option"
+"$meta_executable" \
+  --input "../feature_precision.bed" \
+  --output "output.bed" \
+  --columns 5 \
+  --operation "mean" \
+  --precision 4
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_precision.bed"
+echo "- test8 succeeded -"
+
+popd > /dev/null
+
+# Test 9: header option
+mkdir "$TMPDIR/test9" && pushd "$TMPDIR/test9" > /dev/null
+
+echo "> Run bedtools_merge on GFF file with header option"
+"$meta_executable" \
+  --input "../feature.gff" \
+  --output "output.gff" \
+  --header
+
+# checks
+assert_file_exists "output.gff"
+assert_file_not_empty "output.gff"
+assert_identical_content "output.gff" "../expected_header.bed"
+echo "- test9 succeeded -"
+
+popd > /dev/null
+
+echo "---- All tests succeeded! ----"
+exit 0
diff --git a/src/bedtools/bedtools_merge/test_data/feature.bam b/src/bedtools/bedtools_merge/test_data/feature.bam
new file mode 100644
index 0000000000000000000000000000000000000000..3d56a6317ba2f31f1df17f2f4247a9ad8a0585ae
GIT binary patch
literal 287
zcmb2|=3rp}f&Xj_PR>jWyBLa#zNFqcap1s%2M-TPK1)wsk$yn(O@8RC@Hz1zlV%-y
zD)8Xk%a=({pS%*9G=F}u%={^{geJY8GJ`uvIxKBTdd`CM15X8HPDs8<pE@Tn<-|*g
zoT>9>O`kt|Rd`U~p_h--Q&W->Gqci?Qd*Xrk(h0y?ChN!tn96l>NevPkFIWyj<2t;
z?#>yFeQB&o6V~$N9AEd*(efD2)ZkBvGRkb<n8kN8uC=zi_XOx-c{HcHGh9w?Xkb%#
z_Upao5ss(-+nEHcw;S!#Fg0|&KjC0wZ=)mssw7@zpLPa6S+@jPh95_57pGt`N1A~d
I6d+&#0J{lptpET3

literal 0
HcmV?d00001


From 7269ae4e7b4d4aa2b8e1631a216a5531eb7165b6 Mon Sep 17 00:00:00 2001
From: Theodoro Gasperin Terra Camargo
 <98555209+tgaspe@users.noreply.github.com>
Date: Mon, 2 Sep 2024 14:42:44 +0200
Subject: [PATCH 2/3] Bedtools links (#137)

* Initial Commit

* Tests

* Adding help file

* Adding more description

* Update test.sh

* Update help.txt

* Update CHANGELOG.md
---
 CHANGELOG.md                                |  1 +
 src/bedtools/bedtools_links/config.vsh.yaml | 91 +++++++++++++++++++
 src/bedtools/bedtools_links/help.txt        | 25 ++++++
 src/bedtools/bedtools_links/script.sh       | 14 +++
 src/bedtools/bedtools_links/test.sh         | 98 +++++++++++++++++++++
 5 files changed, 229 insertions(+)
 create mode 100644 src/bedtools/bedtools_links/config.vsh.yaml
 create mode 100644 src/bedtools/bedtools_links/help.txt
 create mode 100644 src/bedtools/bedtools_links/script.sh
 create mode 100644 src/bedtools/bedtools_links/test.sh

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8c1af805..6dda7ab4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -32,6 +32,7 @@
   - `bedtools/bedtools_merge`: Merges overlapping BED/GFF/VCF entries into a single interval (PR #118).
   - `bedtools/bedtools_bamtofastq`: Convert BAM alignments to FASTQ files (PR #101).
   - `bedtools/bedtools_bedtobam`: Converts genomic feature records (bed/gff/vcf) to BAM format (PR #111).
+  - `bedtools/bedtools_links`: Creates an HTML file with links to an instance of the UCSC Genome Browser for all features / intervals in a (bed/gff/vcf) file (PR #137).
  
 * `qualimap/qualimap_rnaseq`: RNA-seq QC analysis using qualimap (PR #74). 
 
diff --git a/src/bedtools/bedtools_links/config.vsh.yaml b/src/bedtools/bedtools_links/config.vsh.yaml
new file mode 100644
index 00000000..b4e43cd3
--- /dev/null
+++ b/src/bedtools/bedtools_links/config.vsh.yaml
@@ -0,0 +1,91 @@
+name: bedtools_links
+namespace: bedtools
+description: | 
+  Creates an HTML file with links to an instance of the UCSC Genome Browser for all features / intervals in a file. 
+  This is useful for cases when one wants to manually inspect through a large set of annotations or features.
+keywords: [Links, BED, GFF, VCF]
+links:
+  documentation: https://bedtools.readthedocs.io/en/latest/content/tools/links.html
+  repository: https://github.com/arq5x/bedtools2
+  homepage: https://bedtools.readthedocs.io/en/latest/#
+  issue_tracker: https://github.com/arq5x/bedtools2/issues
+references:
+  doi: 10.1093/bioinformatics/btq033
+license: MIT
+requirements:
+  commands: [bedtools]
+authors:
+  - __merge__: /src/_authors/theodoro_gasperin.yaml
+    roles: [ author, maintainer ]
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        alternatives: -i
+        type: file
+        description: Input file (bed/gff/vcf).
+        required: true
+    
+  - name: Outputs
+    arguments:
+      - name: --output
+        alternatives: -o
+        type: file
+        direction: output
+        description: Output HTML file to be written.
+
+  - name: Options
+    description: |
+      By default, the links created will point to human (hg18) UCSC browser.
+      If you have a local mirror, you can override this behavior by supplying
+      the -base, -org, and -db options.
+
+      For example, if the URL of your local mirror for mouse MM9 is called: 
+      http://mymirror.myuniversity.edu, then you would use the following:
+      --base_url http://mymirror.myuniversity.edu
+      --organism mouse
+      --database mm9
+    arguments:
+      - name: --base_url
+        alternatives: -base
+        type: string
+        description: | 
+          The “basename” for the UCSC browser.
+        default: http://genome.ucsc.edu
+      
+      - name: --organism
+        alternatives: -org
+        type: string
+        description: | 
+          The organism (e.g. mouse, human). 
+        default: human
+
+      - name: --database
+        alternatives: -db
+        type: string
+        description: | 
+          The genome build. 
+        default: hg18
+      
+resources:
+  - type: bash_script
+    path: script.sh
+
+test_resources:
+  - type: bash_script
+    path: test.sh
+
+engines:
+  - type: docker
+    image: debian:stable-slim
+    setup:
+      - type: apt
+        packages: [bedtools, procps]
+      - type: docker
+        run: |
+          echo "bedtools: \"$(bedtools --version | sed -n 's/^bedtools //p')\"" > /var/software_versions.txt
+
+runners:
+  - type: executable
+  - type: nextflow
diff --git a/src/bedtools/bedtools_links/help.txt b/src/bedtools/bedtools_links/help.txt
new file mode 100644
index 00000000..d848d989
--- /dev/null
+++ b/src/bedtools/bedtools_links/help.txt
@@ -0,0 +1,25 @@
+```
+bedtools links -h
+```
+
+Tool:    bedtools links (aka linksBed)
+Version: v2.30.0
+Summary: Creates HTML links to an UCSC Genome Browser from a feature file.
+
+Usage:   bedtools links [OPTIONS] -i <bed/gff/vcf> > out.html
+
+Options: 
+	-base	The browser basename.  Default: http://genome.ucsc.edu 
+	-org	The organism. Default: human
+	-db	The build.  Default: hg18
+
+Example: 
+	By default, the links created will point to human (hg18) UCSC browser.
+	If you have a local mirror, you can override this behavior by supplying
+	the -base, -org, and -db options.
+
+	For example, if the URL of your local mirror for mouse MM9 is called: 
+	http://mymirror.myuniversity.edu, then you would use the following:
+	-base http://mymirror.myuniversity.edu
+	-org mouse
+	-db mm9
diff --git a/src/bedtools/bedtools_links/script.sh b/src/bedtools/bedtools_links/script.sh
new file mode 100644
index 00000000..b8ee9a56
--- /dev/null
+++ b/src/bedtools/bedtools_links/script.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -eo pipefail
+
+# Execute bedtools links
+bedtools links \
+    ${par_base_url:+-base "$par_base_url"} \
+    ${par_organism:+-org "$par_organism"} \
+    ${par_database:+-db "$par_database"} \
+    -i "$par_input" \
+    > "$par_output"
diff --git a/src/bedtools/bedtools_links/test.sh b/src/bedtools/bedtools_links/test.sh
new file mode 100644
index 00000000..d79cbd6c
--- /dev/null
+++ b/src/bedtools/bedtools_links/test.sh
@@ -0,0 +1,98 @@
+#!/bin/bash
+
+# exit on error
+set -eo pipefail
+
+#############################################
+# helper functions
+assert_file_exists() {
+  [ -f "$1" ] || { echo "File '$1' does not exist" && exit 1; }
+}
+assert_file_not_empty() {
+  [ -s "$1" ] || { echo "File '$1' is empty but shouldn't be" && exit 1; }
+}
+assert_file_contains() {
+  grep -q "$2" "$1" || { echo "File '$1' does not contain '$2'" && exit 1; }
+}
+assert_identical_content() {
+  diff -a "$2" "$1" \
+    || (echo "Files are not identical!" && exit 1)
+}
+#############################################
+
+# Create directories for tests
+echo "Creating Test Data..."
+TMPDIR=$(mktemp -d "$meta_temp_dir/XXXXXX")
+function clean_up {
+  [[ -d "$TMPDIR" ]] && rm -r "$TMPDIR"
+}
+trap clean_up EXIT
+
+# Create test data
+cat <<EOF > "$TMPDIR/genes.bed"
+chr21	9928613	10012791	uc002yip.1	0	-
+chr21	9928613	10012791	uc002yiq.1	0	-
+chr21	9928613	10012791	uc002yir.1	0	-
+chr21	9928613	10012791	uc010gkv.1	0	-
+chr21	9928613	10061300	uc002yis.1	0	-
+chr21	10042683	10120796	uc002yit.1	0	-
+chr21	10042683	10120808	uc002yiu.1	0	-
+chr21	10079666	10120808	uc002yiv.1	0	-
+chr21	10080031	10081687	uc002yiw.1	0	-
+chr21	10081660	10120796	uc002yix.2	0	-
+EOF
+
+# Test 1: Default Use
+mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
+
+echo "> Run bedtools_links on BED file"
+"$meta_executable" \
+  --input "../genes.bed" \
+  --output "genes.html"
+
+# checks
+assert_file_exists "genes.html"
+assert_file_not_empty "genes.html"
+assert_file_contains "genes.html" "uc002yip.1"
+echo "- test1 succeeded -"
+
+popd > /dev/null
+
+# Test 2: Base URL
+mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
+
+echo "> Run bedtools_links with base option"
+"$meta_executable" \
+  --input "../genes.bed" \
+  --output "genes.html" \
+  --base_url "http://genome.ucsc.edu"
+
+# checks
+assert_file_exists "genes.html"
+assert_file_not_empty "genes.html"
+assert_file_contains "genes.html" "uc002yip.1"
+echo "- test2 succeeded -"
+
+popd > /dev/null
+
+# Test 3: Organism and Genome Database Build
+mkdir "$TMPDIR/test3" && pushd "$TMPDIR/test3" > /dev/null
+
+echo "> Run bedtools_links with organism option and genome database build"
+"$meta_executable" \
+  --input "../genes.bed" \
+  --output "genes.html" \
+  --base_url "http://genome.ucsc.edu" \
+  --organism "mouse" \
+  --database "mm9"
+
+# checks
+assert_file_exists "genes.html"
+assert_file_not_empty "genes.html"
+assert_file_contains "genes.html" "uc002yip.1"
+echo "- test3 succeeded -"
+
+popd > /dev/null
+
+echo "---- All tests succeeded! ----"
+exit 0

From 2b29a47575db9dbdff8448b287925c25d9a8b01d Mon Sep 17 00:00:00 2001
From: Theodoro Gasperin Terra Camargo
 <98555209+tgaspe@users.noreply.github.com>
Date: Mon, 2 Sep 2024 15:00:09 +0200
Subject: [PATCH 3/3] Bedtools GroupBY (#123)

* Initial Commit

* Update config.vsh.yaml

* config file

* script.sh

* adding some tests

* more test

* Update CHANGELOG.md

* deleted test_data

* bug fix

* Update config.vsh.yaml

* adding more links

* exit on error

* $TMPDIR

* Update script.sh

* Update config.vsh.yaml

* Suggested change on column option

---------

Co-authored-by: Jakub Majercik <57993790+jakubmajercik@users.noreply.github.com>
---
 CHANGELOG.md                                  |   2 +
 src/bedtools/bedtools_groupby/config.vsh.yaml | 155 ++++++++++++++
 src/bedtools/bedtools_groupby/help.txt        |  93 ++++++++
 src/bedtools/bedtools_groupby/script.sh       |  36 ++++
 src/bedtools/bedtools_groupby/test.sh         | 198 ++++++++++++++++++
 5 files changed, 484 insertions(+)
 create mode 100644 src/bedtools/bedtools_groupby/config.vsh.yaml
 create mode 100644 src/bedtools/bedtools_groupby/help.txt
 create mode 100644 src/bedtools/bedtools_groupby/script.sh
 create mode 100644 src/bedtools/bedtools_groupby/test.sh

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 6dda7ab4..29fb8cfa 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -29,6 +29,7 @@
 * `bedtools`:
   - `bedtools/bedtools_intersect`: Allows one to screen for overlaps between two sets of genomic features (PR #94).
   - `bedtools/bedtools_sort`: Sorts a feature file (bed/gff/vcf) by chromosome and other criteria (PR #98).
+  - `bedtools/bedtools_groupby`: Summarizes a dataset column based upon common column groupings. Akin to the SQL "group by" command (PR #123).
   - `bedtools/bedtools_merge`: Merges overlapping BED/GFF/VCF entries into a single interval (PR #118).
   - `bedtools/bedtools_bamtofastq`: Convert BAM alignments to FASTQ files (PR #101).
   - `bedtools/bedtools_bedtobam`: Converts genomic feature records (bed/gff/vcf) to BAM format (PR #111).
@@ -38,6 +39,7 @@
 
 * `rsem/rsem_prepare_reference`: Prepare transcript references for RSEM (PR #89).
 
+
 ## MINOR CHANGES
 
 * `busco` components: update BUSCO to `5.7.1` (PR #72).
diff --git a/src/bedtools/bedtools_groupby/config.vsh.yaml b/src/bedtools/bedtools_groupby/config.vsh.yaml
new file mode 100644
index 00000000..89c4845b
--- /dev/null
+++ b/src/bedtools/bedtools_groupby/config.vsh.yaml
@@ -0,0 +1,155 @@
+name: bedtools_groupby
+namespace: bedtools
+description: |
+  Summarizes a dataset column based upon common column groupings. 
+  Akin to the SQL "group by" command.
+keywords: [groupby, BED]
+links:
+  documentation: https://bedtools.readthedocs.io/en/latest/content/tools/groupby.html
+  repository: https://github.com/arq5x/bedtools2
+  homepage: https://bedtools.readthedocs.io/en/latest/#
+  issue_tracker: https://github.com/arq5x/bedtools2/issues
+references:
+  doi: 10.1093/bioinformatics/btq033
+license: MIT
+requirements:
+  commands: [bedtools]
+authors:
+  - __merge__: /src/_authors/theodoro_gasperin.yaml
+    roles: [ author, maintainer ]
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        alternatives: -i
+        type: file
+        direction: input
+        description: |
+          The input BED file to be used.
+        required: true
+        example: input_a.bed
+        
+  - name: Outputs
+    arguments:
+      - name: --output
+        type: file
+        direction: output
+        description: | 
+          The output groupby BED file. 
+        required: true
+        example: output.bed
+  
+  - name: Options
+    arguments:
+      - name: --groupby
+        alternatives: [-g, -grp]
+        type: string
+        description: |
+          Specify the columns (1-based) for the grouping.
+          The columns must be comma separated.
+          - Default: 1,2,3  
+        required: true 
+
+      - name: --column
+        alternatives: [-c, -opCols]
+        type: integer
+        description: |
+          Specify the column (1-based) that should be summarized.
+        required: true   
+
+      - name: --operation
+        alternatives: [-o, -ops]
+        type: string
+        description: |
+          Specify the operation that should be applied to opCol.
+          Valid operations:
+              sum, count, count_distinct, min, max,
+              mean, median, mode, antimode,
+              stdev, sstdev (sample standard dev.),
+              collapse (i.e., print a comma separated list (duplicates allowed)), 
+              distinct (i.e., print a comma separated list (NO duplicates allowed)), 
+              distinct_sort_num (as distinct, but sorted numerically, ascending), 
+              distinct_sort_num_desc (as distinct, but sorted numerically, descending), 
+              concat   (i.e., merge values into a single, non-delimited string), 
+              freqdesc (i.e., print desc. list of values:freq)
+              freqasc (i.e., print asc. list of values:freq)
+              first (i.e., print first value)
+              last (i.e., print last value)
+          
+          Default value: sum   
+
+          If there is only column, but multiple operations, all operations will be
+          applied on that column. Likewise, if there is only one operation, but
+          multiple columns, that operation will be applied to all columns.
+          Otherwise, the number of columns must match the the number of operations,
+          and will be applied in respective order.
+          E.g., "-c 5,4,6 -o sum,mean,count" will give the sum of column 5,
+          the mean of column 4, and the count of column 6.
+          The order of output columns will match the ordering given in the command.
+
+      - name: --full
+        type: boolean_true
+        description: |
+          Print all columns from input file. The first line in the group is used.
+          Default: print only grouped columns.
+
+      - name: --inheader
+        type: boolean_true
+        description: |
+          Input file has a header line - the first line will be ignored.
+
+      - name: --outheader
+        type: boolean_true
+        description: |
+          Print header line in the output, detailing the column names. 
+          If the input file has headers (-inheader), the output file
+          will use the input's column names.
+          If the input file has no headers, the output file
+          will use "col_1", "col_2", etc. as the column names.
+      
+      - name: --header
+        type: boolean_true
+        description: same as '-inheader -outheader'.
+
+      - name: --ignorecase
+        type: boolean_true
+        description: |
+          Group values regardless of upper/lower case.
+
+      - name: --precision
+        alternatives: -prec
+        type: integer
+        description: |
+          Sets the decimal precision for output. 
+        default: 5
+
+      - name: --delimiter
+        alternatives: -delim
+        type: string
+        description: |
+          Specify a custom delimiter for the collapse operations.
+        example: "|"
+        default: ","
+
+resources:
+  - type: bash_script
+    path: script.sh
+
+test_resources:
+  - type: bash_script
+    path: test.sh
+
+engines:
+  - type: docker
+    image: debian:stable-slim
+    setup:
+      - type: apt
+        packages: [bedtools, procps]
+      - type: docker
+        run: |
+          echo "bedtools: \"$(bedtools --version | sed -n 's/^bedtools //p')\"" > /var/software_versions.txt
+
+runners:
+  - type: executable
+  - type: nextflow
diff --git a/src/bedtools/bedtools_groupby/help.txt b/src/bedtools/bedtools_groupby/help.txt
new file mode 100644
index 00000000..a631b4b1
--- /dev/null
+++ b/src/bedtools/bedtools_groupby/help.txt
@@ -0,0 +1,93 @@
+```bash
+bedtools groupby
+```
+
+Tool:    bedtools groupby 
+Version: v2.30.0
+Summary: Summarizes a dataset column based upon
+	 common column groupings. Akin to the SQL "group by" command.
+
+Usage:	 bedtools groupby -g [group_column(s)] -c [op_column(s)] -o [ops] 
+	 cat [FILE] | bedtools groupby -g [group_column(s)] -c [op_column(s)] -o [ops] 
+
+Options: 
+	-i		Input file. Assumes "stdin" if omitted.
+
+	-g -grp		Specify the columns (1-based) for the grouping.
+			The columns must be comma separated.
+			- Default: 1,2,3
+
+	-c -opCols	Specify the column (1-based) that should be summarized.
+			- Required.
+
+	-o -ops		Specify the operation that should be applied to opCol.
+			Valid operations:
+			    sum, count, count_distinct, min, max,
+			    mean, median, mode, antimode,
+			    stdev, sstdev (sample standard dev.),
+			    collapse (i.e., print a comma separated list (duplicates allowed)), 
+			    distinct (i.e., print a comma separated list (NO duplicates allowed)), 
+			    distinct_sort_num (as distinct, but sorted numerically, ascending), 
+			    distinct_sort_num_desc (as distinct, but sorted numerically, descending), 
+			    concat   (i.e., merge values into a single, non-delimited string), 
+			    freqdesc (i.e., print desc. list of values:freq)
+			    freqasc (i.e., print asc. list of values:freq)
+			    first (i.e., print first value)
+			    last (i.e., print last value)
+			- Default: sum
+
+		If there is only column, but multiple operations, all operations will be
+		applied on that column. Likewise, if there is only one operation, but
+		multiple columns, that operation will be applied to all columns.
+		Otherwise, the number of columns must match the the number of operations,
+		and will be applied in respective order.
+		E.g., "-c 5,4,6 -o sum,mean,count" will give the sum of column 5,
+		the mean of column 4, and the count of column 6.
+		The order of output columns will match the ordering given in the command.
+
+
+	-full		Print all columns from input file.  The first line in the group is used.
+			Default: print only grouped columns.
+
+	-inheader	Input file has a header line - the first line will be ignored.
+
+	-outheader	Print header line in the output, detailing the column names. 
+			If the input file has headers (-inheader), the output file
+			will use the input's column names.
+			If the input file has no headers, the output file
+			will use "col_1", "col_2", etc. as the column names.
+
+	-header		same as '-inheader -outheader'
+
+	-ignorecase	Group values regardless of upper/lower case.
+
+	-prec	Sets the decimal precision for output (Default: 5)
+
+	-delim	Specify a custom delimiter for the collapse operations.
+		- Example: -delim "|"
+		- Default: ",".
+
+Examples: 
+	$ cat ex1.out
+	chr1 10  20  A   chr1    15  25  B.1 1000    ATAT
+	chr1 10  20  A   chr1    25  35  B.2 10000   CGCG
+
+	$ groupBy -i ex1.out -g 1,2,3,4 -c 9 -o sum
+	chr1 10  20  A   11000
+
+	$ groupBy -i ex1.out -grp 1,2,3,4 -opCols 9,9 -ops sum,max
+	chr1 10  20  A   11000   10000
+
+	$ groupBy -i ex1.out -g 1,2,3,4 -c 8,9 -o collapse,mean
+	chr1 10  20  A   B.1,B.2,    5500
+
+	$ cat ex1.out | groupBy -g 1,2,3,4 -c 8,9 -o collapse,mean
+	chr1 10  20  A   B.1,B.2,    5500
+
+	$ cat ex1.out | groupBy -g 1,2,3,4 -c 10 -o concat
+	chr1 10  20  A   ATATCGCG
+
+Notes: 
+	(1)  The input file/stream should be sorted/grouped by the -grp. columns
+	(2)  If -i is unspecified, input is assumed to come from stdin.
+
diff --git a/src/bedtools/bedtools_groupby/script.sh b/src/bedtools/bedtools_groupby/script.sh
new file mode 100644
index 00000000..b8a40cdc
--- /dev/null
+++ b/src/bedtools/bedtools_groupby/script.sh
@@ -0,0 +1,36 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+# Exit on error
+set -eo pipefail
+
+# Unset parameters
+unset_if_false=(
+    par_full
+    par_inheader
+    par_outheader
+    par_header
+    par_ignorecase
+)
+
+for par in ${unset_if_false[@]}; do
+    test_val="${!par}"
+    [[ "$test_val" == "false" ]] && unset $par
+done
+
+bedtools groupby \
+    ${par_full:+-full} \
+    ${par_inheader:+-inheader} \
+    ${par_outheader:+-outheader} \
+    ${par_header:+-header} \
+    ${par_ignorecase:+-ignorecase} \
+    ${par_precision:+-prec "$par_precision"} \
+    ${par_delimiter:+-delim "$par_delimiter"} \
+    -i "$par_input" \
+    -g "$par_groupby" \
+    -c "$par_column" \
+    ${par_operation:+-o "$par_operation"} \
+    > "$par_output"
+    
\ No newline at end of file
diff --git a/src/bedtools/bedtools_groupby/test.sh b/src/bedtools/bedtools_groupby/test.sh
new file mode 100644
index 00000000..ce99a1ec
--- /dev/null
+++ b/src/bedtools/bedtools_groupby/test.sh
@@ -0,0 +1,198 @@
+#!/bin/bash
+
+# exit on error
+set -eo pipefail
+
+## VIASH START
+meta_executable="target/executable/bedtools/bedtools_groupby/bedtools_groupby"
+meta_resources_dir="src/bedtools/bedtools_groupby"
+## VIASH END
+
+#############################################
+# helper functions
+assert_file_exists() {
+  [ -f "$1" ] || { echo "File '$1' does not exist" && exit 1; }
+}
+assert_file_not_empty() {
+  [ -s "$1" ] || { echo "File '$1' is empty but shouldn't be" && exit 1; }
+}
+assert_file_contains() {
+  grep -q "$2" "$1" || { echo "File '$1' does not contain '$2'" && exit 1; }
+}
+assert_identical_content() {
+  diff -a "$2" "$1" \
+    || (echo "Files are not identical!" && exit 1)
+}
+#############################################
+
+# Create directories for tests
+echo "Creating Test Data..."
+TMPDIR=$(mktemp -d "$meta_temp_dir/XXXXXX")
+function clean_up {
+  [[ -d "$TMPDIR" ]] && rm -r "$TMPDIR"
+}
+trap clean_up EXIT
+
+# Create and populate example.bed
+cat << EOF > $TMPDIR/example.bed
+# Header
+chr21	9719758	9729320	variant1	chr21	9719768	9721892	ALR/Alpha	1004	+
+chr21	9719758	9729320	variant1	chr21	9721905	9725582	ALR/Alpha	1010	+
+chr21	9719758	9729320	variant1	chr21	9725582	9725977	L1PA3	3288	+
+chr21	9719758	9729320	variant1	chr21	9726021	9729309	ALR/Alpha	1051	+
+chr21	9729310	9757478	variant2	chr21	9729320	9729809	L1PA3	3897	-
+chr21	9729310	9757478	variant2	chr21	9729809	9730866	L1P1	8367	+
+chr21	9729310	9757478	variant2	chr21	9730866	9734026	ALR/Alpha	1036	-
+chr21	9729310	9757478	variant2	chr21	9734037	9757471	ALR/Alpha	1182	-
+chr21	9795588	9796685	variant3	chr21	9795589	9795713	(GAATG)n	308	+
+chr21	9795588	9796685	variant3	chr21	9795736	9795894	(GAATG)n	683	+
+chr21	9795588	9796685	variant3	chr21	9795911	9796007	(GAATG)n	345	+
+chr21	9795588	9796685	variant3	chr21	9796028	9796187	(GAATG)n	756	+
+chr21	9795588	9796685	variant3	chr21	9796202	9796615	(GAATG)n	891	+
+chr21	9795588	9796685	variant3	chr21	9796637	9796824	(GAATG)n	621	+
+EOF
+
+# Create and populate expected output files for different tests
+cat << EOF > $TMPDIR/expected.bed
+chr21	9719758	9729320	6353
+chr21	9729310	9757478	14482
+chr21	9795588	9796685	3604
+EOF
+cat << EOF > $TMPDIR/expected_max.bed
+chr21	9719758	9729320	variant1	3288
+chr21	9729310	9757478	variant2	8367
+chr21	9795588	9796685	variant3	891
+EOF
+cat << EOF > $TMPDIR/expected_full.bed
+chr21	9719758	9729320	variant1	chr21	9719768	9721892	ALR/Alpha	1004	+	6353
+chr21	9729310	9757478	variant2	chr21	9729320	9729809	L1PA3	3897	-	14482
+chr21	9795588	9796685	variant3	chr21	9795589	9795713	(GAATG)n	308	+	3604
+EOF
+cat << EOF > $TMPDIR/expected_delimited.bed
+chr21	9719758	9729320	variant1	1004;1010;3288;1051
+chr21	9729310	9757478	variant2	3897;8367;1036;1182
+chr21	9795588	9796685	variant3	308;683;345;756;891;621
+EOF
+cat << EOF > $TMPDIR/expected_precision.bed
+chr21	9719758	9729320	variant1	1.6e+03
+chr21	9729310	9757478	variant2	3.6e+03
+chr21	9795588	9796685	variant3	6e+02
+EOF
+
+# Test 1: without operation option, default operation is sum
+mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
+
+echo "> Run bedtools groupby on BED file"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1,2,3" \
+  --column "9" \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected.bed"
+echo "- test1 succeeded -"
+
+popd > /dev/null
+
+# Test 2: with operation max option
+mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
+
+echo "> Run bedtools groupby on BED file with max operation"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1-4" \
+  --column "9" \
+  --operation "max" \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_max.bed"
+echo "- test2 succeeded -"
+
+popd > /dev/null
+
+# Test 3: full option
+mkdir "$TMPDIR/test3" && pushd "$TMPDIR/test3" > /dev/null
+
+echo "> Run bedtools groupby on BED file with full option"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1-4" \
+  --column "9" \
+  --full \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_full.bed"
+echo "- test3 succeeded -"
+
+popd > /dev/null
+
+# Test 4: header option
+mkdir "$TMPDIR/test4" && pushd "$TMPDIR/test4" > /dev/null
+
+echo "> Run bedtools groupby on BED file with header option"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1-4" \
+  --column "9" \
+  --header \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_file_contains "output.bed" "# Header"
+echo "- test4 succeeded -"
+
+popd > /dev/null
+
+# Test 5: Delimiter and collapse
+mkdir "$TMPDIR/test5" && pushd "$TMPDIR/test5" > /dev/null
+
+echo "> Run bedtools groupby on BED file with delimiter and collapse options"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1-4" \
+  --column "9" \
+  --operation "collapse" \
+  --delimiter ";" \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_delimited.bed"
+echo "- test5 succeeded -"
+
+popd > /dev/null
+
+# Test 6: precision option
+mkdir "$TMPDIR/test6" && pushd "$TMPDIR/test6" > /dev/null
+
+echo "> Run bedtools groupby on BED file with precision option"
+"$meta_executable" \
+  --input "../example.bed" \
+  --groupby "1-4" \
+  --column "9" \
+  --operation "mean" \
+  --precision 2 \
+  --output "output.bed"
+
+# checks
+assert_file_exists "output.bed"
+assert_file_not_empty "output.bed"
+assert_identical_content "output.bed" "../expected_precision.bed"
+echo "- test6 succeeded -"
+
+popd > /dev/null
+
+echo "---- All tests succeeded! ----"
+exit 0