Merge branch 'main' into bcftools_sort

CHANGELOG.md

@@ -29,8 +29,12 @@
 * `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).
+  - `bedtools/bedtools_bed12tobed6`: Converts BED12 files to BED6 files (PR #140).
+  - `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). 
 

src/bedtools/bedtools_bed12tobed6/config.vsh.yaml

@@ -0,0 +1,67 @@
+name: bedtools_bed12tobed6
+namespace: bedtools
+description: | 
+  Converts BED features in BED12 (a.k.a. “blocked” BED features such as genes) to discrete BED6 features.
+  For example, in the case of a gene with six exons, bed12ToBed6 would create six separate BED6 features (i.e., one for each exon).
+keywords: [Converts, BED12, BED6]
+links:
+  documentation: https://bedtools.readthedocs.io/en/latest/content/tools/bed12tobed6.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 BED12 file.
+        required: true
+
+  - name: Outputs
+    arguments:
+      - name: --output
+        alternatives: -o
+        type: file
+        direction: output
+        description: Output BED6 file to be written.
+
+  - name: Options
+    arguments:
+      - name: --n_score
+        alternatives: -n
+        type: boolean_true
+        description: | 
+          Force the score to be the (1-based) block number from the BED12.
+
+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

src/bedtools/bedtools_bed12tobed6/help.txt

@@ -0,0 +1,13 @@
+```
+bedtools bed12tobed6 -h
+```
+
+Tool:    bedtools bed12tobed6 (aka bed12ToBed6)
+Version: v2.30.0
+Summary: Splits BED12 features into discrete BED6 features.
+
+Usage:   bedtools bed12tobed6 [OPTIONS] -i <bed12>
+
+Options: 
+	-n	Force the score to be the (1-based) block number from the BED12.
+

src/bedtools/bedtools_bed12tobed6/script.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -eo pipefail
+
+# Unset parameters
+[[ "$par_n_score" == "false" ]] && unset par_n_score
+
+# Execute bedtools bed12tobed6 conversion 
+bedtools bed12tobed6 \
+    ${par_n_score:+-n} \
+    -i "$par_input" \
+    > "$par_output"

src/bedtools/bedtools_bed12tobed6/test.sh

@@ -0,0 +1,85 @@
+#!/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 "$TMPDIR"
+}
+trap clean_up EXIT
+
+# Create example BED12 file
+cat <<EOF > "$TMPDIR/example.bed12"
+chr21	10079666	10120808	uc002yiv.1	0	-	10081686	1	0	1	2	0	6	0	8	0	4	528,91,101,215,	0,1930,39750,40927,
+chr21	10080031	10081687	uc002yiw.1	0	-	10080031	1	0	0	8	0	0	3	1	0	2	200,91,	0,1565,
+chr21	10081660	10120796	uc002yix.2	0	-	10081660	1	0	0	8	1	6	6	0	0	3	27,101,223,	0,37756,38913,
+EOF
+
+# Expected output bed6 file
+cat <<EOF > "$TMPDIR/expected.bed6"
+chr21	10079666	10120808	uc002yiv.1	0	-
+chr21	10080031	10081687	uc002yiw.1	0	-
+chr21	10081660	10120796	uc002yix.2	0	-
+EOF
+# Expected output bed6 file with -n option
+cat <<EOF > "$TMPDIR/expected_n.bed6"
+chr21	10079666	10120808	uc002yiv.1	1	-
+chr21	10080031	10081687	uc002yiw.1	1	-
+chr21	10081660	10120796	uc002yix.2	1	-
+EOF
+
+# Test 1: Default conversion BED12 to BED6
+mkdir "$TMPDIR/test1" && pushd "$TMPDIR/test1" > /dev/null
+
+echo "> Run bedtools_bed12tobed6 on BED12 file"
+"$meta_executable" \
+  --input "../example.bed12" \
+  --output "output.bed6"
+
+# checks
+assert_file_exists "output.bed6"
+assert_file_not_empty "output.bed6"
+assert_identical_content "output.bed6" "../expected.bed6"
+echo "- test1 succeeded -"
+
+popd > /dev/null
+
+# Test 2: Conversion BED12 to BED6 with -n option
+mkdir "$TMPDIR/test2" && pushd "$TMPDIR/test2" > /dev/null
+
+echo "> Run bedtools_bed12tobed6 on BED12 file with -n option"
+"$meta_executable" \
+  --input "../example.bed12" \
+  --output "output.bed6" \
+  --n_score
+
+# checks
+assert_file_exists "output.bed6"
+assert_file_not_empty "output.bed6"
+assert_identical_content "output.bed6" "../expected_n.bed6"
+echo "- test2 succeeded -"
+
+popd > /dev/null
+
+echo "---- All tests succeeded! ----"
+exit 0

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