From 38f586bec0ac9e4312b016e29c3aa0bd53f292b2 Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Thu, 11 Apr 2024 11:04:14 +0100
Subject: [PATCH 1/5] initial commit dedup

---
 CHANGELOG.md                                  |   3 +
 src/umi_tools/umi_tools_dedup/config.vsh.yaml | 279 ++++++++++++++++++
 src/umi_tools/umi_tools_dedup/help.txt        |  13 +
 src/umi_tools/umi_tools_dedup/script.sh       |  65 ++++
 src/umi_tools/umi_tools_dedup/test.sh         |  49 +++
 5 files changed, 409 insertions(+)
 create mode 100644 src/umi_tools/umi_tools_dedup/config.vsh.yaml
 create mode 100644 src/umi_tools/umi_tools_dedup/help.txt
 create mode 100644 src/umi_tools/umi_tools_dedup/script.sh
 create mode 100644 src/umi_tools/umi_tools_dedup/test.sh

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4fd7f001..1bef9345 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -39,6 +39,9 @@
     - `samtools/flagstat`: Counts the number of alignments in SAM/BAM/CRAM files for each FLAG type (PR #31).
     - `samtools/idxstats`: Reports alignment summary statistics for a SAM/BAM/CRAM file (PR #32).
 
+* `umi_tools`:
+    - `umi_tools/umi_tools_dedup`: Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read (PR #).
+    
 ## MAJOR CHANGES
 
 ## MINOR CHANGES
diff --git a/src/umi_tools/umi_tools_dedup/config.vsh.yaml b/src/umi_tools/umi_tools_dedup/config.vsh.yaml
new file mode 100644
index 00000000..75306541
--- /dev/null
+++ b/src/umi_tools/umi_tools_dedup/config.vsh.yaml
@@ -0,0 +1,279 @@
+name: umi_tool_dedup
+namespace: umi_tools
+description: |
+  Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read.
+keywords: [umi_tools, deduplication, dedup]
+links:
+  homepage: https://umi-tools.readthedocs.io/en/latest/
+  documentation: [ https://umi-tools.readthedocs.io/en/latest/reference/dedup.html,
+                   https://umi-tools.readthedocs.io/en/latest/common_options.html#common-options ]
+  repository: https://github.com/CGATOxford/UMI-tools
+references: 
+  doi: 10.1101/gr.209601.116
+license: MIT
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        alternatives: -I
+        type: file
+        description: Input BAM or SAM file. Use --in_sam to specify SAM format.
+        required: true
+      - name: --in_sam
+        type: boolean_true
+        description: |
+          By default, inputs are assumed to be in BAM format. Use this options 
+          to specify the use of SAM format for input.
+      - name: --bai
+        type: file
+        description: BAM index
+      - name: --get_output_stats
+        type: boolean
+        description: Whether or not to generate output stats. 
+      - name: --random_seed
+        type: integer
+        description: |
+          Random seed to initialize number generator with.
+        default: none
+
+  - name: Outputs
+    arguments:
+      - name: --output
+        alternatives: -S
+        type: file
+        description: Deduplicated BAM file
+        required: true
+        direction: output
+      - name: --out_sam
+        type: boolean_true
+        description: |
+          By default, outputa are written in BAM format. Use this options to 
+          specify the use of SAM format for output.
+      - name: --paired
+        type: boolean_true
+        description: |
+          BAM is paired end - output both read pairs. This will also force the
+          use of the template length to determine reads with the same mapping
+          coordinates.
+      - name: --output_stats
+        type: file
+        description: Directory containing UMI based deduplication statistics files
+        direction: output
+      - name: --extract_umi_method
+        type: string
+        description: |
+          Specify the method by which the barcodes were encoded in the read.
+          The options are: [read_id, tag, umis].
+        default: read_id
+      - name: --umi_tag
+        type: string
+        description: |
+          The tag containing the UMI sequence. 
+          This is only required if the extract_umi_method is set to tag.
+      - name: --umi_separator
+        type: string
+        description: |
+          The separator used to separate the UMI from the read sequence. 
+          This is only required if the extract_umi_method is set to id_read.
+        default: '_'
+      - name: --umi_tag_split
+        type: string
+        description: |
+          Separate the UMI in tag by <SPLIT> and take the first element.
+      - name: --umi_tag_delimiter
+        type: string
+        description: |
+          Separate the UMI in by <DELIMITER> and concatenate the elements
+      - name: --cell_tag
+        type: string
+        description: |
+          The tag containing the cell barcode sequence. 
+          This is only required if the extract_umi_method is set to tag.
+      - name: --cell_tag_split
+        type: string
+        description: |
+          Separate the cell barcode in tag by <SPLIT> and take the first element.
+      - name: --cell_tag_delimiter
+        type: string
+        description: |
+          Separate the cell barcode in by <DELIMITER> and concatenate the elements
+  
+  - name: Grouping Options
+    arguments:    
+      - name: --method
+        type: string
+        description: |
+          The method to use for grouping reads. The options are: 
+          [unique, percentile, cluster, adjacency, directional].
+        default: directional
+      - name: --edit_distance_threshold
+        type: integer
+        description: |
+          For the adjacency and cluster methods the threshold for the edit 
+          distance to connect two UMIs in the network can be increased. The 
+          default value of 1 works best unless the UMI is very long (>14bp).
+        default: 1
+      - name: --spliced_is_unique
+        type: boolean_true
+        description: |
+          Causes two reads that start in the same position on the same strand
+          and having the same UMI to be considered unique if one is spliced 
+          and the other is not. (Uses the ‘N’ cigar operation to test for splicing).
+      - name: --soft_clip_threshold
+        type: integer
+        description: |
+          Mappers that soft clip will sometimes do so rather than mapping a
+          spliced read if there is only a small overhang over the exon junction.
+          By setting this option, you can treat reads with at least this many
+          bases soft-clipped at the 3’ end as spliced.
+        default: 4
+      - name: --multimapping_detection_method
+        type: string
+        description: |
+          If the sam/bam contains tags to identify multimapping reads, you can
+          specify for use when selecting the best read at a given loci. Supported
+          tags are “NH”, “X0” and “XT”. If not specified, the read with the highest
+          mapping quality will be selected.
+      - name: --read_length
+        type: integer
+        description: |
+          Use the read length as a criteria when deduping, for e.g sRNA-Seq.
+  
+  - name: Single-cell RNA-Seq Options
+    arguments:
+      - name: --per_gene
+        type: boolean_true
+        description: |
+          Reads will be grouped together if they have the same gene. This is useful
+          if your library prep generates PCR duplicates with non identical alignment
+          positions such as CEL-Seq. Note this option is hardcoded to be on with the
+          count command. I.e counting is always performed per-gene. Must be combined
+          with either --gene_tag or --per_contig option.
+      - name: --gene_tag
+        type: string
+        description: |
+          Deduplicate per gene. The gene information is encoded in the bam read tag
+          specified.
+      - name: --assigned_status_tag
+        type: string
+        description: |
+          BAM tag which describes whether a read is assigned to a gene. Defaults to
+          the same value as given for --gene_tag.
+      - name: --skip_tags_regex
+        type: string
+        description: |
+          Use in conjunction with the --assigned_status_tag option to skip any reads
+          where the tag matches this regex. Default ("^[__|Unassigned]") matches
+          anything which starts with “__” or “Unassigned”.
+      - name: --per_contig
+        type: boolean_true
+        description: |
+          Deduplicate per contig (field 3 in BAM; RNAME). All reads with the same
+          contig will be considered to have the same alignment position. This is
+          useful if you have aligned to a reference transcriptome with one
+          transcript per gene. If you have aligned to a transcriptome with more
+          than one transcript per gene, you can supply a map between transcripts
+          and gene using the --gene_transcript_map option.
+      - name: --gene_transcript_map
+        type: file
+        description: |
+          A file containing a mapping between gene names and transcript names.
+          The file should be tab separated with the gene name in the first column
+          and the transcript name in the second column.
+      - name: --per_cell
+        type: boolean_true
+        description: |
+          Reads will only be grouped together if they have the same cell barcode.
+          Can be combined with --per_gene.
+  
+  - name: SAM/BAM Options
+    arguments:
+      - name: --mapping_quality
+        type: integer
+        description: |
+          Minimium mapping quality (MAPQ) for a read to be retained.
+        default: 0
+      - name: --unmapped_reads
+        type: string
+        description: |
+          How unmapped reads should be handled. 
+          The options are:
+          "discard": Discard all unmapped reads.
+          "use":     If read2 is unmapped, deduplicate using read1 only. 
+                     Requires --paired.
+          "output":  Output unmapped reads/read pairs without UMI 
+                     grouping/deduplication. Only available in umi_tools group.
+        default: discard
+      - name: --chimeric_pairs
+        type: string
+        description: |
+          How chimeric pairs should be handled. 
+          The options are:
+          "discard": Discard all chimeric read pairs.
+          "use":     Deduplicate using read1 only.
+          "output":  Output chimeric pairs without UMI grouping/deduplication. 
+                     Only available in umi_tools group.
+        default: use
+      - name: --unapired_reads
+        type: string
+        description: |
+          How unpaired reads should be handled. 
+          The options are:
+          "discard": Discard all unpaired reads.
+          "use":     Deduplicate using read1 only.
+          "output":  Output unpaired reads without UMI grouping/deduplication. 
+                     Only available in umi_tools group.
+        default: use
+      - name: --ignore_umi
+        type: boolean_true
+        description: |
+          Ignore the UMI and group reads using mapping coordinates only.
+      - name: --subset
+        type: boolean_true
+        description: |
+          Only consider a fraction of the reads, chosen at random. This is useful
+          for doing saturation analyses.
+      - name: --chrom
+        type: string
+        description: |
+          Only consider a single chromosome. This is useful for debugging/testing 
+          purposes.
+  
+  - name: Group/Dedup Options
+    arguments:
+      - name: --no_sort_output
+        type: boolean_true
+        description: |
+          By default, output is sorted. This involves the use of a temporary unsorted
+          file (saved in --temp-dir). Use this option to turn off sorting.
+      - name: --buffer_whole_contig
+        type: boolean_true
+        description: |
+          Forces dedup to parse an entire contig before yielding any reads for
+          deduplication. This is the only way to absolutely guarantee that all reads
+          with the same start position are grouped together for deduplication since
+          dedup uses the start position of the read, not the alignment coordinate on
+          which the reads are sorted. However, by default, dedup reads for another
+          1000bp before outputting read groups which will avoid any reads being missed
+          with short read sequencing (<1000bp).
+
+
+resources:
+  - type: bash_script
+    path: script.sh
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - type: file
+    path: test_data
+engines:
+  - type: docker
+    image: quay.io/biocontainers/umi_tools:1.1.5--py39hf95cd2a_1
+    setup:
+      - type: docker
+        run: |
+            umi_tools -v | sed 's/ version//g' > /var/software_versions.txt
+runners:
+- type: executable
+- type: nextflow
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/help.txt b/src/umi_tools/umi_tools_dedup/help.txt
new file mode 100644
index 00000000..d3c8fa44
--- /dev/null
+++ b/src/umi_tools/umi_tools_dedup/help.txt
@@ -0,0 +1,13 @@
+```
+umi_tools dedup
+```
+
+dedup - Deduplicate reads using UMI and mapping coordinates
+
+Usage: umi_tools dedup [OPTIONS] [--stdin=IN_BAM] [--stdout=OUT_BAM]
+
+       note: If --stdout is ommited, standard out is output. To
+             generate a valid BAM file on standard out, please
+             redirect log with --log=LOGFILE or --log2stderr 
+
+For full UMI-tools documentation, see https://umi-tools.readthedocs.io/en/latest/
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/script.sh b/src/umi_tools/umi_tools_dedup/script.sh
new file mode 100644
index 00000000..57c01258
--- /dev/null
+++ b/src/umi_tools/umi_tools_dedup/script.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -e
+
+test_dir="${metal_executable}/test_data"
+
+[[ "$par_paired" == "false" ]] && unset par_paired
+[[ "$par_in_sam" == "false" ]] && unset par_in_sam
+[[ "$par_out_sam" == "false" ]] && unset par_out_sam
+[[ "$par_spliced_is_unique" == "false" ]] && unset par_spliced_is_unique
+[[ "$par_per_gene" == "false" ]] && unset par_per_gene
+[[ "$par_per_contig" == "false" ]] && unset par_per_contig
+[[ "$par_per_cell" == "false" ]] && unset par_per_cell
+[[ "$par_no_sort_output" == "false" ]] && unset par_no_sort_output
+[[ "$par_buffer_whole_contig" == "false" ]] && unset par_buffer_whole_contig
+[[ "$par_ignore_umi" == "false" ]] && unset par_ignore_umi
+[[ "$par_subset" == "false" ]] && unset par_subset
+
+
+$(which umi_tools) dedup \
+    -I "$par_input" \
+    ${par_in_sam:+--in-sam} \
+    ${par_bai:+--bai "$par_bai"} \
+    ${par_get_output_stats:+--get-output-stats} \
+    ${par_random_seed:+--random-seed "$par_random_seed"} \
+    -S "$par_output" \
+    ${par_out_sam:+--out-sam} \
+    ${par_paired:+--paired} \
+    ${par_output_stats:+--output-stats "$par_output_stats"} \
+    ${par_extract_umi_method:+--extract-umi-method "$par_extract_umi_method"} \
+    ${par_umi_tag:+--umi-tag "$par_umi_tag"} \
+    ${par_umi_separator:+--umi-separator "$par_umi_separator"} \
+    ${par_umi_tag_split:+--umi-tag-split "$par_umi_tag_split"} \
+    ${par_umi_tag_delimiter:+--umi-tag-delimiter "$par_umi_tag_delimiter"} \
+    ${par_cell_tag:+--cell-tag "$par_cell_tag"} \
+    ${par_cell_tag_split:+--cell-tag-split "$par_cell_tag_split"} \
+    ${par_cell_tag_delimiter:+--cell-tag-delimiter "$par_cell_tag_delimiter"} \
+    ${par_method:+--method "$par_method"} \
+    ${par_edit_distance_threshold:+--edit-distance-threshold "$par_edit_distance_threshold"} \
+    ${par_spliced_is_unique:+--spliced-is-unique} \
+    ${par_soft_clip_threshold:+--soft-clip-threshold "$par_soft_clip_threshold"} \
+    ${par_multimapping_detection_method:+--multimapping-detection-method "$par_multimapping_detection_method"} \
+    ${par_read_length:+--read-length "$par_read_length"} \
+    ${par_per_gene:+--per-gene} \
+    ${par_gene_tag:+--gene-tag "$par_gene_tag"} \
+    ${par_assigned_status_tag:+--assigned-status-tag "$par_assigned_status_tag"} \
+    ${par_skip_tags_regex:+--skip-tags-regex "$par_skip_tags_regex"} \
+    ${par_per_contig:+--per-contig}
+    ${par_gene_transcript_map:+--gene-transcript-map "$par_gene_transcript_map"} \
+    ${par_per_cell:+--per-cell} \
+    ${par_mapping_quality:+--mapping-quality "$par_mapping_quality"} \
+    ${par_unmapped_reads:+--unmapped-reads "$par_unmapped_reads"} \
+    ${par_chimeric_pairs:+--chimeric-pairs "$par_chimeric_pairs"} \
+    ${par_unapired_reads:+--unapired-reads "$par_unapired_reads"} \
+    ${par_ignore_umi:+--ignore-umi} \
+    ${par_subset:+--subset} \
+    ${par_chrom:+--chrom "$par_chrom"} \
+    ${par_no_sort_output:+--no-sort-output} \
+    ${par_buffer_whole_contig:+--buffer-whole-contig}
+
+
+exit 0
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/test.sh b/src/umi_tools/umi_tools_dedup/test.sh
new file mode 100644
index 00000000..1459ec08
--- /dev/null
+++ b/src/umi_tools/umi_tools_dedup/test.sh
@@ -0,0 +1,49 @@
+#!/bin/bash
+
+test_dir="${meta_resources_dir}/test_data"
+echo ">>> Testing $meta_functionality_name"
+
+"$meta_executable" \
+  --bam "$test_dir/a.sorted.bam" \
+  --bai "$test_dir/a.sorted.bam.bai" \
+  --output "$test_dir/a.sorted.idxstats"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$test_dir/a.sorted.idxstats" ] && echo "File 'a.sorted.idxstats' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$test_dir/a.sorted.idxstats" ] && echo "File 'a.sorted.idxstats' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+diff "$test_dir/a.sorted.idxstats" "$test_dir/a_ref.sorted.idxstats" || \
+    (echo "Output file a.sorted.idxstats does not match expected output" && exit 1)
+
+rm "$test_dir/a.sorted.idxstats"
+
+############################################################################################
+
+echo ">>> Testing $meta_functionality_name with singletons in the input"
+
+"$meta_executable" \
+  --bam "$test_dir/test.paired_end.sorted.bam" \
+  --bai "$test_dir/test.paired_end.sorted.bam.bai" \
+  --output "$test_dir/test.paired_end.sorted.idxstats"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$test_dir/test.paired_end.sorted.idxstats" ] && \
+    echo "File 'test.paired_end.sorted.idxstats' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$test_dir/test.paired_end.sorted.idxstats" ] && \
+    echo "File 'test.paired_end.sorted.idxstats' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+diff "$test_dir/test.paired_end.sorted.idxstats" "$test_dir/test_ref.paired_end.sorted.idxstats" || \
+    (echo "Output file test.paired_end.sorted.idxstats does not match expected output" && exit 1)
+
+rm "$test_dir/test.paired_end.sorted.idxstats"
+
+############################################################################################
+
+echo "All tests succeeded!"
+exit 0
\ No newline at end of file

From 2c269682620a407803e528652198646435ef2c03 Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Thu, 11 Apr 2024 11:38:57 +0100
Subject: [PATCH 2/5] Revert "initial commit dedup"

This reverts commit 38f586bec0ac9e4312b016e29c3aa0bd53f292b2.
---
 CHANGELOG.md                                  |   3 -
 src/umi_tools/umi_tools_dedup/config.vsh.yaml | 279 ------------------
 src/umi_tools/umi_tools_dedup/help.txt        |  13 -
 src/umi_tools/umi_tools_dedup/script.sh       |  65 ----
 src/umi_tools/umi_tools_dedup/test.sh         |  49 ---
 5 files changed, 409 deletions(-)
 delete mode 100644 src/umi_tools/umi_tools_dedup/config.vsh.yaml
 delete mode 100644 src/umi_tools/umi_tools_dedup/help.txt
 delete mode 100644 src/umi_tools/umi_tools_dedup/script.sh
 delete mode 100644 src/umi_tools/umi_tools_dedup/test.sh

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1bef9345..4fd7f001 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -39,9 +39,6 @@
     - `samtools/flagstat`: Counts the number of alignments in SAM/BAM/CRAM files for each FLAG type (PR #31).
     - `samtools/idxstats`: Reports alignment summary statistics for a SAM/BAM/CRAM file (PR #32).
 
-* `umi_tools`:
-    - `umi_tools/umi_tools_dedup`: Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read (PR #).
-    
 ## MAJOR CHANGES
 
 ## MINOR CHANGES
diff --git a/src/umi_tools/umi_tools_dedup/config.vsh.yaml b/src/umi_tools/umi_tools_dedup/config.vsh.yaml
deleted file mode 100644
index 75306541..00000000
--- a/src/umi_tools/umi_tools_dedup/config.vsh.yaml
+++ /dev/null
@@ -1,279 +0,0 @@
-name: umi_tool_dedup
-namespace: umi_tools
-description: |
-  Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read.
-keywords: [umi_tools, deduplication, dedup]
-links:
-  homepage: https://umi-tools.readthedocs.io/en/latest/
-  documentation: [ https://umi-tools.readthedocs.io/en/latest/reference/dedup.html,
-                   https://umi-tools.readthedocs.io/en/latest/common_options.html#common-options ]
-  repository: https://github.com/CGATOxford/UMI-tools
-references: 
-  doi: 10.1101/gr.209601.116
-license: MIT
-
-argument_groups:
-  - name: Inputs
-    arguments:
-      - name: --input
-        alternatives: -I
-        type: file
-        description: Input BAM or SAM file. Use --in_sam to specify SAM format.
-        required: true
-      - name: --in_sam
-        type: boolean_true
-        description: |
-          By default, inputs are assumed to be in BAM format. Use this options 
-          to specify the use of SAM format for input.
-      - name: --bai
-        type: file
-        description: BAM index
-      - name: --get_output_stats
-        type: boolean
-        description: Whether or not to generate output stats. 
-      - name: --random_seed
-        type: integer
-        description: |
-          Random seed to initialize number generator with.
-        default: none
-
-  - name: Outputs
-    arguments:
-      - name: --output
-        alternatives: -S
-        type: file
-        description: Deduplicated BAM file
-        required: true
-        direction: output
-      - name: --out_sam
-        type: boolean_true
-        description: |
-          By default, outputa are written in BAM format. Use this options to 
-          specify the use of SAM format for output.
-      - name: --paired
-        type: boolean_true
-        description: |
-          BAM is paired end - output both read pairs. This will also force the
-          use of the template length to determine reads with the same mapping
-          coordinates.
-      - name: --output_stats
-        type: file
-        description: Directory containing UMI based deduplication statistics files
-        direction: output
-      - name: --extract_umi_method
-        type: string
-        description: |
-          Specify the method by which the barcodes were encoded in the read.
-          The options are: [read_id, tag, umis].
-        default: read_id
-      - name: --umi_tag
-        type: string
-        description: |
-          The tag containing the UMI sequence. 
-          This is only required if the extract_umi_method is set to tag.
-      - name: --umi_separator
-        type: string
-        description: |
-          The separator used to separate the UMI from the read sequence. 
-          This is only required if the extract_umi_method is set to id_read.
-        default: '_'
-      - name: --umi_tag_split
-        type: string
-        description: |
-          Separate the UMI in tag by <SPLIT> and take the first element.
-      - name: --umi_tag_delimiter
-        type: string
-        description: |
-          Separate the UMI in by <DELIMITER> and concatenate the elements
-      - name: --cell_tag
-        type: string
-        description: |
-          The tag containing the cell barcode sequence. 
-          This is only required if the extract_umi_method is set to tag.
-      - name: --cell_tag_split
-        type: string
-        description: |
-          Separate the cell barcode in tag by <SPLIT> and take the first element.
-      - name: --cell_tag_delimiter
-        type: string
-        description: |
-          Separate the cell barcode in by <DELIMITER> and concatenate the elements
-  
-  - name: Grouping Options
-    arguments:    
-      - name: --method
-        type: string
-        description: |
-          The method to use for grouping reads. The options are: 
-          [unique, percentile, cluster, adjacency, directional].
-        default: directional
-      - name: --edit_distance_threshold
-        type: integer
-        description: |
-          For the adjacency and cluster methods the threshold for the edit 
-          distance to connect two UMIs in the network can be increased. The 
-          default value of 1 works best unless the UMI is very long (>14bp).
-        default: 1
-      - name: --spliced_is_unique
-        type: boolean_true
-        description: |
-          Causes two reads that start in the same position on the same strand
-          and having the same UMI to be considered unique if one is spliced 
-          and the other is not. (Uses the ‘N’ cigar operation to test for splicing).
-      - name: --soft_clip_threshold
-        type: integer
-        description: |
-          Mappers that soft clip will sometimes do so rather than mapping a
-          spliced read if there is only a small overhang over the exon junction.
-          By setting this option, you can treat reads with at least this many
-          bases soft-clipped at the 3’ end as spliced.
-        default: 4
-      - name: --multimapping_detection_method
-        type: string
-        description: |
-          If the sam/bam contains tags to identify multimapping reads, you can
-          specify for use when selecting the best read at a given loci. Supported
-          tags are “NH”, “X0” and “XT”. If not specified, the read with the highest
-          mapping quality will be selected.
-      - name: --read_length
-        type: integer
-        description: |
-          Use the read length as a criteria when deduping, for e.g sRNA-Seq.
-  
-  - name: Single-cell RNA-Seq Options
-    arguments:
-      - name: --per_gene
-        type: boolean_true
-        description: |
-          Reads will be grouped together if they have the same gene. This is useful
-          if your library prep generates PCR duplicates with non identical alignment
-          positions such as CEL-Seq. Note this option is hardcoded to be on with the
-          count command. I.e counting is always performed per-gene. Must be combined
-          with either --gene_tag or --per_contig option.
-      - name: --gene_tag
-        type: string
-        description: |
-          Deduplicate per gene. The gene information is encoded in the bam read tag
-          specified.
-      - name: --assigned_status_tag
-        type: string
-        description: |
-          BAM tag which describes whether a read is assigned to a gene. Defaults to
-          the same value as given for --gene_tag.
-      - name: --skip_tags_regex
-        type: string
-        description: |
-          Use in conjunction with the --assigned_status_tag option to skip any reads
-          where the tag matches this regex. Default ("^[__|Unassigned]") matches
-          anything which starts with “__” or “Unassigned”.
-      - name: --per_contig
-        type: boolean_true
-        description: |
-          Deduplicate per contig (field 3 in BAM; RNAME). All reads with the same
-          contig will be considered to have the same alignment position. This is
-          useful if you have aligned to a reference transcriptome with one
-          transcript per gene. If you have aligned to a transcriptome with more
-          than one transcript per gene, you can supply a map between transcripts
-          and gene using the --gene_transcript_map option.
-      - name: --gene_transcript_map
-        type: file
-        description: |
-          A file containing a mapping between gene names and transcript names.
-          The file should be tab separated with the gene name in the first column
-          and the transcript name in the second column.
-      - name: --per_cell
-        type: boolean_true
-        description: |
-          Reads will only be grouped together if they have the same cell barcode.
-          Can be combined with --per_gene.
-  
-  - name: SAM/BAM Options
-    arguments:
-      - name: --mapping_quality
-        type: integer
-        description: |
-          Minimium mapping quality (MAPQ) for a read to be retained.
-        default: 0
-      - name: --unmapped_reads
-        type: string
-        description: |
-          How unmapped reads should be handled. 
-          The options are:
-          "discard": Discard all unmapped reads.
-          "use":     If read2 is unmapped, deduplicate using read1 only. 
-                     Requires --paired.
-          "output":  Output unmapped reads/read pairs without UMI 
-                     grouping/deduplication. Only available in umi_tools group.
-        default: discard
-      - name: --chimeric_pairs
-        type: string
-        description: |
-          How chimeric pairs should be handled. 
-          The options are:
-          "discard": Discard all chimeric read pairs.
-          "use":     Deduplicate using read1 only.
-          "output":  Output chimeric pairs without UMI grouping/deduplication. 
-                     Only available in umi_tools group.
-        default: use
-      - name: --unapired_reads
-        type: string
-        description: |
-          How unpaired reads should be handled. 
-          The options are:
-          "discard": Discard all unpaired reads.
-          "use":     Deduplicate using read1 only.
-          "output":  Output unpaired reads without UMI grouping/deduplication. 
-                     Only available in umi_tools group.
-        default: use
-      - name: --ignore_umi
-        type: boolean_true
-        description: |
-          Ignore the UMI and group reads using mapping coordinates only.
-      - name: --subset
-        type: boolean_true
-        description: |
-          Only consider a fraction of the reads, chosen at random. This is useful
-          for doing saturation analyses.
-      - name: --chrom
-        type: string
-        description: |
-          Only consider a single chromosome. This is useful for debugging/testing 
-          purposes.
-  
-  - name: Group/Dedup Options
-    arguments:
-      - name: --no_sort_output
-        type: boolean_true
-        description: |
-          By default, output is sorted. This involves the use of a temporary unsorted
-          file (saved in --temp-dir). Use this option to turn off sorting.
-      - name: --buffer_whole_contig
-        type: boolean_true
-        description: |
-          Forces dedup to parse an entire contig before yielding any reads for
-          deduplication. This is the only way to absolutely guarantee that all reads
-          with the same start position are grouped together for deduplication since
-          dedup uses the start position of the read, not the alignment coordinate on
-          which the reads are sorted. However, by default, dedup reads for another
-          1000bp before outputting read groups which will avoid any reads being missed
-          with short read sequencing (<1000bp).
-
-
-resources:
-  - type: bash_script
-    path: script.sh
-test_resources:
-  - type: bash_script
-    path: test.sh
-  - type: file
-    path: test_data
-engines:
-  - type: docker
-    image: quay.io/biocontainers/umi_tools:1.1.5--py39hf95cd2a_1
-    setup:
-      - type: docker
-        run: |
-            umi_tools -v | sed 's/ version//g' > /var/software_versions.txt
-runners:
-- type: executable
-- type: nextflow
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/help.txt b/src/umi_tools/umi_tools_dedup/help.txt
deleted file mode 100644
index d3c8fa44..00000000
--- a/src/umi_tools/umi_tools_dedup/help.txt
+++ /dev/null
@@ -1,13 +0,0 @@
-```
-umi_tools dedup
-```
-
-dedup - Deduplicate reads using UMI and mapping coordinates
-
-Usage: umi_tools dedup [OPTIONS] [--stdin=IN_BAM] [--stdout=OUT_BAM]
-
-       note: If --stdout is ommited, standard out is output. To
-             generate a valid BAM file on standard out, please
-             redirect log with --log=LOGFILE or --log2stderr 
-
-For full UMI-tools documentation, see https://umi-tools.readthedocs.io/en/latest/
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/script.sh b/src/umi_tools/umi_tools_dedup/script.sh
deleted file mode 100644
index 57c01258..00000000
--- a/src/umi_tools/umi_tools_dedup/script.sh
+++ /dev/null
@@ -1,65 +0,0 @@
-#!/bin/bash
-
-## VIASH START
-## VIASH END
-
-set -e
-
-test_dir="${metal_executable}/test_data"
-
-[[ "$par_paired" == "false" ]] && unset par_paired
-[[ "$par_in_sam" == "false" ]] && unset par_in_sam
-[[ "$par_out_sam" == "false" ]] && unset par_out_sam
-[[ "$par_spliced_is_unique" == "false" ]] && unset par_spliced_is_unique
-[[ "$par_per_gene" == "false" ]] && unset par_per_gene
-[[ "$par_per_contig" == "false" ]] && unset par_per_contig
-[[ "$par_per_cell" == "false" ]] && unset par_per_cell
-[[ "$par_no_sort_output" == "false" ]] && unset par_no_sort_output
-[[ "$par_buffer_whole_contig" == "false" ]] && unset par_buffer_whole_contig
-[[ "$par_ignore_umi" == "false" ]] && unset par_ignore_umi
-[[ "$par_subset" == "false" ]] && unset par_subset
-
-
-$(which umi_tools) dedup \
-    -I "$par_input" \
-    ${par_in_sam:+--in-sam} \
-    ${par_bai:+--bai "$par_bai"} \
-    ${par_get_output_stats:+--get-output-stats} \
-    ${par_random_seed:+--random-seed "$par_random_seed"} \
-    -S "$par_output" \
-    ${par_out_sam:+--out-sam} \
-    ${par_paired:+--paired} \
-    ${par_output_stats:+--output-stats "$par_output_stats"} \
-    ${par_extract_umi_method:+--extract-umi-method "$par_extract_umi_method"} \
-    ${par_umi_tag:+--umi-tag "$par_umi_tag"} \
-    ${par_umi_separator:+--umi-separator "$par_umi_separator"} \
-    ${par_umi_tag_split:+--umi-tag-split "$par_umi_tag_split"} \
-    ${par_umi_tag_delimiter:+--umi-tag-delimiter "$par_umi_tag_delimiter"} \
-    ${par_cell_tag:+--cell-tag "$par_cell_tag"} \
-    ${par_cell_tag_split:+--cell-tag-split "$par_cell_tag_split"} \
-    ${par_cell_tag_delimiter:+--cell-tag-delimiter "$par_cell_tag_delimiter"} \
-    ${par_method:+--method "$par_method"} \
-    ${par_edit_distance_threshold:+--edit-distance-threshold "$par_edit_distance_threshold"} \
-    ${par_spliced_is_unique:+--spliced-is-unique} \
-    ${par_soft_clip_threshold:+--soft-clip-threshold "$par_soft_clip_threshold"} \
-    ${par_multimapping_detection_method:+--multimapping-detection-method "$par_multimapping_detection_method"} \
-    ${par_read_length:+--read-length "$par_read_length"} \
-    ${par_per_gene:+--per-gene} \
-    ${par_gene_tag:+--gene-tag "$par_gene_tag"} \
-    ${par_assigned_status_tag:+--assigned-status-tag "$par_assigned_status_tag"} \
-    ${par_skip_tags_regex:+--skip-tags-regex "$par_skip_tags_regex"} \
-    ${par_per_contig:+--per-contig}
-    ${par_gene_transcript_map:+--gene-transcript-map "$par_gene_transcript_map"} \
-    ${par_per_cell:+--per-cell} \
-    ${par_mapping_quality:+--mapping-quality "$par_mapping_quality"} \
-    ${par_unmapped_reads:+--unmapped-reads "$par_unmapped_reads"} \
-    ${par_chimeric_pairs:+--chimeric-pairs "$par_chimeric_pairs"} \
-    ${par_unapired_reads:+--unapired-reads "$par_unapired_reads"} \
-    ${par_ignore_umi:+--ignore-umi} \
-    ${par_subset:+--subset} \
-    ${par_chrom:+--chrom "$par_chrom"} \
-    ${par_no_sort_output:+--no-sort-output} \
-    ${par_buffer_whole_contig:+--buffer-whole-contig}
-
-
-exit 0
\ No newline at end of file
diff --git a/src/umi_tools/umi_tools_dedup/test.sh b/src/umi_tools/umi_tools_dedup/test.sh
deleted file mode 100644
index 1459ec08..00000000
--- a/src/umi_tools/umi_tools_dedup/test.sh
+++ /dev/null
@@ -1,49 +0,0 @@
-#!/bin/bash
-
-test_dir="${meta_resources_dir}/test_data"
-echo ">>> Testing $meta_functionality_name"
-
-"$meta_executable" \
-  --bam "$test_dir/a.sorted.bam" \
-  --bai "$test_dir/a.sorted.bam.bai" \
-  --output "$test_dir/a.sorted.idxstats"
-
-echo ">>> Checking whether output exists"
-[ ! -f "$test_dir/a.sorted.idxstats" ] && echo "File 'a.sorted.idxstats' does not exist!" && exit 1
-
-echo ">>> Checking whether output is non-empty"
-[ ! -s "$test_dir/a.sorted.idxstats" ] && echo "File 'a.sorted.idxstats' is empty!" && exit 1
-
-echo ">>> Checking whether output is correct"
-diff "$test_dir/a.sorted.idxstats" "$test_dir/a_ref.sorted.idxstats" || \
-    (echo "Output file a.sorted.idxstats does not match expected output" && exit 1)
-
-rm "$test_dir/a.sorted.idxstats"
-
-############################################################################################
-
-echo ">>> Testing $meta_functionality_name with singletons in the input"
-
-"$meta_executable" \
-  --bam "$test_dir/test.paired_end.sorted.bam" \
-  --bai "$test_dir/test.paired_end.sorted.bam.bai" \
-  --output "$test_dir/test.paired_end.sorted.idxstats"
-
-echo ">>> Checking whether output exists"
-[ ! -f "$test_dir/test.paired_end.sorted.idxstats" ] && \
-    echo "File 'test.paired_end.sorted.idxstats' does not exist!" && exit 1
-
-echo ">>> Checking whether output is non-empty"
-[ ! -s "$test_dir/test.paired_end.sorted.idxstats" ] && \
-    echo "File 'test.paired_end.sorted.idxstats' is empty!" && exit 1
-
-echo ">>> Checking whether output is correct"
-diff "$test_dir/test.paired_end.sorted.idxstats" "$test_dir/test_ref.paired_end.sorted.idxstats" || \
-    (echo "Output file test.paired_end.sorted.idxstats does not match expected output" && exit 1)
-
-rm "$test_dir/test.paired_end.sorted.idxstats"
-
-############################################################################################
-
-echo "All tests succeeded!"
-exit 0
\ No newline at end of file

From 8ad212d9315e8124b97bdecdac4924d4c4fd033a Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Sun, 29 Sep 2024 16:02:04 +0200
Subject: [PATCH 3/5] full component with two tests

---
 CHANGELOG.md                                  |   3 +
 .../rseqc_inner_distance/config.vsh.yaml      | 109 ++++++++++++++++++
 src/rseqc/rseqc_inner_distance/help.txt       |  43 +++++++
 src/rseqc/rseqc_inner_distance/script.sh      |  25 ++++
 src/rseqc/rseqc_inner_distance/test.sh        |  77 +++++++++++++
 .../rseqc_inner_distance/test_data/test.bed12 |   4 +
 .../test_data/test.paired_end.sorted.bam      | Bin 0 -> 10205 bytes
 .../test_data/test1.inner_distance.txt        |  49 ++++++++
 .../test_data/test1.inner_distance_freq.txt   | 100 ++++++++++++++++
 .../test_data/test2.inner_distance.txt        |   4 +
 .../test_data/test2.inner_distance_freq.txt   | 100 ++++++++++++++++
 11 files changed, 514 insertions(+)
 create mode 100644 src/rseqc/rseqc_inner_distance/config.vsh.yaml
 create mode 100644 src/rseqc/rseqc_inner_distance/help.txt
 create mode 100644 src/rseqc/rseqc_inner_distance/script.sh
 create mode 100644 src/rseqc/rseqc_inner_distance/test.sh
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test.bed12
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test.paired_end.sorted.bam
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance.txt
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance_freq.txt
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance.txt
 create mode 100644 src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance_freq.txt

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0613fa25..204bec22 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,9 @@
 
 * `rsem/rsem_calculate_expression`: Calculate expression levels (PR #93).
 
+* `rseqc`:
+  - `rseqc/rseqc_inner_distance`: Calculate inner distance between read pairs (PR #159).
+
 ## MINOR CHANGES
 
 * Upgrade to Viash 0.9.0.
diff --git a/src/rseqc/rseqc_inner_distance/config.vsh.yaml b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
new file mode 100644
index 00000000..1b698517
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
@@ -0,0 +1,109 @@
+name: "rseqc_inner_distance"
+namespace: "rseqc"
+description: |
+  Calculate inner distance between read pairs.
+links:
+  homepage: https://rseqc.sourceforge.net/
+  documentation: https://rseqc.sourceforge.net/#inner-distance-py
+  issue_tracker: https://github.com/MonashBioinformaticsPlatform/RSeQC/issues
+  repository: https://github.com/MonashBioinformaticsPlatform/RSeQC
+references:
+  doi: 10.1093/bioinformatics/bts356
+license: GPL-3.0
+authors:
+  - __merge__: /src/_authors/emma_rousseau.yaml
+    roles: [ author, maintainer ]
+
+argument_groups:
+- name: "Input"
+  arguments: 
+  - name: "--input"
+    type: file 
+    required: true
+    description: input alignment file in BAM or SAM format
+
+  - name: "--refgene"
+    type: file 
+    required: true
+    description: Reference gene model in bed format
+
+  - name: "--sample_size"
+    type: integer
+    example: 200000
+    description: Numer of reads sampled from SAM/BAM file, default = 200000.
+  
+  - name: "--map_qual"
+    type: integer
+    example: 30 
+    description: Minimum mapping quality (phred scaled) to determine uniquely mapped reads, default=30.
+
+  - name: "--lower_bound_size"
+    type: integer
+    example: -250 
+    description: Lower bound of inner distance (bp). This option is used for ploting histograme, default=-250.
+
+  - name: "--upper_bound_size"
+    type: integer
+    example: 250 
+    description: Upper bound of inner distance (bp). This option is used for ploting histograme, default=250.
+
+  - name: "--step_size"
+    type: integer
+    example: 5 
+    description: Step size (bp) of histograme. This option is used for plotting histogram, default=5.
+
+- name: "Output"
+  arguments: 
+  - name: "--output_prefix"
+    alternatives: ["-o"]
+    type: string
+    required: true
+    description: Rrefix of output files.
+    
+  - name: "--output_stats"
+    type: file
+    direction: output
+    description: output file (txt) with summary statistics of inner distances of paired reads
+
+  - name: "--output_dist"
+    type: file
+    direction: output
+    description: output file (txt) with inner distances of all paired reads
+
+  - name: "--output_freq"
+    type: file
+    direction: output
+    description: output file (txt) with frequencies of inner distances of all paired reads
+
+  - name: "--output_plot"
+    type: file
+    direction: output
+    description: output file (pdf) with histogram plot of of inner distances of all paired reads
+
+  - name: "--output_plot_r"
+    type: file
+    direction: output
+    description: output file (R) with script of histogram plot of of inner distances of all paired reads
+    
+resources:
+  - type: bash_script
+    path: script.sh
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - path: test_data
+  
+engines:
+- type: docker
+  image: ubuntu:22.04
+  setup:   
+    - type: apt
+      packages: [python3-pip, r-base]
+    - type: python
+      packages: [ RSeQC ]
+    - type: docker
+      run: |
+        echo "RSeQC - inner_distance.py: $(inner_distance.py --version | cut -d' ' -f2)" > /var/software_versions.txt
+runners: 
+- type: executable
+- type: nextflow
\ No newline at end of file
diff --git a/src/rseqc/rseqc_inner_distance/help.txt b/src/rseqc/rseqc_inner_distance/help.txt
new file mode 100644
index 00000000..18f97bb6
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/help.txt
@@ -0,0 +1,43 @@
+```
+inner_distance.py --help
+```
+
+Usage: inner_distance.py [options]
+
+Calculate the inner distance (insert size)  of RNA-seq fragments. 
+
+               RNA fragment
+ _________________||_________________
+|                                    |
+|                                    |
+||||||||||------------------||||||||||
+  read_1      insert_size     read_2
+
+fragment size = read_1 + insert_size + read_2
+
+
+
+Options:
+  --version             show program's version number and exit
+  -h, --help            show this help message and exit
+  -i INPUT_FILE, --input-file=INPUT_FILE
+                        Alignment file in BAM or SAM format.
+  -o OUTPUT_PREFIX, --out-prefix=OUTPUT_PREFIX
+                        Prefix of output files(s)
+  -r REF_GENE, --refgene=REF_GENE
+                        Reference gene model in BED format.
+  -k SAMPLESIZE, --sample-size=SAMPLESIZE
+                        Number of read-pairs used to estimate inner distance.
+                        default=1000000
+  -l LOWER_BOUND_SIZE, --lower-bound=LOWER_BOUND_SIZE
+                        Lower bound of inner distance (bp). This option is
+                        used for ploting histograme. default=-250
+  -u UPPER_BOUND_SIZE, --upper-bound=UPPER_BOUND_SIZE
+                        Upper bound of inner distance (bp). This option is
+                        used for plotting histogram. default=250
+  -s STEP_SIZE, --step=STEP_SIZE
+                        Step size (bp) of histograme. This option is used for
+                        plotting histogram. default=5
+  -q MAP_QUAL, --mapq=MAP_QUAL
+                        Minimum mapping quality (phred scaled) for an
+                        alignment to be called "uniquely mapped". default=30
\ No newline at end of file
diff --git a/src/rseqc/rseqc_inner_distance/script.sh b/src/rseqc/rseqc_inner_distance/script.sh
new file mode 100644
index 00000000..655f5b63
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/script.sh
@@ -0,0 +1,25 @@
+#!/bin/bash
+
+set -exo pipefail 
+
+
+inner_distance.py \
+    -i $par_input \
+    -r $par_refgene \
+    -o $par_output_prefix \
+    ${par_sample_size:+-k "${par_sample_size}"} \
+    ${par_lower_bound_size:+-l "${par_lower_bound_size}"} \
+    ${par_upper_bound_size:+-u "${par_upper_bound_size}"} \
+    ${par_step_size:+-s "${par_step_size}"} \
+    ${par_map_qual:+-q "${par_map_qual}"} \
+> stdout.txt
+
+if [[ -n $par_output_stats ]]; then head -n 2 stdout.txt > $par_output_stats; fi
+
+
+[[ -n "$par_output_dist" && -f "$par_output_prefix.inner_distance.txt" ]] && mv $par_output_prefix.inner_distance.txt $par_output_dist
+[[ -n "$par_output_plot" && -f "$par_output_prefix.inner_distance_plot.pdf" ]] && mv $par_output_prefix.inner_distance_plot.pdf $par_output_plot
+[[ -n "$par_output_plot_r" && -f "$par_output_prefix.inner_distance_plot.r" ]] && mv $par_output_prefix.inner_distance_plot.r $par_output_plot_r
+[[ -n "$par_output_freq" && -f "$par_output_prefix.inner_distance_freq.txt" ]] && mv $par_output_prefix.inner_distance_freq.txt $par_output_freq
+
+exit 0
\ No newline at end of file
diff --git a/src/rseqc/rseqc_inner_distance/test.sh b/src/rseqc/rseqc_inner_distance/test.sh
new file mode 100644
index 00000000..49405696
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+
+
+# define input and output for script
+input_bam="$meta_resources_dir/test_data/test.paired_end.sorted.bam"
+input_bed="$meta_resources_dir/test_data/test.bed12"
+
+output_stats="inner_distance_stats.txt"
+output_dist="inner_distance.txt"
+output_plot="inner_distance_plot.pdf"
+output_plot_r="inner_distance_plot.r"
+output_freq="inner_distance_freq.txt"
+
+# Run executable
+echo "> Running $meta_functionality_name"
+
+"$meta_executable" \
+    --input $input_bam \
+    --refgene $input_bed \
+    --output_prefix "test" \
+    --output_stats $output_stats \
+    --output_dist $output_dist \
+    --output_plot $output_plot \
+    --output_plot_r $output_plot_r \
+    --output_freq $output_freq
+
+exit_code=$?
+[[ $exit_code != 0 ]] && echo "Non zero exit code: $exit_code" && exit 1
+
+echo ">> Check whether output is present and not empty"
+
+[[ -f "$output_stats" ]] || { echo "$output_stats was not created"; exit 1; }
+[[ -s "$output_stats" ]] || { echo "$output_stats is empty"; exit 1; }
+[[ -f "$output_dist" ]] || { echo "$output_dist was not created"; exit 1; }
+[[ -s "$output_dist" ]] || { echo "$output_dist is empty"; exit 1; }
+[[ -f "$output_plot" ]] || { echo "$output_plot was not created"; exit 1; }
+[[ -s "$output_plot" ]] || { echo "$output_plot is empty"; exit 1; }
+[[ -f "$output_plot_r" ]] || { echo "$output_plot_r was not created"; exit 1; }
+[[ -s "$output_plot_r" ]] || { echo "$output_plot_r is empty"; exit 1; }
+[[ -f "$output_freq" ]] || { echo "$output_freq was created"; exit 1; }
+[[ -s "$output_freq" ]] || { echo "$output_freq is empty"; exit 1; }
+
+echo ">> Check whether output is correct"
+diff "$output_freq" "$meta_resources_dir/test_data/test1.inner_distance_freq.txt" || { echo "Output is not correct"; exit 1; }
+diff "$output_dist" "$meta_resources_dir/test_data/test1.inner_distance.txt" || { echo "Output is not correct"; exit 1; }
+
+# clean up
+rm "$output_stats" "$output_dist" "$output_plot" "$output_plot_r" "$output_freq"
+################################################################################
+
+echo "> Running $meta_functionality_name with non-default parameters and default output file names"
+"$meta_executable" \
+    --input $input_bam \
+    --refgene $input_bed \
+    --output_prefix "test" \
+    --sample_size 4 \
+    --map_qual 10
+
+exit_code=$?
+[[ $exit_code != 0 ]] && echo "Non zero exit code: $exit_code" && exit 1
+
+echo ">> Check whether output is present and not empty"
+
+[[ -f "test.inner_distance.txt" ]] || { echo "test.inner_distance.txt was not created"; exit 1; }
+[[ -s "test.inner_distance.txt" ]] || { echo "test.inner_distance.txt is empty"; exit 1; }
+[[ -f "test.inner_distance_plot.pdf" ]] || { echo "test.inner_distance_plot.pdf was not created"; exit 1; }
+[[ -s "test.inner_distance_plot.pdf" ]] || { echo "test.inner_distance_plot.pdf is empty"; exit 1; }
+[[ -f "test.inner_distance_plot.r" ]] || { echo "test.inner_distance_plot.r was not created"; exit 1; }
+[[ -s "test.inner_distance_plot.r" ]] || { echo "test.inner_distance_plot.r is empty"; exit 1; }
+[[ -f "test.inner_distance_freq.txt" ]] || { echo "test.inner_distance_freq.txt was created"; exit 1; }
+[[ -s "test.inner_distance_freq.txt" ]] || { echo "test.inner_distance_freq.txt is empty"; exit 1; }
+
+echo ">> Check whether output is correct"
+diff "test.inner_distance_freq.txt" "$meta_resources_dir/test_data/test2.inner_distance_freq.txt" || { echo "Output is not correct"; exit 1; }
+diff "test.inner_distance.txt" "$meta_resources_dir/test_data/test2.inner_distance.txt" || { echo "Output is not correct"; exit 1; }
+
+exit 0
\ No newline at end of file
diff --git a/src/rseqc/rseqc_inner_distance/test_data/test.bed12 b/src/rseqc/rseqc_inner_distance/test_data/test.bed12
new file mode 100644
index 00000000..33a46951
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test_data/test.bed12
@@ -0,0 +1,4 @@
+MT192765.1	1242	1264	nCoV-2019_5_LEFT	1	+	1242	1264	0	2	10,12,	0,10,
+MT192765.1	1573	1595	nCoV-2019_6_LEFT	2	+	1573	1595	0	2	7,15,	0,7,
+MT192765.1	1623	1651	nCoV-2019_5_RIGHT	1	-	1623	1651	0	2	14,14,	0,14,
+MT192765.1	1942	1964	nCoV-2019_6_RIGHT	2	-	1942	1964	0	2	11,11	0,11,
diff --git a/src/rseqc/rseqc_inner_distance/test_data/test.paired_end.sorted.bam b/src/rseqc/rseqc_inner_distance/test_data/test.paired_end.sorted.bam
new file mode 100644
index 0000000000000000000000000000000000000000..8b215e12d1a932f1619cf7ded7e172141f45d479
GIT binary patch
literal 10205
zcmV<3CnDG%iwFb&00000{{{d;LjnMD0fmy^PQox0hpTtRm)Hxe<5ULHD+VM;vd!s)
z+ok&hE@3OK4I1x#Sl_~Iz@|9l?zE@<zWz=+ww$Z4YlKGkQ@nH;kUsVwSR_Odr#V+i
zXXHO(-(}7-4C$b662P|0=<tpXJENx=o=+KId(1Xz2-vgP+_o3a+_kXpFqKG!y#)(-
z5s5f~&d94SWNDsed`q$CHuchFl)ykQhCRR&yKZPYf7fK8l`v_<TybN?rQ(L<g^a|G
z8ncNNbOFqsY4%J4f#o}g)eeGnl8Y>j$SUWjh*u-d8%zMC+9d0b3kPX^@EAz)ObM}(
zWuT_^euV=9Rjy-S+oj2yru(5*gZU;Wl4qw>0;k-%ZsST(C`}g)cFWTuiT89-s3ayK
z&sy7Ii=3X56WHr%w<Xp~HN&79VOf!bCCTF-kN6|IJu9RC%5=SqbWvFj_X;6&gAi&y
zH2PEseFL0k-#`ch001A02m}BC000301^_}s0su`WwS5b$EmwKo9KT{4GdZ(7+bldP
znKd0b3kTWf{QxJrGk08uBqYdJN+7}%;?k-JC@M+QAR>89S7C{uiWCPTDz#3XP$C+s
z&xA^#5*26?p+YG#h&GCa0JXTSQ0t}<icG$LJ?6Fd+54PxZ|2@}&faTg?{n5S-~ayC
z+U-_kkH3qr<e^uwt>~%fLy<e~#JOkj^WjGxIovrqJv}&mVDI$k=p=gM9Z{qdS3Hr4
zVY+KIODj>Pigm5zveTlGwPB6vOwqPl)Fl^PDnzFmW7?u=+p4INMy0$-)57F=9+z<$
zj=X;qXEcs88GXz1(p?wF^uS&k)5Y#FouXlSM%Tx<EW_z6v+qP#=NQY&cwv9iBl=w#
zeaB-A(aSM{2e|f~yH|hvoqJcKM_&0eyU|a)`s!A7?OL(**WUcs|M@Tf*H`@Qw_c4N
zd)w6)zWwc2qn~?6^_sW66X%{C;pVWs7QHSS@LhcGd*55a@&mU<Q2|h7V^|{7gb7i0
zf_16Ug*JwzZC6*NmZd6nZFF^o{?d5ifS`$G^pvJZM+Pi2{9DlEFhfk$;u*diWO<qS
z=dpWnj?twF-&|e0`UK{C^Bs5ou%GX3!+ftk@hVT9?xrYWcDj%C)Oi+T-<wirclY4r
zc*k-lNvm47O~F%;q%5jVC9N=;nY6CTRO*^(UKn1b+;mBmFkLaG5~1o;x2-Blok*ce
zol3=WI^w{Y5p^cddS=nTmE(CvOvv+oWW{CSOrC{bmu0!blE&$APG4mSD8Dm?G6HvA
zM%*E6JeG?QcV4#jV;;<3@4<X3`mhJ{LpMj!wXG?b2gj$UC(%0qCYMRtaZ^dv6s)RE
zBV^S{rIX4SktT_35+M`DQ_(isu%fM4$LkhXCS}z$LJ3()-j+NO+qpf;g$K}*EMK_C
zmQhyJoVa?>gWP8Ja_}gFtl=xiw;0cI48;D`;qu&$*o!P{OAn(J>})}&a>wPIMv0kU
znTujcaDK7*Y7oV{M{t%~ft%0vaDK4oCh>J^DvD!no(m~vB={>UU8_P$ooZo{l*vxj
ztOd1`RN|FHl{_PkIBBHE_K1lr`0pl8Gk27t=a~b@tD-!B+><dIh?!fJ7`V8SvT^?w
z_7XbI!_8#E&Hp>%p#$?;^oD5Q>u*0l1=Df!87MZROa<}*Jgt<hH9^X&npcSdQI#kw
z)^<8csv3MXwVhoV+sRvk5KLZKWed;A-0ADgagn|)0#!Z1@)-<y87BUf*~G7Yaysu9
zjP%<l1Bd=|KkdOZK98~gFw<{`ho=VzmP0LLO;Q?JC21;o#kHtJVGL%Sa9t;90&&HF
z;7yb0P9!jj+!RtJrr-%Qp5$FpBuxusoO<hZ()h*>59hbtQz0Hxqa4UYr!q2mj(Jvz
z*;AR5H~#{h=<P+h$l}0K3<JvFy%>iAn9q+m6u=~ae|RR41DHDD0HzTz1TYbhu|zi&
zZwr8^mFXBT?S$eYWy%O9(grv~?ZJ%jMjGC<X<|w);g}Sd04bQ9JOFYg7V!eg#;I&e
z9Gq|(u(t(HtQ;X@e<!Rm10){JfPWl-r}thghMSU2MRPISrNGPI-Q;N8IdL?Cv3SWX
zgXImz;#;>k2V@N9$-&{lo;4OT@QNvT$vW^-Q@0W?tazQ^M|;I1<rvs&_k1La1et&8
zOowymz@XS&5lm+sNM~;a*$?-&WE!l4L*kxWo8rK<hNHCCS-&l|Mu)B-IRDWY&YJ+|
zz0O#?_8|}FT_ZT}-TID)?o}f=Uq2dq{Y=o0P7inYqfbM>&4jf|lG?x~7^NFk@viE0
zr#jK<vST9A17J7qh&`V$>(|ef+b7OeZl9RUdB+*Z@tl8SCXbh$^Vxs)bs-T1C&!#$
zzh=%ikLUacBM}KsK^+aE^d~br=ENqatJ@mhRI8F&NL`Y?CNHZZuM6VR=)(Fj5d4ML
zqt>$~E52}=!g@UZ?_OA?v7pD!Jd^XiL|bTqtMA5S-g?I`2G-s_n#{Xj?sdTS3kK`-
zem|K6WAC2@ZimMwd%Mx6Z;zr{a+VtSHZZ_dsuG==ve265RB71?1)tGC##05;Y?xt8
z$fo9+o0L~=lPWkpLY<q;`3<_JTsG|Cb-?Zy=jMp7F-LssbZbD0?K*Sx%h7=7&&@(L
zhu*&cdWBLTcOuJ{rAZ5Qi1<t*$klbqYu)iAVMfCawOm$QNhJ!V8(}J=D!7SN3%$zt
zHrXGFILh3GpSd-yxicr3Re)LS6`c=%dywKW3RY2O{*kjpiwofCh)3Y<jKRBS2Hw^P
zynD8O+=KVG?piiKcfT--UOqKH`#YxxyF1qWR4Jm8hIpiT+9e{9t!`m=suH0cQV1N5
z5>upISYld@*f%M<#H2_RBm`w@+Kx<Bm1-BO_<&^L0<d_L4Cu}5h$|!h_(#1S8hn7>
zVCPn*!}ZSkTQlWvo;6Q#7Q3i2cH@Ba8rzza@qrnh_l)p-VCzS>2JGg+3Ss=Ysb2DU
zl5b?Vfv_qG<XX<)Cne-+LXwjzl`!LN0yT|j2C9qKX_087VDcH#E)^o28euq`PF2=Q
zCe}dX?+5vabXL0EHwwnG1x=Mgx!il$*#Kfb*5`2+d~#grV!ABO;@&Zjy*Cw{rXiW*
zoP@<9#GOtn&d^-t9I=UW^j`uKW1tzmibc_HMsFUCMN`GNzjttQbQr;{K{S^@u@M-$
zDmnyo$T75_T!n{aC4`b%CX98R5t_G7Z9DoorEdRd@6V9#cYcdwl4TIh)rQ5EE!M@P
zE6ESf9q7(sa>*%+nw>YzGdR$8S|yR>b%W5IIV}=8Nvgdr6mOM{JW>Yvk{uLMTO-MW
zA;o3Qs?<mZy)O)h;+KswMkAJGr0|TSt4({wdRvz1G>zEJ!QHUf&Ny=cf{V^<27u=5
z95^pW4vfr#5d1{<E`+F~m`!j6C(ygxv3seLLV87J1<vcRqcKZfP+hzFIgsRs_^*c4
z)h#3A`MKag-@d)9!5-aS%6je}!~Hq6VAgP#m1>)|0;=$YkjpfR!E82$Gsz%<jcky>
zf=nh_rX^fyQ^BX!kV8l*UJGlA6jsxvS8l97m~TEc{e|;Pm_6ql=w~jbz;5+$KHS6k
zRP>f;7<<bM&ZDE#<HP95+rUjIDM|$j$q?t&s;=NoYD6GyEm#U8z<E-@1wqbOG%cbP
zWJ%e1amz1pW_kdMH_pB4FHe!UW5la3Pk?xZb1TL`d}!)cTrUvkozr6FRasu<=fENe
z*d`#x0`}#gtsdQ8Hfbbuiy073z-<2Qypz|eYEmRqSgK*flD4JGp{Jm%7%B~hOGjzz
zTY1L#>{{uPa=A~IJ2cJ*<r<tep9oMsvnhA-{gd2D@V9=7Eo-Z<VeH<izjbhQcyQ>#
zeJ07HSE6otqFdF$n}^~D*F=H*FoWhtykBsMs0Q^1sT8?q9sDm1T_qV6BwCIX0F2?4
z8zyzZSBTGkjk`^GpSsM+#JWeByC7s5Afnf9-MUzEIQUy%W6R_ujK4MYw>+Li&K`{l
z{u3wCagMBTs(7Iam{n20%Wq*xInsNYC3K|#;vLwGXrXH0yCPf!N!bicn0^WdMzxG}
zVD_OvS+2|uUgq%RoT0gjop(>z8PNP2cQ2<&Z%U(RcgD`+)03TJmnKEUOSCDz8MygE
zlmgCH!+0xrB@`%#FjXU0B^Byk8YLrmFyO9Am_*L1LnfIVTwx43V>dpvG91}hYlirK
z0M2Dj$+7J(bh$mC$v2{zu0)fNo99Uh;V;a%IiLxz6|hOk5R9g^F;&Y{K_XmrGBrjb
zm)8=uHNu3B>S+nW1kMVUAUJ5?#2AS)h*c{UJajLB&M}C6u_5jwgK`4F^0N!ykTcCu
z;O1sDU$ipo{Oxp^n-46a=;^6ra=3#!(2<L*Sehc23|}s(;q^<SHT<^Dq=k}gqF{AY
zgTzTnejr4fQ5J=n7D-fI3(AyqaHW%~l{&d0++6Vn8{XC@tuq(*+IVBAg;>|-3!A`X
z6ELrC4ZsCz{=;Yh`2ML)_h9DKD{x+@5O0wkm)Z(HB?Azy!o^N;6CmZxN2D~p#Yif%
zFyme<<1ln_c+Y*Sf;C@)vD`W{@rrY;hw<O{Fg_Ojs)zA8jD3E_$^E_4<J0IhfKfm=
zg@l>b32;N^6_y0jT9_6x->5{Sl0iLos)b5z(vE?(2=H{5ih{|yOYuUfQlZ=Jvp5;w
z2utEZIZHPe4tmo~@onDM1{@>v(FMTrGjlBOUt@dj@8$dV7R&N|?>$lUzh_t;>>Tbn
zH}i%;$@mSjJs}*+CuCef%*@x}dTp6cHK+S)0Or>(X2?TO{9F&_2YWY@$a*l7Z%0gW
zGfRz<H%pKfPB@1*1lg@xs(7|alf_|hHzhKn6^eB=N7~sah`2<`56)AgxGGY-gOEI7
z+qM{#*<6S%*JU0P7p=H}KXc-p`H9DFJj(|szITe^5yG>ggX8*Q<ca3xD*6XG|IDVK
zcr51+^m0x-4C*q-x#jB&PRC7>^UGp~C`op3;bE;>)SOjSUdcm6&2^`QR;Y!q<a*U<
zhf6<XOT&R_fm!*AqWTC(yz#gPXEC}a57`}8DfL)>eUqGTuaxsE_bj&>eHdf^b0+7<
z`^P)Zj<@Vw!0{Py$c$0$K52_CP4JU~BKx;5${TgWtA{sOqNO$ufcf;wa_5iy_t!nN
zLeB5)iTUAs200JJB!JTyF&&shOc-w}8`nH#jh0jzO43e>isNTnD8m}wnhtPP30!yh
zo~VPsTNf>`q#8blmPHm3g%cQ{Y>?JopHYj<$lneb=n=KnqjP!V6^QxtCStyDLd>su
z+<vpi@~P<6qp?@diFvetauR(JCB^fB_;?^)s8Wowc8-hv^F<jhaamRe<pdSX??>iY
zoR3VWH)=Gv`jN@(_M8eE&+cE(nR3zDg$B-SawoFYcc}kP8fNOKP<kLg$LzMovn#wD
zyynHjz5AtT82hE^y*t|7-QC-dzW9AngfuQvPDLsb#Z!Yw3ef^m!KOjHm2w1P2pJUe
zQ-Z^RKzW8MNDhXP$dakQr=wdqyGtvN?Cha4rJ^@$K6JC91eAV$j?#ChD8(a`zB@r_
z$8lhc(%+kM;Krden@pY!<X$n`mD)7Fj6MjOU=Jw${2G*QAEOj>>gWH`z@=WNz9fpC
zpK<AMcYpuH>Qv;~sMrEO5_K1ZNJ*v3G(~)bOfaFAGQkt1mt<9>NZl#XwWytHV2Mi+
zw-+4wJII;l-l=znIPMFY-f}x2MwPcRL`$*Hr`ead@?9Qk%AwYr^_Sb4C#mSnXFRM3
z=e9kEzOqHWh<)=J>2)Ca$Mf`DJ}cmjjeWjVZ4I~)mN$WM{~#Lhy=lfchh>AaPu`AK
zbTeE~ypv6b0F#`3s(sPHX<UMP$dFdG;?yFGYBSeRQK*vg)U}8&T;F);R&u(^rs$}N
zGtRx^<REhKb!b&z@;+TH%NCJs<E!VVN4~G?kCa+SzF0agfp{l@_}%~Y?5bY$J9}sT
zz8_fbCw>xR+gnpYo*eC*`Wk(g)?i|b)Uj!ZY9;cSb&5i>2FYr}kS=1-;ao6dl2W0n
zTp?r^sEn#s3x*1GDl4iarsFX4f`Yi@2K58+stfJ+aawLEK{dLL;QX^q&U`j;=7R(J
z<PR*T<p|>MJU`{6gVP3@6GRfNJE9$j!s`^O6$TMy-8Iy<s7-|!6bdl`7kP`PbX8(n
zRGyPgGd>RvC$rDWaZ)m$IRtB9j>~0?&v^uH{@JDq{oRuaeaLbC$6`5ZfA3$8qMx2}
z^B9HfBbR@#IW%BFrD&6C(IV;;9aJGh!H4=FZ~}E9+keAFZBUve8v__oLV_wqEu_Os
zYSFS;|5ARw$*-wcj6$Y7Jea+C?&=u6w&A`9{TkjGInM11W{g91h>#1^43bU=|JIb6
z9!-+;1PS=M(0~uICW1^P*=s7CbtrL2l!%ZHL53Xwrzs)L3<xR#u~v;JYnZ4ifwDkq
zu5BN;E!nPb#LX@M;V0^5nvV&bZzkR4bVqo5fV~pW^~LNU>VN+Sm-BPC$SAsJ%FdJH
zozp!R9tnoXQn983?M$Uv3;Qimzo>-P)L|hd^<LB_DP-bSx3G?PZPLo5<5X5cklIja
z+6EVKYz$^d#M2X{H@Bnauq<4ehnrBYKs_G~xs-7p%#ID%<6xaEId9wA6d#SjynpN3
z49uHHrOT%=_CKO2n1@G)d&klCZPdCGMQ^<M5}+z6OsUdNaTJM+M23zE>o8to`!boj
zaod=;GWj^+7WZddf-3e6ER;#1$F^6d^!-7U)uPpB)<d#+7(y2s^s_5nq%$g*c@OK;
zJ*-2jj-Y<g)J5{JMq3WncaWP@AOk{cgwCR12P@RJ$~5qpltyAtYq;|%{=@%dX^}uh
zRL~KrdYpVE>Zo62eKS{P9YnZKnR5$i0f8fB9-N)rx=PuY(s+SS=f&1~x#mY=wYzLA
z6Xb5qll=aM_|pCy)|&zAT?Fel-}LLN8o}?{`XdkF{~L+^Px`SEqW^bhY&|(VJvxfM
zgLrq2pJ_W()tfnfkLSJ<*e;>!|64yhc0;)f-rcD<^wL=x`o=Nm;oFNb#h;obf3Cg{
zGyFf*7s3p09fc|H3$}vv*gVBcy!rOjR(Rd!n#cw@Vja8{juH(jhN#@Y&QgjEg&I>S
zfszhL!4Sx`90sQCYU&kFD^W>f1Q=C6?!pvm7Q_7}lJq43*9U9kirD>gv59w<Gq;#?
zh<sz`a=T1%-&we9(7odwo{Wx#9a;GL;%yhS6;F@I5#;dU5sBV6lS4<CXQ0*!l0$rL
z!city7LFfoEo|=K@hx|yZ#Z{@jyK+=TLc_z^Lf6CDUV}n@Bh)atZXlT#53jJ%4Nm<
zhL<8Zn_9us{o{kZz34T!B0Re(vOV(#fooeU)S?RrhHZR+P{8{|a0cDoB8F`cKp@*{
zc$462rYl@f>zX0_O_K%{X`G?T%i|YS+{+icbYonGRg7bzxQ^A>=NPh>T2M((xs-!l
zDdie7U0Z(^5>(6G5_xs)>Yq#%_lriTem(dWUzf|C?=3*}-%S<F>F(*#@vilJQ3usP
z2em1b_o?NO!_sMnaH2Da9AE+A)9Q*N9Ft87fF%lC2zjYR0%3-(sG^`D!pV8s=kmOq
zx0OtzsnO3-)Vdg6KJtg%sorSP+T>7#9@hMjD*MDH$Ct0HR}pY?$Cm(p<y81Qn0CqR
zrLjweK)eQB*idH$SK`VDGC!ro)VIpLQ<j%&;*8;jtWJKG=cWH>QQ0Rp>9RW}x-8g+
zH@tM&Hjozh^wc(Zi6=PMBZPDT_*z5QTZU+?MI}I2m1w|XDR>DdSiquy-pttL+}2z0
zerV=Gq(vT%Ebo`=SuE``TJNJxSm};94iY|i&;$EP4J_6G83=n;U(|Zr5PLj7e*Ylr
z@9=nj{(h(Z$9Nv^pYHEO(f5(8!_h_k4`~8anqe}fDH4izX>Fe1$Q39-%Su{sx1-Ru
zk{xtqx)d~A?ugGA&j)AC{T6WS&GS_9GiO#yu0HcequGaYLU6ALr4P&m)*(Xf6*C=b
zadk>*JeG8<X({HHw5~x46!5_v0ZF}*#olKMYcoP)`XX!%;m+q9raB1Gn>V;u<BG!j
zUK|#=_P6}8=okD1|LPA#(f^;_@{^;3185}N^65N~_GybW#Tci!$G~$!-Ay9{2WlvM
z!K}i^<XR#_<Qp@`QyOBD<s<V;ScbbgQ!NCTwRsEIZXcF!dUu;z{%J{O25^3VzF_Se
z0OtpvyyKx2z0uzYwvT|AcU=--cg*g-1BYxMZ(6Qs&K)XBT5t%5?ohQwS(g$*5?&^i
z%L_cz5DVxUTG9aMl+q}kr-r)qOW;+Bd@=O<W_|&^U;ga7QEXHa_bn>6Epu2Q+yfi;
zi+(2CPYgQ9J(}%Iv20BP&whWC?Yn1Xo8W%}n0L<#;xzW5*^<?r-GigkeOD2eoY%5O
zt`^zd8ptBEh@uR~w@LvlpbULY%ZDln-2>i<E|ui2F=cn<5H*BQW8785y~bI%WgdQE
zv;)Nz>f$(L!t+4SfX0}p;f?&hEHn1{4J2aQxt+O<UHsaw%-cM>0L6I{=3<>~6Et_G
z)TFVu%of9r&}?oXntqcSJ42gK!_@3-?P42e$a0VEBKG_Wg`0fbr@F}U!19sd>njRl
zVPATb_cthTQvgjfPEN>KdiUlLnsVzU9?dWI+<Yo}S2T>hYtGHRo#W%<=t-!->jLv)
zK|+4P(<3>aFC!$3-aa>k&z;%PfAzTuLf#OL5qi&@Z#M`b`^Q>mYC(}CJqlru@4(1>
ziZ--T#rd>;I9^~mIu_$ofpiNu99TpMy>tyiV@vwnD?LK(%Le`SL66W^Fm~V8j6+99
zdxxjdj*XPYLRD$RpbZk(2(zgGs5{z`q%`nCTLbuz(2ypDPgQV~4BMve3{N^LDww=C
ztgFeeGBgT61Q&C<^u}9}I3F8?Jodtw^?Akqdp@oTy49u2`Rx1F)CcbC{rZ3UvOye!
zU;inL{j0e+9_^usZyoz}=*UDea!ym)wyG5x9!f1L%6w5jKJ}o(WTTpDBobq?c|5;p
z41d`p{GM!7-f<RUvHa_anEz~(U(Z&q*8Qy!p21jr6=R=W!t;1%-<Pk9syfu4;LU2?
zNEEC%ycZ=q#o+5TTD1yU5JdULH1Pjg4pdQ@K_w6m3(1jR6pG=lC^5jfSS<Yd?|5)L
zhGdryIb*-mkRx0^a5U>_=eOl>{Qy2y>r33$h0fdt9Ijahx!%nG4Y-bWA)~rD(ERu&
z)4RR0diALu%^`><#{R@y6%OpYZVY9YYP=lU^zl9y5d>|j@kfMN5ufL?%kpt!Pw=(#
z@?zu<YI7qyZ=JC7)mwv-yn7bKlQR9<^K(3{;<PE=>w?hWs?MY}EgM#D5%VY@w;Wr9
zO%C$BuQhr9#%9>Yojs1Q@fsaFxdHjvr>1zGqa2v76!))=2pYtlRKP2i2-=JLMRjDt
z8KV?Ar<KEou9B(&+(?{Q(RIe!?)m4q3J1}qgu}Ln0dbPZ&~)o|X3M>M?sqN9C(VL+
z@1Do;u$hFv4O2@$v=@1Letc8u|F%i#KLmk4{lH+?Lvi)J82j8@d7hjcpB%dCYMXY3
zbzO?^H=!Ctswyr}W}(tbgHX9e%uG$EaEUrFk(wxI88*CZozPwg2(6JvK+f4m%x?Eb
zS69irW%fPLJrU!wH(C@I0=&#M_{4rIqwr-z6NhEiztml3TiI>Y92UFxZPplF#4fc=
zVE)d^a@FsB>^B}-u`cwko|^A{V374dO#=Akb80#;-D0uzprsBp?Lh-`Ycg7>Xw}rQ
zXBSAI{+}jxmpg}!FXmZljJCYW@{uaFQ+AkT6Y*T1lJUx7sfB<3ib>e=JDV&~ywVbh
z2bcY%`!V)U=G$5B@9iJ%J4?jUMlh)W3Qr3#6DgdofX9TivZyItBkPW~<Uln9<-t}<
zAWOXzw4aFqHw}<%B{lpE%WTiiO|3sxI$7EH?Cc7=b7h~Wo}KfH{s_+}HYv`<O2v8q
zgUgDOFn-f~3r2^hT?1Y~Vb)63QdF%;O(8o7I<LVwEt!@gMVX9OH42izmLnAEbb@TC
zT?eiKbO-ioU8|&9;!8HM;Js6nPi;s(`?=!Od5>9!Ik5AIP3*jNB|9Ho!Ol-TxRhGl
z-96kr-gl+j3-PakW`NE#Re_utijZ2c7MLRQ%o|yqU5J|xp3TBDBJ04*ETl3<{zJ(8
z4{tE|W_B}@RVzv!ShF&8sCInn!DYXbFur5X&H>Lg_`tbGL{7Woaa2NTc>A=gQ3~w<
zjG3ZxDD46Ql^`U(r`sXMbS23?kL#o~8*Sh?UH(2#C$7E|SvjiWja{qx)$!yeoUuaZ
zfi)Xy4SuKDS?1@XyHWJkS-`$`cyhSoHn43;S5`>pssaW+5wuYeqbhMLRFN{J7_DrA
zbJPNIT8~Fdb11Jt8y!_i2kqO!C;?e@ku6oGj{MmUq&u^s=iKd#Ipp5GxeM=``LpyK
ze&<~q{m#25fPUA5_t_rM$D*Gdjs5Ig;7?BX4)>y*_7dTV5DL0bm0HuvCx#-ML9SfX
zWc3qXBm(HBP^dgr@C2?iG@m21;xq{L+IfcTGiPs4_?gM<51eZ=p8Y?bi|2LB{t`O<
z{6`Qcntirr_BV}ZAH3w9-DNNNZ5aFL?A{|JKG|{02~Z<6DeawrDw#}BcjXPFifhGS
zJd>stFqN_u37#hkCe)-I>;as-N>s>=!M!UQL@g{~R@eLB!aA*PGp~@dcd3NM!VSf4
z3%1y~$9}IgdjWNF`9AqLZ1U;%c5=I9QLB$#@0t0kjFlamU$7ft<v!=1h21^h11KL{
z=Oy1d@sdL-@ni(%6CTV*F!nF!U>+PD?w>?gXuTT&$=3sE)&Qw2kXmYSLz7>t-YK8d
z{Nm~5tE<9*@?&$IB-iL9*&EGAc9)Y21n*DIq|!rajpp^BCo7Ezr9^mwu_W(vUwucb
zo8hQ4bME2(g&d>c#Y_3eHtG1=RvOJmcbA<IGNeyDKf`k{nx=)JM5ezf5+iGrL%9+a
z5(j{&E#MV1Rk9S-VXb9dwoD0;$Qr}6M+gcBsF7lfR%j;873Xfm-rXM+j6x2<H`j%U
z<|{E+hfjHqS4`g3Cu{DyV6rCczxB2eLH}knDAS*r6Vxfr55R0(2FUHqZPMpre^O$Z
zUqiJBd)3*sLO$;A8?pWF?qRPAryGZm!=KE3t|oS$&G4SN{ru9IdDW|53X)pwExTjC
zwzsq~0%EU|-4o~DVvZ=B3)D|4CJGozl-Kc8h(gga=p;p`#SLdjP$g+)5|-eELRJgD
znQ4#+Ol2)Z%Ua1M4cEcRoVl)ZNnPo&4zw6jGh@drAC1H=C+)J-&Y{hm1qu1HbGf&7
zuM8J{ZEsmp31c=R)(Fp};YgRjhHy%yLaWi9k_rlrrK;>GXV4&lnusdZg$4<cdZo?F
zjBF`$K#ncyeTa8il5UrdTmJJB+!70$*pGu%&KFtl&1bU}E(5In@MO2Ca|L$Gw<Ny=
zo)3n-^?N)Yi*z)M={Z05cTY}Eqbs*l{{l;FBQpGc+VPES39_qPb%vHwB11sF9YS14
zut+LeOe#~|G~g+GA_X6?-?($tRM#mt2XZ!U?#Rp8hP<N}pV>&2S>yYzIb^r5(QUU+
zA@fZNW60h;r{Il+Yzjy|nasLl^mz<%c^+H5ijaY2_X4tat%L0531p!|^h<lorMe&6
zUs?pYyMMd~)NBgsVuA@I6>1<&Qwb)xfWO$biq`OH*o!lKzsor#OU+vD$OZ|Id*|F`
zTz&B~;OLbCS=X(NE6rX!$w38A`oE3f44(8i_LeiG`v*IR2+GKlzA;GBz8&j5=@lZE
zuXwZ?+Hu-%bZs`fY_!drKfugixtu5cjTQEU;C<6vm>rbXp4<=^Wz(hgcG$?xmU%6#
z@pz)kk49U<Y&g#9W8N?tB>h(|=Sh=P&+#PbpRLagl5Y3NB>iR*>bRw@Qq(o^Uo-+~
z1o%COhM_Ha!;y3Dq-k_p^AeXzTvfC%;ygtW3eh%{XZ83f{nLxw@+7^T*#zNg^RZ;4
z)*r!>-rBlc_Wn)#%c`@(*uR;{`oZqr$^L2h^qcEK5%tarnfw%a)%@H$?gT^@Yp<B<
z4&V3bIi35Wb6$q_#gGtnd%Fh>Vd?qNi*2p-SGES^0zE@J6CwQLGjaE5?%0h8S&4F7
zf>Z=j_*Ben8zetbJnl5o`lW%hjXX25TAUnoZnS1d={E|=3m9`%Ak0HNt@sreA%_qy
zvpc=JB4lXxDtq3>Wx2Z8HbFES0ePNdECE5#Kf0-#>CTniOxp*8;}`_}VT}F3oR_pG
zjdR42XDDRbw1yUxCP)$z{mM?4Ey^CCo6^vs(2yL(<+4l)p=FnLDUuID@RAmgmyN;I
z;HAqm$LE`@f0nPiY^+k_ksgji%`^6O>8wxn_`5Yp@Bq(GUMyk`HvQoq&ky!CoiIM0
zGt=QoHeI9Y(HN9H>>l}WD2uvc1<D$t6}9FyOS;w|J_O=*qg9G>Nzu}$IJ9*mpc-VV
zfNj@u=4O%EQjVveoA|=T!SS?{)tBwg*d{3USGbPZ3$KT;pN6=w)coWon||j?oBplC
z<(T_VG4`?f=Y{Q`oF2JsjwpE}s)9Z}lae|$q}Xn53tWYOG*=12#*T6OsTkDM$d&05
z+H4+LmXpRz6A-pi%Jeb!Xpyq}%6yl0o|SVK%J0^=3QothGs5*=t-6>fb9$wZjuxZV
z6yW)hd9TQQvqjEqBI>~e5q2)%84AdR@oVQF8Rqb`?G4urBdfv78miN+ptSqj#eTI>
zwg~%ClX;34zE0P#x3}Lym>maB4%_W`470(MpQ#;2OAdP9)GN-H0?m)CGeLK(>~a5v
zqvaI?e~7VfFMXQb-tMVGlXF#;N|m$|b3>c7(!-i|&_R(?Q7RYGE_9h7hNNaO2)nF=
zN$qFZbscKW2|P~CO*!4C`Nr*~x9Z5|u$~zR5Srh-*rpqyLi5q1LDoZsCOU?{IY;wo
z7e1$}(2(t+9Z4k0nNXMXIT6$nrr~~S##Kch$Hr;tk8-T+8bBvt%L@<^3AQFRNK7JP
zzsR!K<?FJQe*EgU8w&R$A7R|&<C>MJh_kd;(W*@%#$evxE6zVWS}rRPUGG`?Y(Ps*
z+o60(=unGLM%a(Vk)St|nz;{Pu>zj^&o{|@kGxwFWak?crITjo7}{1Q`!IGN9GK<T
z(Z4gk8D7-Cxyhz~|4QGTh&b=OA;NCY@pR<0zWW716ActCZE(~Ip{cVTo;$+N!Z7Yu
zZ~D(Mb=yGXp(kM;94%pWrsbYDd(B^U4mAIGlc>LNBI<t*BU)<_B6|P;ABzYC00000
X0RIL6LPG)o8vp|U0000000000Q5X>i

literal 0
HcmV?d00001

diff --git a/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance.txt b/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance.txt
new file mode 100644
index 00000000..e5f09f8f
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance.txt
@@ -0,0 +1,49 @@
+ERR5069949.29668	-4	sameTranscript=No,dist=genomic
+ERR5069949.114870	-45	sameTranscript=No,dist=genomic
+ERR5069949.147998	94	sameTranscript=No,dist=genomic
+ERR5069949.155944	-105	sameTranscript=No,dist=genomic
+ERR5069949.184542	49	sameTranscript=No,dist=genomic
+ERR5069949.169513	-92	sameTranscript=No,dist=genomic
+ERR5069949.257821	-139	sameTranscript=No,dist=genomic
+ERR5069949.309410	13	sameTranscript=No,dist=genomic
+ERR5069949.376959	-66	sameTranscript=No,dist=genomic
+ERR5069949.366975	-106	sameTranscript=No,dist=genomic
+ERR5069949.465452	-19	sameTranscript=No,dist=genomic
+ERR5069949.479807	5	sameTranscript=No,dist=genomic
+ERR5069949.501486	-82	sameTranscript=No,dist=genomic
+ERR5069949.532979	-96	sameTranscript=No,dist=genomic
+ERR5069949.540529	-61	sameTranscript=No,dist=genomic
+ERR5069949.573706	-63	sameTranscript=No,dist=genomic
+ERR5069949.576388	-77	sameTranscript=No,dist=genomic
+ERR5069949.611123	-125	sameTranscript=No,dist=genomic
+ERR5069949.651338	-33	sameTranscript=No,dist=genomic
+ERR5069949.686090	-29	sameTranscript=No,dist=genomic
+ERR5069949.786562	42	sameTranscript=No,dist=genomic
+ERR5069949.870926	-22	sameTranscript=No,dist=genomic
+ERR5069949.856527	-69	sameTranscript=No,dist=genomic
+ERR5069949.885966	-32	sameTranscript=No,dist=genomic
+ERR5069949.937422	18	sameTranscript=No,dist=genomic
+ERR5069949.919671	-116	sameTranscript=No,dist=genomic
+ERR5069949.973930	-79	sameTranscript=No,dist=genomic
+ERR5069949.986441	-22	sameTranscript=No,dist=genomic
+ERR5069949.1014693	-150	sameTranscript=No,dist=genomic
+ERR5069949.1020777	-122	sameTranscript=No,dist=genomic
+ERR5069949.1066259	-4	sameTranscript=No,dist=genomic
+ERR5069949.1062611	-124	sameTranscript=No,dist=genomic
+ERR5069949.1067032	-103	sameTranscript=No,dist=genomic
+ERR5069949.1088785	-101	sameTranscript=No,dist=genomic
+ERR5069949.1132353	-142	sameTranscript=No,dist=genomic
+ERR5069949.1151736	-55	sameTranscript=No,dist=genomic
+ERR5069949.1258508	62	sameTranscript=No,dist=genomic
+ERR5069949.1189252	-98	sameTranscript=No,dist=genomic
+ERR5069949.1261808	-88	sameTranscript=No,dist=genomic
+ERR5069949.1246538	-122	sameTranscript=No,dist=genomic
+ERR5069949.1328186	-64	sameTranscript=No,dist=genomic
+ERR5069949.1331889	-132	sameTranscript=No,dist=genomic
+ERR5069949.1372331	-29	sameTranscript=No,dist=genomic
+ERR5069949.1340552	-140	sameTranscript=No,dist=genomic
+ERR5069949.1412839	-117	sameTranscript=No,dist=genomic
+ERR5069949.1476386	-98	sameTranscript=No,dist=genomic
+ERR5069949.1538968	-133	sameTranscript=No,dist=genomic
+ERR5069949.1552198	-67	sameTranscript=No,dist=genomic
+ERR5069949.1561137	-59	sameTranscript=No,dist=genomic
diff --git a/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance_freq.txt b/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance_freq.txt
new file mode 100644
index 00000000..908326ff
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test_data/test1.inner_distance_freq.txt
@@ -0,0 +1,100 @@
+-250	-245	0
+-245	-240	0
+-240	-235	0
+-235	-230	0
+-230	-225	0
+-225	-220	0
+-220	-215	0
+-215	-210	0
+-210	-205	0
+-205	-200	0
+-200	-195	0
+-195	-190	0
+-190	-185	0
+-185	-180	0
+-180	-175	0
+-175	-170	0
+-170	-165	0
+-165	-160	0
+-160	-155	0
+-155	-150	1
+-150	-145	0
+-145	-140	2
+-140	-135	1
+-135	-130	2
+-130	-125	1
+-125	-120	3
+-120	-115	2
+-115	-110	0
+-110	-105	2
+-105	-100	2
+-100	-95	3
+-95	-90	1
+-90	-85	1
+-85	-80	1
+-80	-75	2
+-75	-70	0
+-70	-65	3
+-65	-60	3
+-60	-55	2
+-55	-50	0
+-50	-45	1
+-45	-40	0
+-40	-35	0
+-35	-30	2
+-30	-25	2
+-25	-20	2
+-20	-15	1
+-15	-10	0
+-10	-5	0
+-5	0	2
+0	5	1
+5	10	0
+10	15	1
+15	20	1
+20	25	0
+25	30	0
+30	35	0
+35	40	0
+40	45	1
+45	50	1
+50	55	0
+55	60	0
+60	65	1
+65	70	0
+70	75	0
+75	80	0
+80	85	0
+85	90	0
+90	95	1
+95	100	0
+100	105	0
+105	110	0
+110	115	0
+115	120	0
+120	125	0
+125	130	0
+130	135	0
+135	140	0
+140	145	0
+145	150	0
+150	155	0
+155	160	0
+160	165	0
+165	170	0
+170	175	0
+175	180	0
+180	185	0
+185	190	0
+190	195	0
+195	200	0
+200	205	0
+205	210	0
+210	215	0
+215	220	0
+220	225	0
+225	230	0
+230	235	0
+235	240	0
+240	245	0
+245	250	0
diff --git a/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance.txt b/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance.txt
new file mode 100644
index 00000000..a1930c9e
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance.txt
@@ -0,0 +1,4 @@
+ERR5069949.29668	-4	sameTranscript=No,dist=genomic
+ERR5069949.114870	-45	sameTranscript=No,dist=genomic
+ERR5069949.147998	94	sameTranscript=No,dist=genomic
+ERR5069949.155944	-105	sameTranscript=No,dist=genomic
diff --git a/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance_freq.txt b/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance_freq.txt
new file mode 100644
index 00000000..021311a2
--- /dev/null
+++ b/src/rseqc/rseqc_inner_distance/test_data/test2.inner_distance_freq.txt
@@ -0,0 +1,100 @@
+-250	-245	0
+-245	-240	0
+-240	-235	0
+-235	-230	0
+-230	-225	0
+-225	-220	0
+-220	-215	0
+-215	-210	0
+-210	-205	0
+-205	-200	0
+-200	-195	0
+-195	-190	0
+-190	-185	0
+-185	-180	0
+-180	-175	0
+-175	-170	0
+-170	-165	0
+-165	-160	0
+-160	-155	0
+-155	-150	0
+-150	-145	0
+-145	-140	0
+-140	-135	0
+-135	-130	0
+-130	-125	0
+-125	-120	0
+-120	-115	0
+-115	-110	0
+-110	-105	1
+-105	-100	0
+-100	-95	0
+-95	-90	0
+-90	-85	0
+-85	-80	0
+-80	-75	0
+-75	-70	0
+-70	-65	0
+-65	-60	0
+-60	-55	0
+-55	-50	0
+-50	-45	1
+-45	-40	0
+-40	-35	0
+-35	-30	0
+-30	-25	0
+-25	-20	0
+-20	-15	0
+-15	-10	0
+-10	-5	0
+-5	0	1
+0	5	0
+5	10	0
+10	15	0
+15	20	0
+20	25	0
+25	30	0
+30	35	0
+35	40	0
+40	45	0
+45	50	0
+50	55	0
+55	60	0
+60	65	0
+65	70	0
+70	75	0
+75	80	0
+80	85	0
+85	90	0
+90	95	1
+95	100	0
+100	105	0
+105	110	0
+110	115	0
+115	120	0
+120	125	0
+125	130	0
+130	135	0
+135	140	0
+140	145	0
+145	150	0
+150	155	0
+155	160	0
+160	165	0
+165	170	0
+170	175	0
+175	180	0
+180	185	0
+185	190	0
+190	195	0
+195	200	0
+200	205	0
+205	210	0
+210	215	0
+215	220	0
+220	225	0
+225	230	0
+230	235	0
+235	240	0
+240	245	0
+245	250	0

From ded981b556b74a36a249c8293eea31f4f2d2a3ea Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Sun, 29 Sep 2024 16:41:42 +0200
Subject: [PATCH 4/5] fix default values

---
 src/rseqc/rseqc_inner_distance/config.vsh.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/rseqc/rseqc_inner_distance/config.vsh.yaml b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
index 1b698517..30c84e18 100644
--- a/src/rseqc/rseqc_inner_distance/config.vsh.yaml
+++ b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
@@ -29,8 +29,8 @@ argument_groups:
 
   - name: "--sample_size"
     type: integer
-    example: 200000
-    description: Numer of reads sampled from SAM/BAM file, default = 200000.
+    example: 1000000
+    description: Numer of reads sampled from SAM/BAM file, default = 1000000.
   
   - name: "--map_qual"
     type: integer
@@ -59,7 +59,7 @@ argument_groups:
     type: string
     required: true
     description: Rrefix of output files.
-    
+
   - name: "--output_stats"
     type: file
     direction: output

From 1fb6ab44799358f2449e226ec9b69b0f653ff0a3 Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Tue, 1 Oct 2024 10:12:37 +0200
Subject: [PATCH 5/5] adjust argument names and container image

---
 .../rseqc_inner_distance/config.vsh.yaml      | 21 ++++++++++++-------
 src/rseqc/rseqc_inner_distance/script.sh      | 10 ++++-----
 src/rseqc/rseqc_inner_distance/test.sh        |  6 +++---
 3 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/src/rseqc/rseqc_inner_distance/config.vsh.yaml b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
index 30c84e18..e050bb24 100644
--- a/src/rseqc/rseqc_inner_distance/config.vsh.yaml
+++ b/src/rseqc/rseqc_inner_distance/config.vsh.yaml
@@ -17,37 +17,44 @@ authors:
 argument_groups:
 - name: "Input"
   arguments: 
-  - name: "--input"
+  - name: "--input_file"
+    alternatives: ["-i"]
     type: file 
     required: true
     description: input alignment file in BAM or SAM format
 
   - name: "--refgene"
+    alternatives: ["-r"]
     type: file 
     required: true
     description: Reference gene model in bed format
 
   - name: "--sample_size"
+    alternatives: ["-k"]
     type: integer
     example: 1000000
     description: Numer of reads sampled from SAM/BAM file, default = 1000000.
   
-  - name: "--map_qual"
+  - name: "--mapq"
+    alternatives: ["-q"]
     type: integer
     example: 30 
     description: Minimum mapping quality (phred scaled) to determine uniquely mapped reads, default=30.
 
-  - name: "--lower_bound_size"
+  - name: "--lower_bound"
+    alternatives: ["-l"]
     type: integer
     example: -250 
     description: Lower bound of inner distance (bp). This option is used for ploting histograme, default=-250.
 
-  - name: "--upper_bound_size"
+  - name: "--upper_bound"
+    alternatives: ["-u"]
     type: integer
     example: 250 
     description: Upper bound of inner distance (bp). This option is used for ploting histograme, default=250.
 
-  - name: "--step_size"
+  - name: "--step"
+    alternatives: ["-s"]
     type: integer
     example: 5 
     description: Step size (bp) of histograme. This option is used for plotting histogram, default=5.
@@ -95,10 +102,10 @@ test_resources:
   
 engines:
 - type: docker
-  image: ubuntu:22.04
+  image: python:3.10
   setup:   
     - type: apt
-      packages: [python3-pip, r-base]
+      packages: [r-base]
     - type: python
       packages: [ RSeQC ]
     - type: docker
diff --git a/src/rseqc/rseqc_inner_distance/script.sh b/src/rseqc/rseqc_inner_distance/script.sh
index 655f5b63..fe00c590 100644
--- a/src/rseqc/rseqc_inner_distance/script.sh
+++ b/src/rseqc/rseqc_inner_distance/script.sh
@@ -4,14 +4,14 @@ set -exo pipefail
 
 
 inner_distance.py \
-    -i $par_input \
+    -i $par_input_file \
     -r $par_refgene \
     -o $par_output_prefix \
     ${par_sample_size:+-k "${par_sample_size}"} \
-    ${par_lower_bound_size:+-l "${par_lower_bound_size}"} \
-    ${par_upper_bound_size:+-u "${par_upper_bound_size}"} \
-    ${par_step_size:+-s "${par_step_size}"} \
-    ${par_map_qual:+-q "${par_map_qual}"} \
+    ${par_lower_bound:+-l "${par_lower_bound}"} \
+    ${par_upper_bound:+-u "${par_upper_bound}"} \
+    ${par_step:+-s "${par_step}"} \
+    ${par_mapq:+-q "${par_mapq}"} \
 > stdout.txt
 
 if [[ -n $par_output_stats ]]; then head -n 2 stdout.txt > $par_output_stats; fi
diff --git a/src/rseqc/rseqc_inner_distance/test.sh b/src/rseqc/rseqc_inner_distance/test.sh
index 49405696..927a69a9 100644
--- a/src/rseqc/rseqc_inner_distance/test.sh
+++ b/src/rseqc/rseqc_inner_distance/test.sh
@@ -15,7 +15,7 @@ output_freq="inner_distance_freq.txt"
 echo "> Running $meta_functionality_name"
 
 "$meta_executable" \
-    --input $input_bam \
+    --input_file $input_bam \
     --refgene $input_bed \
     --output_prefix "test" \
     --output_stats $output_stats \
@@ -50,11 +50,11 @@ rm "$output_stats" "$output_dist" "$output_plot" "$output_plot_r" "$output_freq"
 
 echo "> Running $meta_functionality_name with non-default parameters and default output file names"
 "$meta_executable" \
-    --input $input_bam \
+    --input_file $input_bam \
     --refgene $input_bed \
     --output_prefix "test" \
     --sample_size 4 \
-    --map_qual 10
+    --mapq 10
 
 exit_code=$?
 [[ $exit_code != 0 ]] && echo "Non zero exit code: $exit_code" && exit 1