From d3b20532f669b09319bc62e551febfa0b1111a8f Mon Sep 17 00:00:00 2001
From: emmarousseau <emmarou1@icloud.com>
Date: Sat, 13 Apr 2024 08:28:56 +0100
Subject: [PATCH] Samtools sort (#36)

* Initial version of samtools sort, no tests

* Add tests, final touches

* Update changelog

* Update src/samtools/samtools_sort/config.vsh.yaml

Remove "must_exist: false" since that is the default value

Co-authored-by: Robrecht Cannoodt <rcannood@gmail.com>

* Clean up test script, update changelog

* Minor changes, paths, config and script

---------

Co-authored-by: Robrecht Cannoodt <rcannood@gmail.com>
---
 CHANGELOG.md                                  |   1 +
 src/samtools/samtools_sort/config.vsh.yaml    | 149 ++++++++++++++++++
 src/samtools/samtools_sort/help.txt           |  40 +++++
 src/samtools/samtools_sort/script.sh          |  43 +++++
 src/samtools/samtools_sort/test.sh            |  79 ++++++++++
 src/samtools/samtools_sort/test_data/a.bam    | Bin 0 -> 184 bytes
 .../test_data/output/a_ref.sorted.bam         | Bin 0 -> 301 bytes
 .../test_data/output/ascii_ref.sorted.bam     | Bin 0 -> 325 bytes
 .../output/compressed_ref.sorted.bam          | Bin 0 -> 312 bytes
 .../samtools_sort/test_data/script.sh         |   8 +
 .../test_data/text/a_ref.sorted.txt           |   6 +
 .../test_data/text/ascii_ref.sorted.txt       |   6 +
 .../test_data/text/compressed_ref.sorted.txt  |   6 +
 13 files changed, 338 insertions(+)
 create mode 100644 src/samtools/samtools_sort/config.vsh.yaml
 create mode 100644 src/samtools/samtools_sort/help.txt
 create mode 100644 src/samtools/samtools_sort/script.sh
 create mode 100644 src/samtools/samtools_sort/test.sh
 create mode 100644 src/samtools/samtools_sort/test_data/a.bam
 create mode 100644 src/samtools/samtools_sort/test_data/output/a_ref.sorted.bam
 create mode 100644 src/samtools/samtools_sort/test_data/output/ascii_ref.sorted.bam
 create mode 100644 src/samtools/samtools_sort/test_data/output/compressed_ref.sorted.bam
 create mode 100755 src/samtools/samtools_sort/test_data/script.sh
 create mode 100644 src/samtools/samtools_sort/test_data/text/a_ref.sorted.txt
 create mode 100644 src/samtools/samtools_sort/test_data/text/ascii_ref.sorted.txt
 create mode 100644 src/samtools/samtools_sort/test_data/text/compressed_ref.sorted.txt

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 43787a4b..ba7bf0e3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -39,6 +39,7 @@
     - `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).
     - `samtools/samtools_index`: Index SAM/BAM/CRAM files (PR #35).
+    - `samtools/samtools_sort`: Sort SAM/BAM/CRAM files (PR #36).
     - `samtools/samtools_stats`: Reports alignment summary statistics for a BAM file (PR #39).
 
 ## MAJOR CHANGES
diff --git a/src/samtools/samtools_sort/config.vsh.yaml b/src/samtools/samtools_sort/config.vsh.yaml
new file mode 100644
index 00000000..7cd9ec48
--- /dev/null
+++ b/src/samtools/samtools_sort/config.vsh.yaml
@@ -0,0 +1,149 @@
+name: samtools_sort
+namespace: samtools
+description: Sort SAM/BAM/CRAM file.
+keywords: [sort, bam, sam, cram]
+links:
+  homepage: https://www.htslib.org/
+  documentation: https://www.htslib.org/doc/samtools-idxstats.html
+  repository: https://github.com/samtools/samtools
+references: 
+  doi: [10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008]
+license: MIT/Expat
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        type: file
+        description: SAM/BAM/CRAM input file.
+        required: true
+        must_exist: true
+  - name: Outputs
+    arguments:
+      - name: --output
+        type: file
+        description: |
+          Write final output to file.
+        required: true
+        direction: output
+        example: out.bam
+      - name: --output_fmt
+        alternatives: -O
+        type: string
+        description: |
+          Specify output format (SAM, BAM, CRAM).
+        example: BAM
+      - name: --output_fmt_option
+        type: string
+        description: |
+          Specify a single output file format option in the form
+          of OPTION or OPTION=VALUE.
+      - name: --reference
+        type: file
+        description: |
+          Reference sequence FASTA FILE.
+        example: ref.fa
+      - name: --write_index
+        type: boolean_true
+        description: |
+          Automatically index the output files.
+      - name: --prefix
+        alternatives: -T
+        type: string
+        description: |
+          Write temporary files to PREFIX.nnnn.bam.
+      - name: --no_PG
+        type: boolean_true
+        description: |
+          Do not add a PG line.
+      - name: --template_coordinate
+        type: boolean_true
+        description: |
+          Sort by template-coordinate.
+      - name: --input_fmt_option
+        type: string
+        description: |
+          Specify a single input file format option in the form
+          of OPTION or OPTION=VALUE.
+  - name: Options
+    arguments:
+      - name: --compression
+        alternatives: -l
+        type: integer
+        description: |
+          Set compression level, from 0 (uncompressed) to 9 (best).
+        default: 0
+      - name: --uncompressed
+        alternatives: -u
+        type: boolean_true
+        description: |
+          Output uncompressed data (equivalent to --compression 0).
+      - name: --minimiser
+        alternatives: -M
+        type: boolean_true
+        description: |
+          Use minimiser for clustering unaligned/unplaced reads.
+      - name: --not_reverse
+        alternatives: -R
+        type: boolean_true
+        description: |
+          Do not use reverse strand (only compatible with --minimiser)
+      - name: --kmer_size
+        alternatives: -K
+        type: integer
+        description: |
+          Kmer size to use for minimiser.
+        example: 20
+      - name: --order
+        alternatives: -I
+        type: file
+        description: |
+          Order minimisers by their position in FILE FASTA.
+        example: ref.fa
+      - name: --window
+        alternatives: -w
+        type: integer
+        description: |
+          Window size for minimiser INDEXING VIA --order REF.FA.
+        example: 100
+      - name: --homopolymers
+        alternatives: -H
+        type: boolean_true
+        description: |
+          Squash homopolymers when computing minimiser.
+      - name: --natural_sort
+        alternatives: -n
+        type: boolean_true
+        description: |
+          Sort by read name (natural): cannot be used with samtools index.
+      - name: --ascii_sort
+        alternatives: -N
+        type: boolean_true
+        description: |
+          Sort by read name (ASCII): cannot be used with samtools index.
+      - name: --tag
+        alternatives: -t
+        type: string
+        description: |
+          Sort by value of TAG. Uses position as secondary index 
+          (or read name if --natural_sort is set).
+
+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/samtools:1.19.2--h50ea8bc_1
+    setup:
+      - type: docker
+        run: |
+          samtools --version 2>&1 | grep -E '^(samtools|Using htslib)' | \
+          sed 's#Using ##;s# \([0-9\.]*\)$#: \1#' > /var/software_versions.txt
+runners:
+- type: executable
+- type: nextflow
\ No newline at end of file
diff --git a/src/samtools/samtools_sort/help.txt b/src/samtools/samtools_sort/help.txt
new file mode 100644
index 00000000..27cd86a0
--- /dev/null
+++ b/src/samtools/samtools_sort/help.txt
@@ -0,0 +1,40 @@
+```
+samtools sort
+```
+
+Usage: samtools sort [options...] [in.bam]
+Options:
+  -l INT     Set compression level, from 0 (uncompressed) to 9 (best)
+  -u         Output uncompressed data (equivalent to -l 0)
+  -m INT     Set maximum memory per thread; suffix K/M/G recognized [768M]
+  -M         Use minimiser for clustering unaligned/unplaced reads
+  -R         Do not use reverse strand (only compatible with -M)
+  -K INT     Kmer size to use for minimiser [20]
+  -I FILE    Order minimisers by their position in FILE FASTA
+  -w INT     Window size for minimiser indexing via -I ref.fa [100]
+  -H         Squash homopolymers when computing minimiser
+  -n         Sort by read name (natural): cannot be used with samtools index
+  -N         Sort by read name (ASCII): cannot be used with samtools index
+  -t TAG     Sort by value of TAG. Uses position as secondary index (or read name if -n is set)
+  -o FILE    Write final output to FILE rather than standard output
+  -T PREFIX  Write temporary files to PREFIX.nnnn.bam
+      --no-PG
+               Do not add a PG line
+      --template-coordinate
+               Sort by template-coordinate
+      --input-fmt-option OPT[=VAL]
+               Specify a single input file format option in the form
+               of OPTION or OPTION=VALUE
+  -O, --output-fmt FORMAT[,OPT[=VAL]]...
+               Specify output format (SAM, BAM, CRAM)
+      --output-fmt-option OPT[=VAL]
+               Specify a single output file format option in the form
+               of OPTION or OPTION=VALUE
+      --reference FILE
+               Reference sequence FASTA FILE [null]
+  -@, --threads INT
+               Number of additional threads to use [0]
+      --write-index
+               Automatically index the output files [off]
+      --verbosity INT
+               Set level of verbosity
\ No newline at end of file
diff --git a/src/samtools/samtools_sort/script.sh b/src/samtools/samtools_sort/script.sh
new file mode 100644
index 00000000..94836c18
--- /dev/null
+++ b/src/samtools/samtools_sort/script.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -e
+
+[[ "$par_uncompressed" == "false" ]] && unset par_uncompressed
+[[ "$par_minimiser" == "false" ]] && unset par_minimiser
+[[ "$par_not_reverse" == "false" ]] && unset par_not_reverse
+[[ "$par_homopolymers" == "false" ]] && unset par_homopolymers
+[[ "$par_natural_sort" == "false" ]] && unset par_natural_sort
+[[ "$par_ascii_sort" == "false" ]] && unset par_ascii_sort
+[[ "$par_template_coordinate" == "false" ]] && unset par_template_coordinate
+[[ "$par_write_index" == "false" ]] && unset par_write_index
+[[ "$par_no_PG" == "false" ]] && unset par_no_PG
+
+
+samtools sort \
+    ${par_compression:+-l "$par_compression"} \
+    ${par_uncompressed:+-u} \
+    ${par_minimiser:+-M} \
+    ${par_not_reverse:+-R} \
+    ${par_kmer_size:+-K "$par_kmer_size"} \
+    ${par_order:+-I "$par_order"} \
+    ${par_window:+-w "$par_window"} \
+    ${par_homopolymers:+-H} \
+    ${par_natural_sort:+-n} \
+    ${par_ascii_sort:+-N} \
+    ${par_tag:+-t "$par_tag"} \
+    ${par_input_fmt_option:+--input-fmt-option "$par_input_fmt_option"} \
+    ${par_template_coordinate:+--template-coordinate} \
+    ${par_write_index:+--write-index} \
+    ${par_prefix:+-T "$par_prefix"} \
+    ${par_no_PG:+--no-PG} \
+    ${par_output_fmt:+-O "$par_output_fmt"} \
+    ${par_output_fmt_option:+--output-fmt-option "$par_output_fmt_option"} \
+    ${par_reference:+--reference "$par_reference"} \
+    -o "$par_output" \
+    "$par_input"
+
+# save text files containing the output of samtools view for later comparison
+samtools view "$par_output" -o "$par_output".txt
\ No newline at end of file
diff --git a/src/samtools/samtools_sort/test.sh b/src/samtools/samtools_sort/test.sh
new file mode 100644
index 00000000..d8425dc9
--- /dev/null
+++ b/src/samtools/samtools_sort/test.sh
@@ -0,0 +1,79 @@
+#!/bin/bash
+
+test_dir="${meta_resources_dir}/test_data"
+out_dir="${meta_resources_dir}/test_data/text"
+
+# Files are compared using the "samtools view" output.
+############################################################################################
+
+echo ">>> Test 1: Sorting a BAM file"
+
+"$meta_executable" \
+  --input "$test_dir/a.bam" \
+  --output "$test_dir/a.sorted.bam"
+
+echo ">>> Check if output file exists"
+[ ! -f "$test_dir/a.sorted.bam" ] \
+    && echo "Output file a.sorted.bam does not exist" && exit 1
+
+echo ">>> Check if output is empty"
+[ ! -s "$test_dir/a.sorted.bam" ] \
+    && echo "Output file a.sorted.bam is empty" && exit 1
+
+echo ">>> Check if output matches expected output"
+diff -a "$test_dir/a.sorted.bam.txt" "$out_dir/a_ref.sorted.txt" \
+    || (echo "Output file a.sorted.bam does not match expected output" && exit 1)
+
+rm "$test_dir/a.sorted.bam" "$test_dir/a.sorted.bam.txt"
+
+############################################################################################
+
+echo ">>> Test 2: Sorting a BAM file according to ascii order"
+
+"$meta_executable" \
+  --input "$test_dir/a.bam" \
+  --ascii_sort \
+  --output "$test_dir/ascii.sorted.bam"
+
+echo ">>> Check if output file exists"
+[ ! -f "$test_dir/ascii.sorted.bam" ] \
+    && echo "Output file ascii.sorted.bam does not exist" && exit 1
+
+echo ">>> Check if output is empty"
+[ ! -s "$test_dir/ascii.sorted.bam" ] \
+    && echo "Output file ascii.sorted.bam is empty" && exit 1
+
+echo ">>> Check if output matches expected output"
+diff -a "$test_dir/ascii.sorted.bam.txt" "$out_dir/ascii_ref.sorted.txt" \
+    || (echo "Output file ascii.sorted.bam does not match expected output" && exit 1)
+
+rm "$test_dir/ascii.sorted.bam" "$test_dir/ascii.sorted.bam.txt"
+
+############################################################################################
+
+echo ">>> Test 3: Sorting a BAM file with compression"
+
+"$meta_executable" \
+  --input "$test_dir/a.bam" \
+  --compression 5 \
+  --output "$test_dir/compressed.sorted.bam"
+  
+echo ">>> Check if output file exists"
+[ ! -f "$test_dir/compressed.sorted.bam" ] \
+    && echo "Output file compressed.sorted.bam does not exist" && exit 1
+
+echo ">>> Check if output is empty"
+[ ! -s "$test_dir/compressed.sorted.bam" ] \
+    && echo "Output file compressed.sorted.bam is empty" && exit 1
+
+echo ">>> Check if output matches expected output" #
+diff "$test_dir/compressed.sorted.bam.txt" "$out_dir/compressed_ref.sorted.txt" \
+    || (echo "Output file compressed.sorted.bam does not match expected output" && exit 1)
+
+rm "$test_dir/compressed.sorted.bam" "$test_dir/compressed.sorted.bam.txt"
+
+############################################################################################
+
+
+echo "All tests succeeded!"
+exit 0
\ No newline at end of file
diff --git a/src/samtools/samtools_sort/test_data/a.bam b/src/samtools/samtools_sort/test_data/a.bam
new file mode 100644
index 0000000000000000000000000000000000000000..dba1268acbd8446e4fde54d7da33434597fbe635
GIT binary patch
literal 184
zcmb2|=3rp}f&Xj_PR>jWb_~TuUs6R95)ukH_@3~5+q`PUgD)R98yP)FV(BtuE_7vW
z=9s|5aI{h|P#vgC9!+};gK@G0Lz<hvqFY-Eo1TWeOE*K|BE`c@3aT7Ta|#mNTF$9#
zDph-Y^(5<cOUZS@EcgEW|1baQ7N3BEZ@SP;tH~Q*u`nF>-KrbIh-tVq12fpEAOZjf
CvNY8I

literal 0
HcmV?d00001

diff --git a/src/samtools/samtools_sort/test_data/output/a_ref.sorted.bam b/src/samtools/samtools_sort/test_data/output/a_ref.sorted.bam
new file mode 100644
index 0000000000000000000000000000000000000000..da4edc86ce845f32e87096851b93ac7d1e381b46
GIT binary patch
literal 301
zcmb2|=3rp}f&Xj_PR>jW%NdG`zNF4Mb>P5*2M-TPK1)wsk$z0_P5#t5^W&#XnmIjU
z(y6BcGAAV8q=yC`eEB#%HRZrlfd}VazDx?8Gb4J^{Q1FWBp<XVH1is4xnlgN<XdC6
zmdJDQsTwbyX-`=qHvPzQm1!!ko==}9GG*Ee^<&~om%VIU5*++xl2Gx)5S6AMF+Dsy
zJZFGdRFp>vNHGNa_av_YI!_+Wof!<q$qo!@ZvKjHZ7FPe8uPmw8y#C38x=23NMvMY
zZe9Qc3hFX51Q!~2=FB}=QCf7c)UWMzN<u<H#pnP3>sMr3TLFQ`<(V$q&ZVreVm$7<
RRX2ta(;{gGW^nj`2mtJmbie=r

literal 0
HcmV?d00001

diff --git a/src/samtools/samtools_sort/test_data/output/ascii_ref.sorted.bam b/src/samtools/samtools_sort/test_data/output/ascii_ref.sorted.bam
new file mode 100644
index 0000000000000000000000000000000000000000..58e4f57e7061005d529f9fbeb58cde781386eb0f
GIT binary patch
literal 325
zcmb2|=3rp}f&Xj_PR>jWdl`It9Qm3IL|FG1hF+6v;AS{<=*YSN&nqn2%Q~Y!wXX6#
zkQ6<s%D6whK=IwZJw9oBt$gk=On7HhlxD&w-Xi~Uv-q#C2f_r-xi9D~*c4>mdp9=h
zMun!m;JFpWD(NOOt1~yM{_c^=SsT==$SVEaTu%RROU|eJuceo+l{c^t*e7~ynrT!|
zNdE47ZW&sd-n#1^CUjcuN%)=q@W4G5hGh&7WX>==U_K=&@#Z|x(eh}n&tfo6c3?<z
z^H+3hOJUQ~nBU#l=-ATOsCaQgA|o?%^8z4HP?wpZxU%WR9G>eZ4;(n~;o1NH{{!aA
rg1`)`k2hz!Y@6$ua(kxFwz(%G-m)<KSWxH_!-#2>Gy^j@+&}~X>U@0T

literal 0
HcmV?d00001

diff --git a/src/samtools/samtools_sort/test_data/output/compressed_ref.sorted.bam b/src/samtools/samtools_sort/test_data/output/compressed_ref.sorted.bam
new file mode 100644
index 0000000000000000000000000000000000000000..d10c2c0079e633c0edc9ee46b03ca58e8a790ecf
GIT binary patch
literal 312
zcmb2|=3rp}f&Xj_PR>jWn;3k14sta)h`7$*B6Yp?z@LU$PL7*532ALODRAr56CZ&L
z|Fn4q|1bBq>8`rFxBc+VJimk744<42t_xc7vFmF3MWv{}6<S7#aq$tlt>4#7QHpM<
z+?sye$>OST((?$_`rpDH*9(u8J)K_EKCR-)N7eoblMAn8xN04o*fw#J*zbc<&wKLL
z>^wd>r=%wM@BCHE<k=Vum>J$D@-gIR951il1$3!Anv*jajFTN0(%k$N-P%&v^fcyo
zH#R!9G&U+;oRG-K%-p;H2o%(1W(Y1c?#!8cvZA!;V5wi*>y(6qgo@Aq|JSd`wzdKS
ekIOS%ww+5^W5syfcdKp;Bc?^t49wu50ucafe|m-h

literal 0
HcmV?d00001

diff --git a/src/samtools/samtools_sort/test_data/script.sh b/src/samtools/samtools_sort/test_data/script.sh
new file mode 100755
index 00000000..a7a5b13c
--- /dev/null
+++ b/src/samtools/samtools_sort/test_data/script.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# dowload test data from snakemake wrapper
+if [ ! -d /tmp/idxstats_source ]; then
+  git clone --depth 1 --single-branch --branch master https://github.com/snakemake/snakemake-wrappers.git /tmp/sort_source
+fi
+
+cp -r /tmp/sort_source/bio/samtools/sort/test/mapped/* src/samtools/samtools_sort/test_data
diff --git a/src/samtools/samtools_sort/test_data/text/a_ref.sorted.txt b/src/samtools/samtools_sort/test_data/text/a_ref.sorted.txt
new file mode 100644
index 00000000..ce8d0527
--- /dev/null
+++ b/src/samtools/samtools_sort/test_data/text/a_ref.sorted.txt
@@ -0,0 +1,6 @@
+a1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+b1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+c1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+a1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+b1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+c1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
diff --git a/src/samtools/samtools_sort/test_data/text/ascii_ref.sorted.txt b/src/samtools/samtools_sort/test_data/text/ascii_ref.sorted.txt
new file mode 100644
index 00000000..00cdbc69
--- /dev/null
+++ b/src/samtools/samtools_sort/test_data/text/ascii_ref.sorted.txt
@@ -0,0 +1,6 @@
+a1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+a1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+b1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+b1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+c1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+c1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
diff --git a/src/samtools/samtools_sort/test_data/text/compressed_ref.sorted.txt b/src/samtools/samtools_sort/test_data/text/compressed_ref.sorted.txt
new file mode 100644
index 00000000..ce8d0527
--- /dev/null
+++ b/src/samtools/samtools_sort/test_data/text/compressed_ref.sorted.txt
@@ -0,0 +1,6 @@
+a1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+b1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+c1	99	xx	1	1	10M	=	11	20	AAAAAAAAAA	**********
+a1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+b1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********
+c1	147	xx	11	1	10M	=	1	-20	TTTTTTTTTT	**********