Merge branch 'main' into samtools_fastq

CHANGELOG.md

@@ -44,11 +44,13 @@
     - `samtools/samtools_sort`: Sort SAM/BAM/CRAM files (PR #36).
     - `samtools/samtools_stats`: Reports alignment summary statistics for a BAM file (PR #39).
     - `samtools/samtools_faidx`: Indexes FASTA files to enable random access to fasta and fastq files (PR #41).
+    - `samtools/samtools_collate`: Shuffles and groups reads in SAM/BAM/CRAM files together by their names (PR #42).
+    - `samtools/samtools_view`: Views and converts SAM/BAM/CRAM files (PR #48).
     - `samtools/samtools_fastq`: Converts a SAM/BAM/CRAM file to FASTQ (PR #52).
-    - `samtools_collate`: Shuffles and groups reads in SAM/BAM/CRAM files together by their names (PR #42).
 
 * `falco`: A C++ drop-in replacement of FastQC to assess the quality of sequence read data (PR #43).
 
+
 ## MAJOR CHANGES
 
 ## MINOR CHANGES

src/samtools/samtools_idxstats/config.vsh.yaml

@@ -7,7 +7,7 @@ links:
   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
+  doi: [10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008]
 license: MIT/Expat
 
 argument_groups:

src/samtools/samtools_sort/config.vsh.yaml

@@ -4,7 +4,7 @@ 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
+  documentation: https://www.htslib.org/doc/samtools-sort.html
   repository: https://github.com/samtools/samtools
 references: 
   doi: [10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008]

src/samtools/samtools_stats/config.vsh.yaml

@@ -4,10 +4,10 @@ description: Reports alignment summary statistics for a BAM file.
 keywords: [statistics, counts, bam, sam, cram]
 links:
   homepage: https://www.htslib.org/
-  documentation: https://www.htslib.org/doc/samtools-idxstats.html
+  documentation: https://www.htslib.org/doc/samtools-stats.html
   repository: https://github.com/samtools/samtools
 references: 
-  doi: 10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008
+  doi: [10.1093/bioinformatics/btp352, 10.1093/gigascience/giab008]
 license: MIT/Expat
 
 argument_groups:

src/samtools/samtools_view/help.txt

@@ -0,0 +1,80 @@
+```
+samtools view
+```
+
+Usage: samtools view [options] <in.bam>|<in.sam>|<in.cram> [region ...]
+
+Output options:
+  -b, --bam                  Output BAM
+  -C, --cram                 Output CRAM (requires -T)
+  -1, --fast                 Use fast BAM compression (and default to --bam)
+  -u, --uncompressed         Uncompressed BAM output (and default to --bam)
+  -h, --with-header          Include header in SAM output
+  -H, --header-only          Print SAM header only (no alignments)
+      --no-header            Print SAM alignment records only [default]
+  -c, --count                Print only the count of matching records
+  -o, --output FILE          Write output to FILE [standard output]
+  -U, --unoutput FILE, --output-unselected FILE
+                             Output reads not selected by filters to FILE
+  -p, --unmap                Set flag to UNMAP on reads not selected
+                             then write to output file.
+  -P, --fetch-pairs          Retrieve complete pairs even when outside of region
+Input options:
+  -t, --fai-reference FILE   FILE listing reference names and lengths
+  -M, --use-index            Use index and multi-region iterator for regions
+      --region[s]-file FILE  Use index to include only reads overlapping FILE
+  -X, --customized-index     Expect extra index file argument after <in.bam>
+
+Filtering options (Only include in output reads that...):
+  -L, --target[s]-file FILE  ...overlap (BED) regions in FILE
+  -N, --qname-file [^]FILE   ...whose read name is listed in FILE ("^" negates)
+  -r, --read-group STR       ...are in read group STR
+  -R, --read-group-file [^]FILE
+                             ...are in a read group listed in FILE
+  -d, --tag STR1[:STR2]      ...have a tag STR1 (with associated value STR2)
+  -D, --tag-file STR:FILE    ...have a tag STR whose value is listed in FILE
+  -q, --min-MQ INT           ...have mapping quality >= INT
+  -l, --library STR          ...are in library STR
+  -m, --min-qlen INT         ...cover >= INT query bases (as measured via CIGAR)
+  -e, --expr STR             ...match the filter expression STR
+  -f, --require-flags FLAG   ...have all of the FLAGs present
+  -F, --excl[ude]-flags FLAG ...have none of the FLAGs present
+      --rf, --incl-flags, --include-flags FLAG
+                             ...have some of the FLAGs present
+  -G FLAG                    EXCLUDE reads with all of the FLAGs present
+      --subsample FLOAT      Keep only FLOAT fraction of templates/read pairs
+      --subsample-seed INT   Influence WHICH reads are kept in subsampling [0]
+  -s INT.FRAC                Same as --subsample 0.FRAC --subsample-seed INT
+
+Processing options:
+      --add-flags FLAG       Add FLAGs to reads
+      --remove-flags FLAG    Remove FLAGs from reads
+  -x, --remove-tag STR
+               Comma-separated read tags to strip (repeatable) [null]
+      --keep-tag STR
+               Comma-separated read tags to preserve (repeatable) [null].
+               Equivalent to "-x ^STR"
+  -B, --remove-B             Collapse the backward CIGAR operation
+  -z, --sanitize FLAGS       Perform sanitity checking and fixing on records.
+                             FLAGS is comma separated (see manual). [off]
+
+General options:
+  -?, --help   Print long help, including note about region specification
+  -S           Ignored (input format is auto-detected)
+      --no-PG  Do not add a PG line
+      --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
+  -T, --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

src/samtools/samtools_view/script.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+set -e
+
+[[ "$par_bam" == "false" ]] && unset par_bam
+[[ "$par_cram" == "false" ]] && unset par_cram
+[[ "$par_fast" == "false" ]] && unset par_fast
+[[ "$par_uncompressed" == "false" ]] && unset par_uncompressed
+[[ "$par_with_header" == "false" ]] && unset par_with_header
+[[ "$par_header_only" == "false" ]] && unset par_header_only
+[[ "$par_no_header" == "false" ]] && unset par_no_header
+[[ "$par_count" == "false" ]] && unset par_count
+[[ "$par_unmap" == "false" ]] && unset par_unmap
+[[ "$par_use_index" == "false" ]] && unset par_use_index
+[[ "$par_fetch_pairs" == "false" ]] && unset par_fetch_pairs
+[[ "$par_customized_index" == "false" ]] && unset par_customized_index
+[[ "$par_no_PG" == "false" ]] && unset par_no_PG
+[[ "$par_write_index" == "false" ]] && unset par_write_index
+[[ "$par_remove_B" == "false" ]] && unset par_remove_B
+
+samtools view \
+    ${par_bam:+-b} \
+    ${par_cram:+-C} \
+    ${par_fast:+--fast} \
+    ${par_uncompressed:+-u} \
+    ${par_with_header:+--with-header} \
+    ${par_header_only:+-H} \
+    ${par_no_header:+--no-header} \
+    ${par_count:+-c} \
+    ${par_output:+-o "$par_output"} \
+    ${par_output_unselected:+-U "$par_output_unselected"} \
+    ${par_unmap:+-p "$par_unmap"} \
+    ${par_fetch_pairs:+-P "$par_fetch_pairs"} \
+    ${par_fai_reference:+-t "$par_fai_reference"} \
+    ${par_use_index:+-M "$par_use_index"} \
+    ${par_region_file:+--region-file "$par_region_file"} \
+    ${par_customized_index:+-X} \
+    ${par_target_file:+-L "$par_target_file"} \
+    ${par_qname_file:+-N "$par_qname_file"} \
+    ${par_read_group:+-r "$par_read_group"} \
+    ${par_read_group_file:+-R "$par_read_group_file"} \
+    ${par_tag:+-d "$par_tag"} \
+    ${par_tag_file:+-D "$par_tag_file"} \
+    ${par_min_MQ:+-q "$par_min_MQ"} \
+    ${par_library:+-l "$par_library"} \
+    ${par_min_qlen:+-m "$par_min_qlen"} \
+    ${par_expr:+-e "$par_expr"} \
+    ${par_require_flags:+-f "$par_require_flags"} \
+    ${par_excl_flags:+-F "$par_excl_flags"} \
+    ${par_incl_flags:+--rf "$par_incl_flags"} \
+    ${par_excl_all_flags:+-G "$par_excl_all_flags"} \
+    ${par_subsample:+--subsample "$par_subsample"} \
+    ${par_subsample_seed:+--subsample-seed "$par_subsample_seed"} \
+    ${par_add_flags:+--add-flags "$par_add_flags"} \
+    ${par_remove_flags:+--remove-flags "$par_remove_flags"} \
+    ${par_remove_tag:+-x "$par_remove_tag"} \
+    ${par_keep_tag:+--keep-tag "$par_keep_tag"} \
+    ${par_remove_B:+-B} \
+    ${par_sanitize:+-z "$par_sanitize"} \
+    ${par_input_fmt_option:+--input-fmt-option "$par_input_fmt_option"} \
+    ${par_output_fmt:+-O "$par_output_fmt"} \
+    ${par_output_fmt_option:+--output-fmt-option "$par_output_fmt_option"} \
+    ${par_reference:+-T "$par_reference"} \
+    ${par_write_index:+--write-index} \
+    ${par_no_PG:+--no-PG} \
+    "$par_input"
+
+exit 0

src/samtools/samtools_view/test.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+test_dir="${meta_resources_dir}/test_data"
+temp_dir="${meta_resources_dir}/out"
+
+############################################################################################
+
+echo ">>> Test 1: Import SAM to BAM when @SQ lines are present in the header"
+"$meta_executable" \
+   --bam \
+   --output "$temp_dir/a.bam" \
+   --input "$test_dir/a.sam"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$temp_dir/a.bam" ] && echo "File 'a.bam' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$temp_dir/a.bam" ] && echo "File 'a.bam' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+# compare output of "samtools view" for both files
+diff <(samtools view "$temp_dir/a.bam") <(samtools view "$test_dir/a.bam") || \
+    (echo "Output file a.bam does not match expected output" && exit 1)
+
+############################################################################################
+
+echo ">>> Test 2: ${meta_functionality_name} with CRAM format output"
+
+"$meta_executable" \
+   --cram \
+   --output "$temp_dir/a.cram" \
+   --input "$test_dir/a.sam"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$temp_dir/a.cram" ] && echo "File 'a.cram' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$temp_dir/a.cram" ] && echo "File 'a.cram' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+# compare output of "samtools view" for both files
+diff <(samtools view "$temp_dir/a.cram") <(samtools view "$test_dir/a.cram") || \
+    (echo "Output file a.cram does not match expected output" && exit 1)
+
+############################################################################################
+
+echo ">>> Test 3: ${meta_functionality_name} with --count option"
+
+"$meta_executable" \
+   --count \
+   --output "$temp_dir/a.count" \
+   --input "$test_dir/a.sam"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$temp_dir/a.count" ] && echo "File 'a.count' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$temp_dir/a.count" ] && echo "File 'a.count' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+diff "$temp_dir/a.count" "$test_dir/a.count" || \
+    (echo "Output file a.count does not match expected output" && exit 1)
+
+############################################################################################
+
+echo ">>> Test 4: ${meta_functionality_name} including only the forward reads from read pairs"
+
+"$meta_executable" \
+   --output "$temp_dir/a.forward" \
+   --excl_flags "0x80" \
+   --input "$test_dir/a.sam"
+
+echo ">>> Checking whether output exists"
+[ ! -f "$temp_dir/a.forward" ] && echo "File 'a.forward' does not exist!" && exit 1
+
+echo ">>> Checking whether output is non-empty"
+[ ! -s "$temp_dir/a.forward" ] && echo "File 'a.forward' is empty!" && exit 1
+
+echo ">>> Checking whether output is correct"
+diff "$temp_dir/a.forward" "$test_dir/a.forward" || \
+    (echo "Output file a.forward does not match expected output" && exit 1)
+
+############################################################################################
+
+echo ">>> All test passed successfully"
+rm -rf "${temp_dir}"
+exit 0

src/samtools/samtools_view/test_data/a.count

@@ -0,0 +1 @@
+6

src/samtools/samtools_view/test_data/a.forward

@@ -0,0 +1,3 @@
+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	**********

src/samtools/samtools_view/test_data/a.sam

@@ -0,0 +1,7 @@
+@SQ	SN:xx	LN:20
+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	**********

src/samtools/samtools_view/test_data/script.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# dowload test data from snakemake wrapper
+if [ ! -d /tmp/view_source ]; then
+  git clone --depth 1 --single-branch --branch master https://github.com/snakemake/snakemake-wrappers.git /tmp/view_source
+fi
+
+cp -r /tmp/idxstats_source/bio/samtools/view/test/*.sam src/samtools/samtools_view/test_data