changeset 12:541082d03bef draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/samtools/samtools_stats commit 9c5a35ce695c3d134e41d8695487edd5f71ea33c
author iuc
date Sun, 08 Sep 2024 03:27:04 +0000
parents fed4aa48ba09
children
files macros.xml test-data/1.stats.expected test-data/11.stats.expected test-data/11.stats.g4.expected test-data/12.2reads.nooverlap.expected test-data/12.2reads.overlap.expected test-data/12.3reads.nooverlap.expected test-data/12.3reads.overlap.expected test-data/2.stats.expected test-data/6.stats.expected test-data/samtools_stats_out1.tab
diffstat 11 files changed, 94 insertions(+), 16 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Mon Nov 20 22:17:08 2023 +0000
+++ b/macros.xml	Sun Sep 08 03:27:04 2024 +0000
@@ -11,9 +11,9 @@
          please only bump the minor version in order to let the requirement
          version catch up eventually). To find the tools check:
         `grep "<tool" . -r | grep -v VERSION_SUFFIX | cut -d":" -f 1` -->
-    <token name="@TOOL_VERSION@">1.15.1</token>
+    <token name="@TOOL_VERSION@">1.20</token>
     <token name="@VERSION_SUFFIX@">2</token>
-    <token name="@PROFILE@">20.05</token>
+    <token name="@PROFILE@">22.05</token>
     <token name="@FLAGS@"><![CDATA[
         #set $flags = 0
         #if $filter
--- a/test-data/1.stats.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/1.stats.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats --ref-seq reference.fa -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -419,6 +419,8 @@
 FRL	35	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	35	1
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	40	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
 # Coverage distribution. Use `grep ^COV | cut -f 2-` to extract this part.
--- a/test-data/11.stats.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/11.stats.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats -@ 0 infile ref1:10-24 ref1:30-46 ref1:39-56
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -183,6 +183,32 @@
 FRL	10	14
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	10	12
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	0	1
+MAPQ	1	1
+MAPQ	2	1
+MAPQ	3	1
+MAPQ	4	1
+MAPQ	5	1
+MAPQ	6	1
+MAPQ	7	1
+MAPQ	8	1
+MAPQ	9	1
+MAPQ	10	1
+MAPQ	11	1
+MAPQ	12	1
+MAPQ	13	1
+MAPQ	14	1
+MAPQ	15	1
+MAPQ	16	1
+MAPQ	17	1
+MAPQ	18	1
+MAPQ	19	1
+MAPQ	20	1
+MAPQ	21	1
+MAPQ	22	1
+MAPQ	23	1
+MAPQ	50	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
 # Coverage distribution. Use `grep ^COV | cut -f 2-` to extract this part.
--- a/test-data/11.stats.g4.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/11.stats.g4.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats -g 4 -@ 0 infile ref1:10-24 ref1:30-46 ref1:39-56
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -183,6 +183,32 @@
 FRL	10	14
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	10	12
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	0	1
+MAPQ	1	1
+MAPQ	2	1
+MAPQ	3	1
+MAPQ	4	1
+MAPQ	5	1
+MAPQ	6	1
+MAPQ	7	1
+MAPQ	8	1
+MAPQ	9	1
+MAPQ	10	1
+MAPQ	11	1
+MAPQ	12	1
+MAPQ	13	1
+MAPQ	14	1
+MAPQ	15	1
+MAPQ	16	1
+MAPQ	17	1
+MAPQ	18	1
+MAPQ	19	1
+MAPQ	20	1
+MAPQ	21	1
+MAPQ	22	1
+MAPQ	23	1
+MAPQ	50	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
 # Coverage distribution. Use `grep ^COV | cut -f 2-` to extract this part.
--- a/test-data/12.2reads.nooverlap.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/12.2reads.nooverlap.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,6 +1,6 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
-# The command line was:  stats -t /tmp/tmp0r5zs075/files/b/2/1/dataset_b2175431-044e-449d-8f60-1bfd33679b61.dat -p -@ 0 infile
+# The command line was:  stats -t /tmp/tmp5q_kwqc0/files/5/e/6/dataset_5e6cda5d-79e8-4b8f-9e14-97f3be9f87de.dat -p -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
 # CHK, CRC32 of reads which passed filtering followed by addition (32bit overflow)
 CHK	5b31676a	b0edee94	471895da
@@ -855,6 +855,9 @@
 FRL	100	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	100	1
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	7	1
+MAPQ	37	1
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	2	0	1
 ID	3	1	0
--- a/test-data/12.2reads.overlap.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/12.2reads.overlap.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,6 +1,6 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
-# The command line was:  stats -t /tmp/tmp0r5zs075/files/2/a/2/dataset_2a2a3ee9-3133-4880-a37c-50b6354c9000.dat -@ 0 infile
+# The command line was:  stats -t /tmp/tmp5q_kwqc0/files/4/0/f/dataset_40fb1106-2fe0-491f-8790-2139e9b1b3bd.dat -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
 # CHK, CRC32 of reads which passed filtering followed by addition (32bit overflow)
 CHK	5b31676a	b0edee94	471895da
@@ -855,6 +855,9 @@
 FRL	100	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	100	1
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	7	1
+MAPQ	37	1
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	2	0	1
 ID	3	1	0
--- a/test-data/12.3reads.nooverlap.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/12.3reads.nooverlap.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,6 +1,6 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
-# The command line was:  stats -t /tmp/tmp0r5zs075/files/1/3/0/dataset_13082855-efe1-437e-8a91-ff7d013770db.dat -p -@ 0 infile
+# The command line was:  stats -t /tmp/tmp5q_kwqc0/files/b/2/6/dataset_b262e070-b3ea-4ab2-970d-29726b177ea2.dat -p -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
 # CHK, CRC32 of reads which passed filtering followed by addition (32bit overflow)
 CHK	09f8b87f	140798ec	2b989f07
@@ -872,6 +872,9 @@
 FRL	100	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	100	2
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	37	1
+MAPQ	60	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	1	1	2
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
--- a/test-data/12.3reads.overlap.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/12.3reads.overlap.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,6 +1,6 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
-# The command line was:  stats -t /tmp/tmp0r5zs075/files/6/5/e/dataset_65ea4e4d-a70d-4001-911d-9d81ff2829a6.dat -@ 0 infile
+# The command line was:  stats -t /tmp/tmp5q_kwqc0/files/8/f/b/dataset_8fbfc56f-17f3-4728-895b-34544e586ee7.dat -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
 # CHK, CRC32 of reads which passed filtering followed by addition (32bit overflow)
 CHK	09f8b87f	140798ec	2b989f07
@@ -872,6 +872,9 @@
 FRL	100	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	100	2
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	37	1
+MAPQ	60	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	1	1	2
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
--- a/test-data/2.stats.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/2.stats.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats --ref-seq reference.fa -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -419,6 +419,8 @@
 FRL	35	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	35	1
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	40	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
 # Coverage distribution. Use `grep ^COV | cut -f 2-` to extract this part.
--- a/test-data/6.stats.expected	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/6.stats.expected	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats --insert-size 0 --ref-seq reference.fa -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -419,6 +419,8 @@
 FRL	35	1
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	35	1
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	40	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	1	1	0
 # Indels per cycle. Use `grep ^IC | cut -f 2-` to extract this part. The columns are: cycle, number of insertions (fwd), .. (rev) , number of deletions (fwd), .. (rev)
--- a/test-data/samtools_stats_out1.tab	Mon Nov 20 22:17:08 2023 +0000
+++ b/test-data/samtools_stats_out1.tab	Sun Sep 08 03:27:04 2024 +0000
@@ -1,4 +1,4 @@
-# This file was produced by samtools stats (1.12+htslib-1.12) and can be plotted using plot-bamstats
+# This file was produced by samtools stats (1.20+htslib-1.20) and can be plotted using plot-bamstats
 # This file contains statistics for all reads.
 # The command line was:  stats --ref-seq reference.fa -@ 0 infile
 # CHK, Checksum	[2]Read Names	[3]Sequences	[4]Qualities
@@ -1862,6 +1862,14 @@
 FRL	251	100
 # Read lengths - last fragments. Use `grep ^LRL | cut -f 2-` to extract this part. The columns are: read length, count
 LRL	251	100
+# Mapping qualities for reads !(UNMAP|SECOND|SUPPL|QCFAIL|DUP). Use `grep ^MAPQ | cut -f 2-` to extract this part. The columns are: mapq, count
+MAPQ	0	6
+MAPQ	3	6
+MAPQ	8	3
+MAPQ	23	2
+MAPQ	24	4
+MAPQ	40	2
+MAPQ	42	2
 # Indel distribution. Use `grep ^ID | cut -f 2-` to extract this part. The columns are: length, number of insertions, number of deletions
 ID	1	1	0
 ID	2	1	0