| Previous changeset 24:620d5603d1a8 (2017-01-20) Next changeset 26:7f5a8d427b39 (2018-04-29) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 76065f751b678abf87e6c723be680fecaa8cb589 |
|
modified:
README.rst htseq-count.xml static/images/count_modes.png test-data/htseq-test_samout.bam |
|
added:
test-data/htseq-test_counts_nonunique.tsv |
| b |
| diff -r 620d5603d1a8 -r f1368427a79c README.rst --- a/README.rst Fri Jan 20 15:46:13 2017 -0500 +++ b/README.rst Mon Feb 05 15:04:47 2018 -0500 |
| b |
| @@ -1,21 +1,19 @@ htseq-count wrapper for Galaxy ============================== -Galaxy wrapper for -`htseq-count <http://www-huber.embl.de/users/anders/HTSeq/doc/count.html>`_ -script from python -`HTSeq <http://www-huber.embl.de/users/anders/HTSeq/doc/index.html>`_ package. +Galaxy wrapper for `htseq-count <https://htseq.readthedocs.io/en/release_0.9.1/count.html>`_ +script from the `HTSEQ <https://readthedocs.org/projects/htseq/>`_ python package. Installation ------------ -Installation directly from the `Galaxy Toolshed <http://toolshed.g2.bx.psu.edu/view/lparsons/htseq_count>`_ is -recommended. +Installation directly from the `Galaxy Toolshed <http://toolshed.g2.bx.psu.edu/view/lparsons/htseq_count>`_ +is recommended. Galaxy Wrapper License ---------------------- -Copyright (c) 2012-2014, Lance R. Parsons <lparsons@princeton.edu> +Copyright (c) 2012-2018, Lance R. Parsons <lparsons@princeton.edu> All rights reserved. Licensed under the BSD 2-Clause License: <http://opensource.org/licenses/BSD-2-Clause> |
| b |
| diff -r 620d5603d1a8 -r f1368427a79c htseq-count.xml --- a/htseq-count.xml Fri Jan 20 15:46:13 2017 -0500 +++ b/htseq-count.xml Mon Feb 05 15:04:47 2018 -0500 |
| [ |
| b'@@ -1,8 +1,8 @@\n-<tool id="htseq_count" name="htseq-count" version="0.6.1galaxy3" profile="16.04">\n+<tool id="htseq_count" name="htseq-count" version="0.9.1" profile="16.04">\n <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description>\n <requirements>\n- <requirement type="package" version="0.6.1.post1">htseq</requirement>\n- <requirement type="package" version="1.3.1">samtools</requirement>\n+ <requirement type="package" version="0.9.1">htseq</requirement>\n+ <requirement type="package" version="1.7">samtools</requirement>\n </requirements>\n \n <stdio>\n@@ -12,7 +12,6 @@\n <regex match="Error: Feature (.+) does not contain a \'(.+)\' attribute" source="both" level="fatal" description="Error parsing the GFF file, at least one feature of the specified \'Feature type\' does not have a value for the specified \'ID Attribute\'" />\n <regex match="Error occured in line (\\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />\n <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />\n- <regex match="Warning: Read (.+) claims to have an aligned mate which could not be found. \\(Is the SAM file properly sorted\\?\\)" source="stderr" level="warning" description="PAIRED DATA MISSING OR NOT PROPERLY SORTED. Try reruning and selecting the option to \'Force sorting of SAM/BAM file by NAME\'. See stderr output of this dataset for more information." />\n </stdio>\n \n <version_command>htseq-count -h | grep version | sed \'s/^\\(.*\\)*\\(version .*\\)\\./\\2/\'</version_command>\n@@ -20,21 +19,22 @@\n <command><![CDATA[\n ##set up input files\n #set $reference_fasta_filename = "localref.fa"\n- #if $samout_conditional.samout == "Yes":\n- #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":\n- ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" &&\n- samtools faidx \'${reference_fasta_filename}\' 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 &&\n- #else:\n- #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )\n+ #set $name_sorted_alignment_filename = "name_sorted_alignment.sam"\n+ #if str( $advanced_options.advanced_options_selector ) == "advanced":\n+ #if str( $advanced_options.samout_conditional.samout ) == "Yes":\n+ #if str( $advanced_options.samout_conditional.reference_source.reference_source_selector ) == "history":\n+ ln -s "${advanced_options.samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" &&\n+ samtools faidx \'${reference_fasta_filename}\' 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 &&\n+ #else:\n+ #set $reference_fasta_filename = str( $advanced_options.samout_conditional.reference_source.ref_file.fields.path )\n+ #end if\n #end if\n #end if\n \n- #if $force_sort == "True":\n- #if $samfile.extension == \'bam\':\n- samtools sort -n -o \'name_sorted_alignment.bam\' \'$samfile\' &&\n- #else\n- samtools view -Su -t \'${reference_fasta_filename}.fai\' \'$samfile\' | samtools sort -n -o \'name_sorted_alignment.bam\' - &&\n- #end if\n+ #if $samfile.extension == \'bam\':\n+ samtools sort -n --output-fmt=SAM -o \'$name_sorted_alignment_filename\' \'$samfile\' &&\n+ #else\n+ samtools view -Su -t \'${reference_fasta_filename}.fai\' \'$samfile\' | samtools sort -n --output-fmt=SAM -o \'$name_sorted_alignment_filename\' - &&\n #end if\n \n htseq-count\n@@ -43,28 +43,31 @@\n --minaqual=$minaqual\n --type=\'$featuretype\'\n --idattr=\'$idattr\'\n- #if $samout_conditional.samout == "Yes":\n- --samout=\'$__new_file_path__/${samoutfile.id}_tmp\'\n+\n+ #if str( $advanced_options.advanced_options_selector ) == "advanced'..b"on. If your data is not sorted, use the samtools sort function of samtools to sort it. Use this option, with name or pos for <order> to indicate how the input data has been sorted. The default is name.\n+\n+ If name is indicated, htseq-count expects all the alignments for the reads of a given read pair to appear in adjacent records in the input data. For pos, this is not expected; rather, read alignments whose mate alignment have not yet been seen are kept in a buffer in memory until the mate is found. While, strictly speaking, the latter will also work with unsorted data, sorting ensures that most alignment mates appear close to each other in the data and hence the buffer is much less likely to overflow.\n+\n+ --max-reads-in-buffer=<number>\n+\n+ When <alignment_file> is paired end sorted by position, allow only so many reads to stay in memory until the mates are found (raising this number will use more memory). Has no effect for single end or paired end sorted by name. (default: 30000000)\n+\n+ -s <yes/no/reverse>, --stranded=<yes/no/reverse>\n+\n+ whether the data is from a strand-specific assay (default: yes)\n+\n+ For stranded=no, a read is considered overlapping with a feature regardless of whether it is mapped to the same or the opposite strand as the feature. For stranded=yes and single-end reads, the read has to be mapped to the same strand as the feature. For paired-end reads, the first read has to be on the same strand and the second read on the opposite strand. For stranded=reverse, these rules are reversed.\n+\n+ -a <minaqual>, --a=<minaqual>\n+\n+ skip all reads with alignment quality lower than the given minimum value (default: 10 \xe2\x80\x94 Note: the default used to be 0 until version 0.5.4.)\n+\n+ -t <feature type>, --type=<feature type>\n+\n+ feature type (3rd column in GFF file) to be used, all features of other type are ignored (default, suitable for RNA-Seq analysis using an Ensembl GTF file: exon)\n+\n+ -i <id attribute>, --idattr=<id attribute>\n+\n+ GFF attribute to be used as feature ID. Several GFF lines with the same feature ID will be considered as parts of the same feature. The feature ID is used to identity the counts in the output table. The default, suitable for RNA-Seq analysis using an Ensembl GTF file, is gene_id.\n \n-Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology\n-Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General\n-Public License v3. Part of the 'HTSeq' framework.\n+ --additional-attr=<id attributes>\n+\n+ Additional feature attributes, which will be printed as an additional column after the primary attribute column but before the counts column(s). The default is none, a suitable value to get gene names using an Ensembl GTF file is gene_name.\n+\n+ -m <mode>, --mode=<mode>\n+\n+ Mode to handle reads overlapping more than one feature. Possible values for <mode> are union, intersection-strict and intersection-nonempty (default: union)\n+\n+ --nonunique=<nonunique mode>\n+\n+ Mode to handle reads that align to or are assigned to more than one feature in the overlap <mode> of choice (see -m option). <nonunique mode> are none and all (default: none)\n+\n+ --secondary-alignments=<mode>\n+\n+ Mode to handle secondary alignments (SAM flag 0x100). <mode> can be score and ignore (default: score)\n+\n+ --supplementary-alignments=<mode>\n+\n+ Mode to handle supplementary/chimeric alignments (SAM flag 0x800). <mode> can be score and ignore (default: score)\n+\n+ -o <samout>, --samout=<samout>\n+\n+ write out all SAM alignment records into an output SAM file called <samout>, annotating each line with its assignment to a feature or a special counter (as an optional field with tag \xe2\x80\x98XF\xe2\x80\x99)\n+\n+ -q, --quiet\n+\n+ suppress progress report and warnings\n+\n+ -h, --help\n+\n+ Show a usage summary and exit\n+\n+.. _FAQ: https://htseq.readthedocs.io/en/release_0.9.1/count.html#frequenctly-asked-questions\n+\n ]]>\n </help>\n <citations>\n" |
| b |
| diff -r 620d5603d1a8 -r f1368427a79c static/images/count_modes.png |
| b |
| Binary file static/images/count_modes.png has changed |
| b |
| diff -r 620d5603d1a8 -r f1368427a79c test-data/htseq-test_counts_nonunique.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/htseq-test_counts_nonunique.tsv Mon Feb 05 15:04:47 2018 -0500 |
| b |
| @@ -0,0 +1,127 @@ +HRA1 0 +YAL001C 3 +YAL002W 2 +YAL003W 31 +YAL004W 0 +YAL005C 31 +YAL007C 8 +YAL008W 0 +YAL009W 0 +YAL010C 0 +YAL011W 1 +YAL012W 6 +YAL013W 1 +YAL014C 0 +YAL015C 1 +YAL016C-A 0 +YAL016C-B 0 +YAL016W 4 +YAL017W 3 +YAL018C 0 +YAL019W 5 +YAL019W-A 0 +YAL020C 0 +YAL021C 1 +YAL022C 0 +YAL023C 7 +YAL024C 0 +YAL025C 3 +YAL026C 4 +YAL026C-A 0 +YAL027W 0 +YAL028W 0 +YAL029C 7 +YAL030W 2 +YAL031C 2 +YAL031W-A 0 +YAL032C 0 +YAL033W 3 +YAL034C 0 +YAL034C-B 0 +YAL034W-A 1 +YAL035W 23 +YAL036C 7 +YAL037C-A 0 +YAL037C-B 0 +YAL037W 0 +YAL038W 105 +YAL039C 3 +YAL040C 5 +YAL041W 3 +YAL042C-A 0 +YAL042W 6 +YAL043C 3 +YAL044C 2 +YAL044W-A 2 +YAL045C 0 +YAL046C 0 +YAL047C 2 +YAL047W-A 0 +YAL048C 0 +YAL049C 1 +YAL051W 1 +YAL053W 4 +YAL054C 0 +YAL055W 0 +YAL056C-A 0 +YAL056W 0 +YAL058W 1 +YAL059C-A 0 +YAL059W 2 +YAL060W 4 +YAL061W 3 +YAL062W 0 +YAL063C 0 +YAL063C-A 0 +YAL064C-A 0 +YAL064W 0 +YAL064W-B 0 +YAL065C 0 +YAL066W 0 +YAL067C 0 +YAL067W-A 0 +YAL068C 0 +YAL068W-A 0 +YAL069W 0 +YAR002C-A 2 +YAR002W 2 +YAR003W 3 +YAR007C 4 +YAR008W 1 +YAR009C 0 +YAR010C 0 +YAR014C 5 +YAR015W 5 +YAR018C 0 +YAR019C 1 +YAR019W-A 0 +YAR020C 0 +YAR023C 0 +YAR027W 2 +YAR028W 0 +YAR029W 0 +YAR030C 0 +YAR031W 0 +YAR033W 0 +YAR035C-A 0 +YAR035W 0 +YAR042W 2 +YAR047C 0 +YAR050W 0 +YAR053W 0 +YAR060C 0 +YAR061W 0 +YAR062W 0 +YAR064W 0 +YAR066W 0 +YAR068W 11 +YAR069C 0 +YAR070C 0 +YAR071W 1 +YAR073W 0 +YAR075W 0 +snR18 1 +tA(UGC)A 0 +tL(CAA)A 0 +tP(UGG)A 0 +tS(AGA)A 0 |
| b |
| diff -r 620d5603d1a8 -r f1368427a79c test-data/htseq-test_samout.bam |
| b |
| Binary file test-data/htseq-test_samout.bam has changed |
