annotate htseq-count.xml @ 25:88cea300225a draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
author iuc
date Tue, 17 Jan 2017 09:26:25 -0500
parents 0c01ed8d0e60
children d8c5761a8ba7
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
1 <tool id="htseq_count" name="htseq-count" version="0.6.1galaxy3" profile="16.04">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
2 <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
3 <requirements>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
4 <requirement type="package" version="0.6.1.post1">htseq</requirement>
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
5 <requirement type="package" version="1.3.1">samtools</requirement>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
6 </requirements>
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
7
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
8 <stdio>
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
9 <exit_code range="1:" level="fatal" description="Unknown error occurred" />
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
10 <regex match="htseq-count: (command ){0,1}not found" source="stderr" level="fatal" description="The HTSeq python package is not properly installed, contact Galaxy administrators" />
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
11 <regex match="samtools: (command ){0,1}not found" source="stderr" level="fatal" description="The samtools package is not properly installed, contact Galaxy administrators" />
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
12 <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'" />
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
13 <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
14 <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
15 <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." />
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
16 </stdio>
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
17
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
18 <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command>
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
19
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
20 <command><![CDATA[
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
21 ##set up input files
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
22 #set $reference_fasta_filename = "localref.fa"
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
23 #if $samout_conditional.samout == "Yes":
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
24 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
25 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" &&
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
26 samtools faidx '${reference_fasta_filename}' 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 &&
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
27 #else:
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
28 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
29 #end if
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
30 #end if
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
31
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
32 #if $force_sort == "True":
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
33 #if $samfile.extension == 'bam':
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
34 samtools sort -n -o 'name_sorted_alignment.bam' '$samfile' &&
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
35 #else
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
36 samtools view -Su -t '${reference_fasta_filename}.fai' '$samfile' | samtools sort -n -o 'name_sorted_alignment.bam' - &&
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
37 #end if
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
38 #end if
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
39
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
40 htseq-count
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
41 --mode=$mode
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
42 --stranded=$stranded
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
43 --minaqual=$minaqual
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
44 --type='$featuretype'
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
45 --idattr='$idattr'
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
46 #if $samout_conditional.samout == "Yes":
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
47 --samout='$__new_file_path__/${samoutfile.id}_tmp'
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
48 #end if
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
49 #if $force_sort == "True":
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
50 --order=name
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
51 --format=bam
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
52 name_sorted_alignment.bam
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
53 #else
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
54 --order=pos
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
55 --format=$samfile.extension
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
56 '$samfile'
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
57 #end if
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
58
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
59 "$gfffile" | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&2"; else print $0}'
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
60 > '$counts'
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
61 2> '$othercounts'
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
62
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
63 #if $samout_conditional.samout == "Yes":
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
64 && samtools view -Su
25
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
65 -t '${reference_fasta_filename}.fai'
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
66 '$__new_file_path__/${samoutfile.id}_tmp'
88cea300225a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit da411ad3afa5b8fb7d28fdb1b13a777854e87212
iuc
parents: 24
diff changeset
67 | samtools sort -o '$samoutfile' -
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
68 #end if
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
69 ]]>
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
70 </command>
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
71
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
72 <inputs>
13
256d3114ce31 Fix input format string and change dependency owners to devteam
lparsons
parents: 12
diff changeset
73 <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
74 <param format="gff" name="gfffile" type="data" label="GFF File"/>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
75 <param name="mode" type="select" label="Mode" argument="(--mode)">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
76 <help>Mode to handle reads overlapping more than one feature.</help>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
77 <option value="union" selected="True">Union</option>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
78 <option value="intersection-strict">Intersection (strict)</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
79 <option value="intersection-nonempty">Intersection (nonempty)</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
80 </param>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
81 <param name="stranded" type="select" label="Stranded" argument="(--stranded)">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
82 <help>Specify whether the data is from a strand-specific assay. 'Reverse' means yes with reversed strand interpretation.</help>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
83 <option value="yes" selected="True">Yes</option>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
84 <option value="no">No</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
85 <option value="reverse">Reverse</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
86 </param>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
87 <param name="minaqual" type="integer" value="10" label="Minimum alignment quality" argument="--minaqual">
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
88 <help>Skip all reads with alignment quality lower than the given minimum value.</help>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
89 </param>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
90 <param name="featuretype" type="text" value="exon" label="Feature type" argument="--type">
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
91 <help>Feature type (3rd column in GFF file) to be used. All features of other types are ignored. The default, suitable for RNA-Seq and Ensembl GTF files, is exon.</help>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
92 </param>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
93 <param name="idattr" type="text" value="gene_id" label="ID Attribute" argument="--idattr">
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
94 <help>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. All features of the specified type MUST have a value for this attribute. The default, suitable for RNA-Seq and Ensembl GTF files, is gene_id.</help>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
95 </param>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
96 <conditional name="samout_conditional">
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
97 <param name="samout" type="select" label="Additional BAM Output">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
98 <help>Write out all SAM alignment records into an output BAM file, annotating each line with its assignment to a feature or a special counter (as an optional field with tag ‘XF’).</help>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
99 <option value="No" selected="True">Do not output additional BAM file</option>
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
100 <option value="Yes">Output additional BAM file</option>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
101 </param>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
102 <when value="Yes">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
103 <conditional name="reference_source">
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
104 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
105 <option value="cached">Locally cached</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
106 <option value="history">History</option>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
107 </param>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
108 <when value="cached">
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
109 <param name="ref_file" type="select" label="Using reference genome">
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
110 <options from_data_table="sam_fa_indexes">
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
111 <filter type="data_meta" key="dbkey" ref="samfile" column="1"/>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
112 </options>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
113 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
114 </param>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
115 </when>
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
116 <when value="history">
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
117 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
118 </when>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
119 </conditional>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
120 </when>
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
121 <when value="No">
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
122 <!-- Do nothing -->
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
123 </when>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
124 </conditional>
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
125 <param name="force_sort" type="boolean" value="False" truevalue="True" falsevalue="False" label="Force sorting of SAM/BAM file by NAME">
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
126 <help>This option can be used for for paired-end data that has many unmapped mates. Use this if you get the warning about paired end data missing or not being properly sorted.</help>
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
127 </param>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
128 </inputs>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
129
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
130 <outputs>
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
131 <data format="tabular" name="counts" metadata_source="samfile" label="${tool.name} on ${on_string}">
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
132 <actions>
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
133 <action name="column_names" type="metadata" default="Geneid,${samfile.name}" />
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
134 </actions>
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
135 </data>
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
136 <data format="tabular" name="othercounts" metadata_source="samfile" label="${tool.name} on ${on_string} (no feature)"/>
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
137 <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)">
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
138 <filter>samout_conditional['samout'] == "Yes"</filter>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
139 </data>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
140 </outputs>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
141
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
142 <tests>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
143 <test>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
144 <param name="samfile" value="htseq-test.sam" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
145 <param name="gfffile" value="htseq-test.gff" />
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
146 <param name="samout" value="No" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
147 <output name="counts" file="htseq-test_counts.tsv" />
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
148 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
149 </test>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
150 <test>
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
151 <param name="samfile" value="htseq-test.sam" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
152 <param name="gfffile" value="htseq-test.gff" />
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
153 <param name="samout" value="No" />
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
154 <param name="force_sort" value="True" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
155 <output name="counts" file="htseq-test_counts.tsv" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
156 <output name="othercounts" file="htseq-test_othercounts.tsv" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
157 </test>
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
158 <test>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
159 <param name="samfile" value="htseq-test.bam" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
160 <param name="gfffile" value="htseq-test.gff" />
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
161 <param name="samout" value="No" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
162 <output name="counts" file="htseq-test_counts.tsv" />
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
163 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
164 </test>
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
165 <test>
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
166 <param name="samfile" value="htseq-test-paired.bam" />
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
167 <param name="singlepaired" value="paired" />
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
168 <param name="gfffile" value="htseq-test.gff" />
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
169 <param name="samout" value="No" />
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
170 <output name="counts" file="htseq-test-paired_counts.tsv" />
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
171 <output name="othercounts" file="htseq-test-paired_othercounts.tsv" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
172 </test>
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
173 <test>
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
174 <param name="samfile" value="htseq-test-paired.bam" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
175 <param name="singlepaired" value="paired" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
176 <param name="gfffile" value="htseq-test.gff" />
23
b638ba24d9fb planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents: 22
diff changeset
177 <param name="samout" value="No" />
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
178 <param name="force_sort" value="True" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
179 <output name="counts" file="htseq-test-paired_counts.tsv" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
180 <output name="othercounts" file="htseq-test-paired_othercounts.tsv" />
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
181 </test>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
182 <test>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
183 <param name="samfile" value="htseq-test.sam" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
184 <param name="gfffile" value="htseq-test.gff" />
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
185 <param name="samout" value="Yes" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
186 <param name="reference_source_selector" value="history" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
187 <param name="ref_file" value="htseq-test_reference.fasta" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
188 <output name="counts" file="htseq-test_counts.tsv" />
5
0a835934d792 Version 0.3
lparsons
parents: 4
diff changeset
189 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
190 <output name="samoutfile" file="htseq-test_samout.bam" />
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
191 </test>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
192 </tests>
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
193
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
194 <help>
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
195 <![CDATA[
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
196 Overview
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
197 --------
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
198
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
199 This tool takes an alignment file in SAM or BAM format and feature file in GFF format
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
200 and calculates the number of reads mapping to each feature. It uses the *htseq-count*
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
201 script that is part of the HTSeq python module. See
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
202 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
203
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
204 A feature is an interval (i.e., a range of positions) on a chromosome or a union of
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
205 such intervals. In the case of RNA-Seq, the features are typically genes, where
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
206 each gene is considered here as the union of all its exons. One may also consider
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
207 each exon as a feature, e.g., in order to check for alternative splicing. For
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
208 comparative ChIP-Seq, the features might be binding regions from a pre-determined
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
209 list.
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
210
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
211
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
212 Overlap Modes
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
213 -------------
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
214
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
215 Special care must be taken to decide how to deal with reads that overlap more than one feature.
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
216
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
217 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*.
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
218
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
219 The following figure illustrates the effect of these three modes:
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
220
14
c1db55359a86 Fix image path and size
lparsons
parents: 13
diff changeset
221 .. image:: count_modes.png
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
222
6
08a11d1eaec6 Updated HTSEQ package to version 0.5.4p1, attempted to fix galaxy install where lib64 directory does not exist
lparsons
parents: 5
diff changeset
223
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
224 Strandedness
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
225 ------------
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
226
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
227 **Important**: The default for strandedness is yes. If your RNA-Seq data has not been made with a strand-specific protocol, this causes half of the reads to be lost. Hence, make sure to set the option Stranded to 'No' unless you have strand-specific data!
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
228
6
08a11d1eaec6 Updated HTSEQ package to version 0.5.4p1, attempted to fix galaxy install where lib64 directory does not exist
lparsons
parents: 5
diff changeset
229
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
230 Output
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
231 ------
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
232
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
233 The script outputs a table with counts for each feature, followed by the special counters, which count reads that were not counted for any feature for various reasons, namely
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
234
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
235 - *no_feature*: reads which could not be assigned to any feature (set S as described above was empty).
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
236
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
237 - *ambiguous*: reads which could have been assigned to more than one feature and hence were not counted for any of these (set S had mroe than one element).
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
238
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
239 - *too_low_aQual*: reads which were not counted due to the -a option, see below
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
240
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
241 - *not_aligned*: reads in the SAM file without alignment
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
242
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
243 - *alignment_not_unique*: reads with more than one reported alignment. These reads are recognized from the NH optional SAM field tag. (If the aligner does not set this field, multiply aligned reads will be counted multiple times.)
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
244
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
245
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
246 Options Summary
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
247 ---------------
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
248
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
249 Usage: htseq-count [options] sam_file gff_file
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
250
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
251 This script takes an alignment file in SAM format and a feature file in GFF
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
252 format and calculates for each feature the number of reads mapping to it. See
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
253 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
254
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
255 Options:
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
256 -h, --help show this help message and exit
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
257 -m MODE, --mode=MODE mode to handle reads overlapping more than one
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
258 feature(choices: union, intersection-strict,
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
259 intersection-nonempty; default: union)
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
260 -s STRANDED, --stranded=STRANDED
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
261 whether the data is from a strand-specific assay.
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
262 Specify 'yes', 'no', or 'reverse' (default: yes).
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
263 'reverse' means 'yes' with reversed strand
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
264 interpretation
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
265 -a MINAQUAL, --minaqual=MINAQUAL
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
266 skip all reads with alignment quality lower than the
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
267 given minimum value (default: 0)
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
268 -t FEATURETYPE, --type=FEATURETYPE
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
269 feature type (3rd column in GFF file) to be used, all
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
270 features of other type are ignored (default, suitable
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
271 for Ensembl GTF files: exon)
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
272 -i IDATTR, --idattr=IDATTR
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
273 GFF attribute to be used as feature ID (default,
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
274 suitable for Ensembl GTF files: gene_id)
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
275 -o SAMOUT, --samout=SAMOUT
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
276 write out all SAM alignment records into an output SAM
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
277 file called SAMOUT, annotating each line with its
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
278 feature assignment (as an optional field with tag
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
279 'XF')
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
280 -q, --quiet suppress progress report and warnings
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
281
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
282 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
283 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
284 Public License v3. Part of the 'HTSeq' framework.
19
8bc865a85024 planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit e53f827acbedaec2da3a44488fb6628c9e922055
lparsons
parents: 18
diff changeset
285 ]]>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
286 </help>
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
287 <citations>
24
0c01ed8d0e60 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 66df855014c39f31f97345e1249ddca5eb9f6e59
iuc
parents: 23
diff changeset
288 <citation type="doi">10.1093/bioinformatics/btu638</citation>
18
737cda668bdd planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents: 17
diff changeset
289 </citations>
0
b8349d8458fa Initial commit
Lance Parsons <lparsons@princeton.edu>
parents:
diff changeset
290 </tool>