Mercurial > repos > lparsons > htseq_count
annotate htseq-count.xml @ 23:6e5c95760ab1 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
author | iuc |
---|---|
date | Wed, 21 Sep 2016 10:59:41 -0400 |
parents | 55ed198f2c1c |
children | 620d5603d1a8 |
rev | line source |
---|---|
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
1 <tool id="htseq_count" name="htseq-count" version="0.6.1galaxy2"> |
0 | 2 <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description> |
3 <requirements> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
4 <requirement type="package" version="0.6.1.post1">htseq</requirement> |
13 | 5 <requirement type="package" version="0.1.19">samtools</requirement> |
0 | 6 </requirements> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
7 |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
8 <stdio> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
9 <exit_code range="1:" level="fatal" description="Unknown error occurred" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
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" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
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" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
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'" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
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" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
14 <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
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." /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
16 </stdio> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
17 |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
18 <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
19 |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
20 <command><![CDATA[ |
0 | 21 ##set up input files |
22 #set $reference_fasta_filename = "localref.fa" | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
23 #if $samout_conditional.samout == "Yes": |
0 | 24 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history": |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
25 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" && |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
26 samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 && |
0 | 27 #else: |
28 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path ) | |
29 #end if | |
30 #end if | |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
31 |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
32 #if $force_sort == "True": |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
33 #if $samfile.extension == 'bam': |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
34 samtools sort -n "$samfile" "name_sorted_alignment" && |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
35 #else |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
36 samtools view -Su -t "${reference_fasta_filename}.fai" "$samfile" | samtools sort -n - "name_sorted_alignment" && |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
37 #end if |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
38 #end if |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
39 |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
40 htseq-count |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
41 --mode=$mode |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
42 --stranded=$stranded |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
43 --minaqual=$minaqual |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
44 --type="$featuretype" |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
45 --idattr="$idattr" |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
46 #if $samout_conditional.samout == "Yes": |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
47 --samout='$__new_file_path__/${samoutfile.id}_tmp' |
0 | 48 #end if |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
49 #if $force_sort == "True": |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
50 --order=name |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
51 --format=bam |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
52 name_sorted_alignment.bam |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
53 #else |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
54 --order=pos |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
55 --format=$samfile.extension |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
56 '$samfile' |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
57 #end if |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
58 |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
59 "$gfffile" | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&2"; else print $0}' |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
60 > '$counts' |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
61 2> '$othercounts' |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
62 |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
63 #if $samout_conditional.samout == "Yes": |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
64 && samtools view -Su |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
65 -t "${reference_fasta_filename}.fai" |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
66 "$__new_file_path__/${samoutfile.id}_tmp" |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
67 | samtools sort -o - name_sorted_alignment > "$samoutfile" |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
68 #end if |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
69 ]]> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
70 </command> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
71 |
0 | 72 <inputs> |
16
227f9d3f0e32
Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents:
15
diff
changeset
|
73 <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/> |
0 | 74 <param format="gff" name="gfffile" type="data" label="GFF File"/> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
75 <param name="mode" type="select" label="Mode" argument="(--mode)"> |
0 | 76 <help>Mode to handle reads overlapping more than one feature.</help> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
77 <option value="union" selected="True">Union</option> |
0 | 78 <option value="intersection-strict">Intersection (strict)</option> |
79 <option value="intersection-nonempty">Intersection (nonempty)</option> | |
80 </param> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
81 <param name="stranded" type="select" label="Stranded" argument="(--stranded)"> |
0 | 82 <help>Specify whether the data is from a strand-specific assay. 'Reverse' means yes with reversed strand interpretation.</help> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
83 <option value="yes" selected="True">Yes</option> |
0 | 84 <option value="no">No</option> |
85 <option value="reverse">Reverse</option> | |
86 </param> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
87 <param name="minaqual" type="integer" value="10" label="Minimum alignment quality" argument="--minaqual"> |
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
88 <help>Skip all reads with alignment quality lower than the given minimum value.</help> |
0 | 89 </param> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
90 <param name="featuretype" type="text" value="exon" label="Feature type" argument="--type"> |
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
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 | 92 </param> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
93 <param name="idattr" type="text" value="gene_id" label="ID Attribute" argument="--idattr"> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
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 | 95 </param> |
96 <conditional name="samout_conditional"> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
97 <param name="samout" type="select" label="Additional BAM Output"> |
0 | 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> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
99 <option value="No" selected="True">Do not output additional BAM file</option> |
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
100 <option value="Yes">Output additional BAM file</option> |
0 | 101 </param> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
102 <when value="Yes"> |
0 | 103 <conditional name="reference_source"> |
104 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> | |
105 <option value="cached">Locally cached</option> | |
106 <option value="history">History</option> | |
107 </param> | |
108 <when value="cached"> | |
109 <param name="ref_file" type="select" label="Using reference genome"> | |
110 <options from_data_table="sam_fa_indexes"> | |
9
971e20519fb8
Fix for dbkey column check when output additional bam is selected
lparsons
parents:
8
diff
changeset
|
111 <filter type="data_meta" key="dbkey" ref="samfile" column="1"/> |
0 | 112 </options> |
113 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
114 </param> | |
115 </when> | |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
116 <when value="history"> |
0 | 117 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> |
118 </when> | |
119 </conditional> | |
120 </when> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
121 <when value="No"> |
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
122 <!-- Do nothing --> |
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
123 </when> |
0 | 124 </conditional> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
125 <param name="force_sort" type="boolean" value="False" truevalue="True" falsevalue="False" label="Force sorting of SAM/BAM file by NAME"> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
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> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
127 </param> |
0 | 128 </inputs> |
129 | |
130 <outputs> | |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
131 <data format="tabular" name="counts" metadata_source="samfile" label="${tool.name} on ${on_string}"> |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
132 <actions> |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
133 <action name="column_names" type="metadata" default="Geneid,${samfile.name}" /> |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
134 </actions> |
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
135 </data> |
10
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
136 <data format="tabular" name="othercounts" metadata_source="samfile" label="${tool.name} on ${on_string} (no feature)"/> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
137 <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)"> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
138 <filter>samout_conditional['samout'] == "Yes"</filter> |
0 | 139 </data> |
140 </outputs> | |
141 | |
142 <tests> | |
143 <test> | |
144 <param name="samfile" value="htseq-test.sam" /> | |
145 <param name="gfffile" value="htseq-test.gff" /> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
146 <param name="samout" value="No" /> |
0 | 147 <output name="counts" file="htseq-test_counts.tsv" /> |
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
148 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
0 | 149 </test> |
150 <test> | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
151 <param name="samfile" value="htseq-test.sam" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
152 <param name="gfffile" value="htseq-test.gff" /> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
153 <param name="samout" value="No" /> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
154 <param name="force_sort" value="True" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
155 <output name="counts" file="htseq-test_counts.tsv" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
156 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
157 </test> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
158 <test> |
0 | 159 <param name="samfile" value="htseq-test.bam" /> |
160 <param name="gfffile" value="htseq-test.gff" /> | |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
161 <param name="samout" value="No" /> |
0 | 162 <output name="counts" file="htseq-test_counts.tsv" /> |
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
163 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
0 | 164 </test> |
10
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
165 <test> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
166 <param name="samfile" value="htseq-test-paired.bam" /> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
167 <param name="singlepaired" value="paired" /> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
168 <param name="gfffile" value="htseq-test.gff" /> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
169 <param name="samout" value="No" /> |
10
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
170 <output name="counts" file="htseq-test-paired_counts.tsv" /> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
171 <output name="othercounts" file="htseq-test-paired_othercounts.tsv" /> |
5d969cb56112
Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents:
9
diff
changeset
|
172 </test> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
173 <test> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
174 <param name="samfile" value="htseq-test-paired.bam" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
175 <param name="singlepaired" value="paired" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
176 <param name="gfffile" value="htseq-test.gff" /> |
22
55ed198f2c1c
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit 03f64004f90ac0a7be67ecfc355a7b361f3c3314
iuc
parents:
21
diff
changeset
|
177 <param name="samout" value="No" /> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
178 <param name="force_sort" value="True" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
179 <output name="counts" file="htseq-test-paired_counts.tsv" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
180 <output name="othercounts" file="htseq-test-paired_othercounts.tsv" /> |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
181 </test> |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
182 |
0 | 183 <test> |
184 <param name="samfile" value="htseq-test.sam" /> | |
185 <param name="gfffile" value="htseq-test.gff" /> | |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
186 <param name="samout" value="Yes" /> |
0 | 187 <param name="reference_source_selector" value="history" /> |
188 <param name="ref_file" value="htseq-test_reference.fasta" /> | |
189 <output name="counts" file="htseq-test_counts.tsv" /> | |
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
190 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
0 | 191 <output name="samoutfile" file="htseq-test_samout.bam" /> |
192 </test> | |
193 </tests> | |
194 | |
195 <help> | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
196 <![CDATA[ |
0 | 197 Overview |
198 -------- | |
199 | |
200 This tool takes an alignment file in SAM or BAM format and feature file in GFF format | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
201 and calculates the number of reads mapping to each feature. It uses the *htseq-count* |
0 | 202 script that is part of the HTSeq python module. See |
203 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
204 | |
205 A feature is an interval (i.e., a range of positions) on a chromosome or a union of | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
206 such intervals. In the case of RNA-Seq, the features are typically genes, where |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
207 each gene is considered here as the union of all its exons. One may also consider |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
208 each exon as a feature, e.g., in order to check for alternative splicing. For |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
209 comparative ChIP-Seq, the features might be binding regions from a pre-determined |
0 | 210 list. |
211 | |
212 | |
213 Overlap Modes | |
214 ------------- | |
215 | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
216 Special care must be taken to decide how to deal with reads that overlap more than one feature. |
0 | 217 |
218 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*. | |
219 | |
220 The following figure illustrates the effect of these three modes: | |
221 | |
16
227f9d3f0e32
Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents:
15
diff
changeset
|
222 .. image:: count_modes.png |
0 | 223 |
11 | 224 |
0 | 225 Strandedness |
226 ------------ | |
227 | |
228 **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! | |
229 | |
11 | 230 |
0 | 231 Output |
232 ------ | |
233 | |
234 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 | |
235 | |
236 - *no_feature*: reads which could not be assigned to any feature (set S as described above was empty). | |
237 | |
238 - *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). | |
239 | |
240 - *too_low_aQual*: reads which were not counted due to the -a option, see below | |
241 | |
242 - *not_aligned*: reads in the SAM file without alignment | |
243 | |
244 - *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.) | |
245 | |
246 | |
247 Options Summary | |
248 --------------- | |
249 | |
250 Usage: htseq-count [options] sam_file gff_file | |
251 | |
252 This script takes an alignment file in SAM format and a feature file in GFF | |
253 format and calculates for each feature the number of reads mapping to it. See | |
254 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
255 | |
256 Options: | |
257 -h, --help show this help message and exit | |
258 -m MODE, --mode=MODE mode to handle reads overlapping more than one | |
259 feature(choices: union, intersection-strict, | |
260 intersection-nonempty; default: union) | |
261 -s STRANDED, --stranded=STRANDED | |
262 whether the data is from a strand-specific assay. | |
263 Specify 'yes', 'no', or 'reverse' (default: yes). | |
264 'reverse' means 'yes' with reversed strand | |
265 interpretation | |
266 -a MINAQUAL, --minaqual=MINAQUAL | |
267 skip all reads with alignment quality lower than the | |
268 given minimum value (default: 0) | |
269 -t FEATURETYPE, --type=FEATURETYPE | |
270 feature type (3rd column in GFF file) to be used, all | |
271 features of other type are ignored (default, suitable | |
272 for Ensembl GTF files: exon) | |
273 -i IDATTR, --idattr=IDATTR | |
274 GFF attribute to be used as feature ID (default, | |
275 suitable for Ensembl GTF files: gene_id) | |
276 -o SAMOUT, --samout=SAMOUT | |
277 write out all SAM alignment records into an output SAM | |
278 file called SAMOUT, annotating each line with its | |
279 feature assignment (as an optional field with tag | |
280 'XF') | |
281 -q, --quiet suppress progress report and warnings | |
282 | |
283 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology | |
284 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General | |
285 Public License v3. Part of the 'HTSeq' framework. | |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
286 ]]> |
0 | 287 </help> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
288 |
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
289 <citations> |
23
6e5c95760ab1
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/htseq_count commit ee302cfd1ae3f7fcb3def4359e372341a7272790
iuc
parents:
22
diff
changeset
|
290 <citation type="doi">10.1093/bioinformatics/btu638</citation> |
20
3b3601a2a7c7
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 8a40cf16ce0b48cdfda88a505869e77e8826cb23
lparsons
parents:
17
diff
changeset
|
291 </citations> |
0 | 292 </tool> |