annotate htseq-count.xml @ 18:087e32034c95 draft

Uploaded
author lparsons
date Fri, 26 Sep 2014 10:48:21 -0400
parents d5edaf8dc974
children 3b3601a2a7c7
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
17
d5edaf8dc974 Fixed test output, added missing pysam dependency
lparsons
parents: 16
diff changeset
1 <tool id="htseq_count" name="htseq-count" version="0.4.1">
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
2 <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
3 <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
4 <requirements>
13
30bb8acb77a4 Updated to v0.5.4p5, use repository dependencies.
lparsons
parents: 12
diff changeset
5 <requirement type="package" version="1.7.1">numpy</requirement>
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
6 <requirement type="package" version="0.6.1">htseq</requirement>
13
30bb8acb77a4 Updated to v0.5.4p5, use repository dependencies.
lparsons
parents: 12
diff changeset
7 <requirement type="package" version="0.1.19">samtools</requirement>
17
d5edaf8dc974 Fixed test output, added missing pysam dependency
lparsons
parents: 16
diff changeset
8 <requirement type="package" version="0.7.7">pysam</requirement>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
9 </requirements>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
10 <command>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
11 ##set up input files
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
12 #set $reference_fasta_filename = "localref.fa"
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
13 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
14 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
15 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" &amp;&amp;
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
16 samtools faidx "${reference_fasta_filename}" 2&gt;&amp;1 || echo "Error running samtools faidx for htseq-count" &gt;&amp;2 &amp;&amp;
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
17 #else:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
18 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
19 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
20 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
21 htseq-count
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
22 --format=$samfile.extension
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
23 --order=pos
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
24 --mode=$mode
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
25 --stranded=$stranded
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
26 --minaqual=$minaqual
6
2861eb44fbbf Fix issue with workflows (type->featuretype) and general error check
Lance Parsons <lparsons@princeton.edu>
parents: 5
diff changeset
27 --type=$featuretype
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
28 --idattr=$idattr
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
29 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
30 --samout=$__new_file_path__/${samoutfile.id}_tmp
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
31 #end if
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
32 $samfile
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
33 $gfffile
3
f7a5b54a8d4f Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents: 0
diff changeset
34 | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&amp;2"; else print $0}' &gt; $counts 2&gt;$othercounts
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
35 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
36 &amp;&amp; samtools view -Su -t ${reference_fasta_filename}.fai $__new_file_path__/${samoutfile.id}_tmp | samtools sort -o - sorted > $samoutfile
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
37 #end if</command>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
38 <inputs>
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
39 <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
40 <param format="gff" name="gfffile" type="data" label="GFF File"/>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
41 <param name="mode" type="select" label="Mode">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
42 <help>Mode to handle reads overlapping more than one feature.</help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
43 <option value="union" selected="true">Union</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
44 <option value="intersection-strict">Intersection (strict)</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
45 <option value="intersection-nonempty">Intersection (nonempty)</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
46 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
47 <param name="stranded" type="select" label="Stranded">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
48 <help>Specify whether the data is from a strand-specific assay. 'Reverse' means yes with reversed strand interpretation.</help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
49 <option value="yes" selected="true">Yes</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
50 <option value="no">No</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
51 <option value="reverse">Reverse</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
52 </param>
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
53 <param name="minaqual" type="integer" value="10" label="Minimum alignment quality">
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
54 <help>Skip all reads with alignment quality lower than the given minimum value</help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
55 </param>
6
2861eb44fbbf Fix issue with workflows (type->featuretype) and general error check
Lance Parsons <lparsons@princeton.edu>
parents: 5
diff changeset
56 <param name="featuretype" type="text" value="exon" label="Feature type">
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
57 <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>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
58 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
59 <param name="idattr" type="text" value="gene_id" label="ID Attribute">
5
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
60 <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
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
61 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
62 <conditional name="samout_conditional">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
63 <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
64 <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>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
65 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
66 <when value="True">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
67 <conditional name="reference_source">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
68 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
69 <option value="cached">Locally cached</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
70 <option value="history">History</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
71 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
72 <when value="cached">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
73 <param name="ref_file" type="select" label="Using reference genome">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
74 <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
75 <filter type="data_meta" key="dbkey" ref="samfile" column="1"/>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
76 </options>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
77 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
78 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
79 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
80 <when value="history"> <!-- FIX ME!!!! -->
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
81 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
82 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
83 </conditional>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
84 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
85 </conditional>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
86 </inputs>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
87
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
88 <outputs>
10
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
89 <data format="tabular" name="counts" metadata_source="samfile" label="${tool.name} on ${on_string}"/>
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
90 <data format="tabular" name="othercounts" metadata_source="samfile" label="${tool.name} on ${on_string} (no feature)"/>
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
91 <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)">
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
92 <filter>samout_conditional['samout']</filter>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
93 </data>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
94 </outputs>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
95
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
96 <stdio>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
97 <exit_code range="1:" level="fatal" description="Unknown error occurred" />
5
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
98 <regex match="htseq-count: command not found" source="stderr" level="fatal" description="The HTSeq python package is not properly installed, contact Galaxy administrators" />
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
99 <regex match="samtools: command not found" source="stderr" level="fatal" description="The samtools package is not properly installed, contact Galaxy administrators" />
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
100 <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'" />
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
101 <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />
6
2861eb44fbbf Fix issue with workflows (type->featuretype) and general error check
Lance Parsons <lparsons@princeton.edu>
parents: 5
diff changeset
102 <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />
10
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
103 <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 paired-end option. See stderr output of this dataset for more information." />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
104 </stdio>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
105
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
106 <tests>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
107 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
108 <param name="samfile" value="htseq-test.sam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
109 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
110 <param name="samout" value="False" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
111 <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
112 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
113 </test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
114 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
115 <param name="samfile" value="htseq-test.bam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
116 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
117 <param name="samout" value="False" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
118 <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
119 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
120 </test>
10
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
121 <test>
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
122 <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
123 <param name="singlepaired" value="paired" />
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
124 <param name="gfffile" value="htseq-test.gff" />
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
125 <param name="samout" value="False" />
5d969cb56112 Version 0.3 - paried-end sorting is now built-in (uses Picard tools)
lparsons
parents: 9
diff changeset
126 <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
127 <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
128 </test>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
129 <!-- Seems to be an issue setting the $reference_fasta_filename variable during test
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
130 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
131 <param name="samfile" value="htseq-test.sam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
132 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
133 <param name="samout" value="True" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
134 <param name="reference_source_selector" value="history" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
135 <param name="ref_file" value="htseq-test_reference.fasta" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
136 <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
137 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
138 <output name="samoutfile" file="htseq-test_samout.bam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
139 </test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
140 -->
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
141 </tests>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
142
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
143 <help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
144 Overview
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
145 --------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
146
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
147 This tool takes an alignment file in SAM or BAM format and feature file in GFF format
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
148 and calculates the number of reads mapping to each feature. It uses the *htseq-count*
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
149 script that is part of the HTSeq python module. See
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
150 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
151
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
152 A feature is an interval (i.e., a range of positions) on a chromosome or a union of
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
153 such intervals. In the case of RNA-Seq, the features are typically genes, where
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
154 each gene is considered here as the union of all its exons. One may also consider
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
155 each exon as a feature, e.g., in order to check for alternative splicing. For
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
156 comparative ChIP-Seq, the features might be binding regions from a pre-determined
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
157 list.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
158
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
159
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
160 Overlap Modes
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
161 -------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
162
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
163 Special care must be taken to decide how to deal with reads that overlap more than one feature.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
164
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
165 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
166
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
167 The following figure illustrates the effect of these three modes:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
168
16
227f9d3f0e32 Updated HTSeq package to version 0.6.1, fixed input format string, updated dependency definitions
lparsons
parents: 15
diff changeset
169 .. image:: count_modes.png
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
170
11
f320093f1e8e Removed sorting notice from help
lparsons
parents: 10
diff changeset
171
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
172 Strandedness
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
173 ------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
174
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
175 **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!
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
176
11
f320093f1e8e Removed sorting notice from help
lparsons
parents: 10
diff changeset
177
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
178 Output
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
179 ------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
180
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
181 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
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
182
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
183 - *no_feature*: reads which could not be assigned to any feature (set S as described above was empty).
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
184
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
185 - *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).
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
186
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
187 - *too_low_aQual*: reads which were not counted due to the -a option, see below
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
188
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
189 - *not_aligned*: reads in the SAM file without alignment
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
190
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
191 - *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.)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
192
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
193
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
194 Options Summary
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
195 ---------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
196
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
197 Usage: htseq-count [options] sam_file gff_file
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
198
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
199 This script takes an alignment file in SAM format and a feature file in GFF
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
200 format and calculates for each feature the number of reads mapping to it. See
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
201 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
202
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
203 Options:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
204 -h, --help show this help message and exit
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
205 -m MODE, --mode=MODE mode to handle reads overlapping more than one
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
206 feature(choices: union, intersection-strict,
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
207 intersection-nonempty; default: union)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
208 -s STRANDED, --stranded=STRANDED
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
209 whether the data is from a strand-specific assay.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
210 Specify 'yes', 'no', or 'reverse' (default: yes).
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
211 'reverse' means 'yes' with reversed strand
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
212 interpretation
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
213 -a MINAQUAL, --minaqual=MINAQUAL
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
214 skip all reads with alignment quality lower than the
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
215 given minimum value (default: 0)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
216 -t FEATURETYPE, --type=FEATURETYPE
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
217 feature type (3rd column in GFF file) to be used, all
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
218 features of other type are ignored (default, suitable
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
219 for Ensembl GTF files: exon)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
220 -i IDATTR, --idattr=IDATTR
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
221 GFF attribute to be used as feature ID (default,
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
222 suitable for Ensembl GTF files: gene_id)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
223 -o SAMOUT, --samout=SAMOUT
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
224 write out all SAM alignment records into an output SAM
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
225 file called SAMOUT, annotating each line with its
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
226 feature assignment (as an optional field with tag
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
227 'XF')
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
228 -q, --quiet suppress progress report and warnings
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
229
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
230 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
231 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
232 Public License v3. Part of the 'HTSeq' framework.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
233 </help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
234 </tool>