annotate htseq-count.xml @ 9:971e20519fb8

Fix for dbkey column check when output additional bam is selected
author lparsons
date Fri, 26 Oct 2012 15:57:08 -0400
parents 5bfb7a651fac
children 5d969cb56112
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
5bfb7a651fac Uploaded to attempt to reset metadata
lparsons
parents: 5
diff changeset
1 <tool id="htseq_count" name="htseq-count" version="0.2.1">
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>
4
14bec14f4290 Added tool_dependencies.xml back, dependency installation requires Galaxy changeset 7621:108cda898646
Lance Parsons <lparsons@princeton.edu>
parents: 3
diff changeset
5 <requirement type="package" version="1.6.2">numpy</requirement>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
6 <requirement type="package" version="0.5.3p9">htseq</requirement>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
7 <requirement type="package" version="0.1.18">samtools</requirement>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
8 </requirements>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
9 <command>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
10 ##set up input files
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
11 #set $reference_fasta_filename = "localref.fa"
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
12 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
13 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
14 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" &amp;&amp;
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
15 samtools faidx "${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
16 #else:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
17 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
18 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
19 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
20
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
21 #if $samfile.extension == "bam":
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
22 samtools view $samfile |
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
23 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
24 htseq-count
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
25 --mode=$mode
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
26 --stranded=$stranded
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
27 --minaqual=$minaqual
8
5bfb7a651fac Uploaded to attempt to reset metadata
lparsons
parents: 5
diff changeset
28 --type=$featuretype
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
29 --idattr=$idattr
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
30 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
31 --samout=$__new_file_path__/${samoutfile.id}_tmp
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
32 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
33 #if $samfile.extension == "bam":
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
34 -
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
35 #else
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
36 $samfile
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
37 #end if
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
38 $gfffile
3
f7a5b54a8d4f Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents: 0
diff changeset
39 | 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
40 #if $samout_conditional.samout:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
41 &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
42 #end if</command>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
43 <inputs>
5
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
44 <param format="sam, bam" name="samfile" type="data" label="Aligned SAM/BAM File">
8
5bfb7a651fac Uploaded to attempt to reset metadata
lparsons
parents: 5
diff changeset
45 <help>Paired-End data MUST be sorted by QUERY NAME, use "NGS: Picard - Paired Read Mate Fixer" to sort by QUERY NAME and output to SAM (not BAM) before using this tool on paired data.</help>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
46 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
47 <param format="gff" name="gfffile" type="data" label="GFF File"/>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
48 <param name="mode" type="select" label="Mode">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
49 <help>Mode to handle reads overlapping more than one feature.</help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
50 <option value="union" selected="true">Union</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
51 <option value="intersection-strict">Intersection (strict)</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
52 <option value="intersection-nonempty">Intersection (nonempty)</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
53 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
54 <param name="stranded" type="select" label="Stranded">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
55 <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
56 <option value="yes" selected="true">Yes</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
57 <option value="no">No</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
58 <option value="reverse">Reverse</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
59 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
60 <param name="minaqual" type="integer" value="0" label="Minimum alignment quality">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
61 <help>Skip all reads with alignment quality lower than the given minimum value</help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
62 </param>
8
5bfb7a651fac Uploaded to attempt to reset metadata
lparsons
parents: 5
diff changeset
63 <param name="featuretype" type="text" value="exon" label="Feature type">
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
64 <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
65 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
66 <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
67 <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
68 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
69 <conditional name="samout_conditional">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
70 <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
71 <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
72 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
73 <when value="True">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
74 <conditional name="reference_source">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
75 <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
76 <option value="cached">Locally cached</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
77 <option value="history">History</option>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
78 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
79 <when value="cached">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
80 <param name="ref_file" type="select" label="Using reference genome">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
81 <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
82 <filter type="data_meta" key="dbkey" ref="samfile" column="1"/>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
83 </options>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
84 <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
85 </param>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
86 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
87 <when value="history"> <!-- FIX ME!!!! -->
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
88 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
89 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
90 </conditional>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
91 </when>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
92 </conditional>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
93 </inputs>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
94
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
95 <outputs>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
96 <data format="tabular" name="counts" label="${tool.name} on ${on_string}"/>
3
f7a5b54a8d4f Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents: 0
diff changeset
97 <data format="tabular" name="othercounts" label="${tool.name} on ${on_string} (no feature)"/>
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
98 <data format="bam" name="samoutfile" label="${tool.name} on ${on_string} (BAM)">
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
99 <filter>samout_conditional['samout']</filter>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
100 </data>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
101 </outputs>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
102
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
103 <stdio>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
104 <exit_code range="1:" level="fatal" description="Unknown error occurred" />
5
8a5d43b21c6e Improved error handling
Lance Parsons <lparsons@princeton.edu>
parents: 4
diff changeset
105 <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
106 <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
107 <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
108 <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />
8
5bfb7a651fac Uploaded to attempt to reset metadata
lparsons
parents: 5
diff changeset
109 <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
110 </stdio>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
111
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
112 <tests>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
113 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
114 <param name="samfile" value="htseq-test.sam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
115 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
116 <param name="samout" value="False" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
117 <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
118 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
119 </test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
120 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
121 <param name="samfile" value="htseq-test.bam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
122 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
123 <param name="samout" value="False" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
124 <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
125 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
126 </test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
127 <!-- Seems to be an issue setting the $reference_fasta_filename variable during test
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
128 <test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
129 <param name="samfile" value="htseq-test.sam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
130 <param name="gfffile" value="htseq-test.gff" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
131 <param name="samout" value="True" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
132 <param name="reference_source_selector" value="history" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
133 <param name="ref_file" value="htseq-test_reference.fasta" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
134 <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
135 <output name="othercounts" file="htseq-test_othercounts.tsv" />
0
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
136 <output name="samoutfile" file="htseq-test_samout.bam" />
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
137 </test>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
138 -->
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
139 </tests>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
140
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
141 <help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
142 Overview
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
143 --------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
144
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
145 This tool takes an alignment file in SAM or BAM format and feature file in GFF format
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
146 and calculates the number of reads mapping to each feature. It uses the *htseq-count*
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
147 script that is part of the HTSeq python module. See
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
148 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
149
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
150 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
151 such intervals. In the case of RNA-Seq, the features are typically genes, where
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
152 each gene is considered here as the union of all its exons. One may also consider
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
153 each exon as a feature, e.g., in order to check for alternative splicing. For
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
154 comparative ChIP-Seq, the features might be binding regions from a pre-determined
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
155 list.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
156
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
157 **Paired-end Data MUST be sorted by QUERY NAME first**
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
158
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
159 This tool requires that paired-end data be sorted by query name, which is NOT the default for Galaxy. Using the Picard Paired Read Mate Fixer with Query name sort FIRST is required for paired end data.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
160
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
161
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
162 Overlap Modes
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
163 -------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
164
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
165 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
166
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
167 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
168
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
169 The following figure illustrates the effect of these three modes:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
170
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
171 .. image:: /static/images/count_modes.png
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
172 :width: 500
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
173
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
174 Strandedness
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
175 ------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
176
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
177 **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
178
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
179 Output
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
180 ------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
181
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
182 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
183
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
184 - *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
185
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
186 - *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
187
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
188 - *too_low_aQual*: reads which were not counted due to the -a option, see below
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
189
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
190 - *not_aligned*: reads in the SAM file without alignment
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
191
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
192 - *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
193
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
194
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
195 Options Summary
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
196 ---------------
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
197
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
198 Usage: htseq-count [options] sam_file gff_file
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
199
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
200 This script takes an alignment file in SAM format and a feature file in GFF
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
201 format and calculates for each feature the number of reads mapping to it. See
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
202 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
203
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
204 Options:
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
205 -h, --help show this help message and exit
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
206 -m MODE, --mode=MODE mode to handle reads overlapping more than one
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
207 feature(choices: union, intersection-strict,
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
208 intersection-nonempty; default: union)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
209 -s STRANDED, --stranded=STRANDED
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
210 whether the data is from a strand-specific assay.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
211 Specify 'yes', 'no', or 'reverse' (default: yes).
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
212 'reverse' means 'yes' with reversed strand
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
213 interpretation
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
214 -a MINAQUAL, --minaqual=MINAQUAL
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
215 skip all reads with alignment quality lower than the
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
216 given minimum value (default: 0)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
217 -t FEATURETYPE, --type=FEATURETYPE
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
218 feature type (3rd column in GFF file) to be used, all
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
219 features of other type are ignored (default, suitable
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
220 for Ensembl GTF files: exon)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
221 -i IDATTR, --idattr=IDATTR
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
222 GFF attribute to be used as feature ID (default,
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
223 suitable for Ensembl GTF files: gene_id)
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
224 -o SAMOUT, --samout=SAMOUT
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
225 write out all SAM alignment records into an output SAM
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
226 file called SAMOUT, annotating each line with its
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
227 feature assignment (as an optional field with tag
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
228 'XF')
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
229 -q, --quiet suppress progress report and warnings
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
230
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
231 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
232 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
233 Public License v3. Part of the 'HTSeq' framework.
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
234 </help>
3fdeebd7e710 Initial commit
lparsons
parents:
diff changeset
235 </tool>