Mercurial > repos > lparsons > htseq_count
annotate htseq-count.xml @ 3:f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
| author | Lance Parsons <lparsons@princeton.edu> |
|---|---|
| date | Mon, 10 Sep 2012 17:30:10 -0400 |
| parents | 3fdeebd7e710 |
| children | 14bec14f4290 |
| rev | line source |
|---|---|
|
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
1 <tool id="htseq_count" name="htseq-count" version="0.2"> |
| 0 | 2 <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description> |
| 3 <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command> | |
| 4 <requirements> | |
| 5 <requirement type="package" version="0.5.3p9">htseq</requirement> | |
| 6 <requirement type="package" version="0.1.18">samtools</requirement> | |
| 7 </requirements> | |
| 8 <command> | |
| 9 ##set up input files | |
| 10 #set $reference_fasta_filename = "localref.fa" | |
| 11 #if $samout_conditional.samout: | |
| 12 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history": | |
| 13 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" && | |
| 14 samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 && | |
| 15 #else: | |
| 16 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path ) | |
| 17 #end if | |
| 18 #end if | |
| 19 | |
| 20 #if $samfile.extension == "bam": | |
| 21 samtools view $samfile | | |
| 22 #end if | |
| 23 htseq-count | |
| 24 --mode=$mode | |
| 25 --stranded=$stranded | |
| 26 --minaqual=$minaqual | |
| 27 --type=$type | |
| 28 --idattr=$idattr | |
| 29 #if $samout_conditional.samout: | |
| 30 --samout=$__new_file_path__/${samoutfile.id}_tmp | |
| 31 #end if | |
| 32 #if $samfile.extension == "bam": | |
| 33 - | |
| 34 #else | |
| 35 $samfile | |
| 36 #end if | |
| 37 $gfffile | |
|
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
38 | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&2"; else print $0}' > $counts 2>$othercounts |
| 0 | 39 #if $samout_conditional.samout: |
| 40 && samtools view -Su -t ${reference_fasta_filename}.fai $__new_file_path__/${samoutfile.id}_tmp | samtools sort -o - sorted > $samoutfile | |
| 41 #end if</command> | |
| 42 <inputs> | |
| 43 <param format="sam, bam" name="samfile" type="data" label="Aligned SAM File"> | |
| 44 <help>Paired-End data must be sorted by QUERY NAME, use Picard Read Mate Fixer and Query name sort order before using this tool on paired data</help> | |
| 45 </param> | |
| 46 <param format="gff" name="gfffile" type="data" label="GFF File"/> | |
| 47 <param name="mode" type="select" label="Mode"> | |
| 48 <help>Mode to handle reads overlapping more than one feature.</help> | |
| 49 <option value="union" selected="true">Union</option> | |
| 50 <option value="intersection-strict">Intersection (strict)</option> | |
| 51 <option value="intersection-nonempty">Intersection (nonempty)</option> | |
| 52 </param> | |
| 53 <param name="stranded" type="select" label="Stranded"> | |
| 54 <help>Specify whether the data is from a strand-specific assay. 'Reverse' means yes with reversed strand interpretation.</help> | |
| 55 <option value="yes" selected="true">Yes</option> | |
| 56 <option value="no">No</option> | |
| 57 <option value="reverse">Reverse</option> | |
| 58 </param> | |
| 59 <param name="minaqual" type="integer" value="0" label="Minimum alignment quality"> | |
| 60 <help>Skip all reads with alignment quality lower than the given minimum value</help> | |
| 61 </param> | |
| 62 <param name="type" type="text" value="exon" label="Feature type"> | |
| 63 <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> | |
| 64 </param> | |
| 65 <param name="idattr" type="text" value="gene_id" label="ID Attribute"> | |
| 66 <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. The default, suitable for RNA-SEq and Ensembl GTF files, is gene_id.</help> | |
| 67 </param> | |
| 68 <conditional name="samout_conditional"> | |
| 69 <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output"> | |
| 70 <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> | |
| 71 </param> | |
| 72 <when value="True"> | |
| 73 <conditional name="reference_source"> | |
| 74 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> | |
| 75 <option value="cached">Locally cached</option> | |
| 76 <option value="history">History</option> | |
| 77 </param> | |
| 78 <when value="cached"> | |
| 79 <param name="ref_file" type="select" label="Using reference genome"> | |
| 80 <options from_data_table="sam_fa_indexes"> | |
| 81 <filter type="data_meta" key="dbkey" ref="samfile" column="3"/> | |
| 82 </options> | |
| 83 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
| 84 </param> | |
| 85 </when> | |
| 86 <when value="history"> <!-- FIX ME!!!! --> | |
| 87 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> | |
| 88 </when> | |
| 89 </conditional> | |
| 90 </when> | |
| 91 </conditional> | |
| 92 </inputs> | |
| 93 | |
| 94 <outputs> | |
| 95 <data format="tabular" name="counts" label="${tool.name} on ${on_string}"/> | |
|
3
f7a5b54a8d4f
Split feature and non-feature counts, removed tool_dependencies.xml (for now)
Lance Parsons <lparsons@princeton.edu>
parents:
0
diff
changeset
|
96 <data format="tabular" name="othercounts" label="${tool.name} on ${on_string} (no feature)"/> |
| 0 | 97 <data format="bam" name="samoutfile" label="${tool.name} on ${on_string} (BAM)"> |
| 98 <filter>samout_conditional['samout']</filter> | |
| 99 </data> | |
| 100 </outputs> | |
| 101 | |
| 102 <stdio> | |
| 103 <exit_code range="1:" level="fatal" description="Unknown error occurred" /> | |
| 104 </stdio> | |
| 105 | |
| 106 <tests> | |
| 107 <test> | |
| 108 <param name="samfile" value="htseq-test.sam" /> | |
| 109 <param name="gfffile" value="htseq-test.gff" /> | |
| 110 <param name="samout" value="False" /> | |
| 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 | 113 </test> |
| 114 <test> | |
| 115 <param name="samfile" value="htseq-test.bam" /> | |
| 116 <param name="gfffile" value="htseq-test.gff" /> | |
| 117 <param name="samout" value="False" /> | |
| 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 | 120 </test> |
| 121 <!-- Seems to be an issue setting the $reference_fasta_filename variable during test | |
| 122 <test> | |
| 123 <param name="samfile" value="htseq-test.sam" /> | |
| 124 <param name="gfffile" value="htseq-test.gff" /> | |
| 125 <param name="samout" value="True" /> | |
| 126 <param name="reference_source_selector" value="history" /> | |
| 127 <param name="ref_file" value="htseq-test_reference.fasta" /> | |
| 128 <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
|
129 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
| 0 | 130 <output name="samoutfile" file="htseq-test_samout.bam" /> |
| 131 </test> | |
| 132 --> | |
| 133 </tests> | |
| 134 | |
| 135 <help> | |
| 136 Overview | |
| 137 -------- | |
| 138 | |
| 139 This tool takes an alignment file in SAM or BAM format and feature file in GFF format | |
| 140 and calculates the number of reads mapping to each feature. It uses the *htseq-count* | |
| 141 script that is part of the HTSeq python module. See | |
| 142 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
| 143 | |
| 144 A feature is an interval (i.e., a range of positions) on a chromosome or a union of | |
| 145 such intervals. In the case of RNA-Seq, the features are typically genes, where | |
| 146 each gene is considered here as the union of all its exons. One may also consider | |
| 147 each exon as a feature, e.g., in order to check for alternative splicing. For | |
| 148 comparative ChIP-Seq, the features might be binding regions from a pre-determined | |
| 149 list. | |
| 150 | |
| 151 **Paired-end Data MUST be sorted by QUERY NAME first** | |
| 152 | |
| 153 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. | |
| 154 | |
| 155 | |
| 156 Overlap Modes | |
| 157 ------------- | |
| 158 | |
| 159 Special care must be taken to decide how to deal with reads that overlap more than one feature. | |
| 160 | |
| 161 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*. | |
| 162 | |
| 163 The following figure illustrates the effect of these three modes: | |
| 164 | |
| 165 .. image:: /static/images/count_modes.png | |
| 166 :width: 500 | |
| 167 | |
| 168 Strandedness | |
| 169 ------------ | |
| 170 | |
| 171 **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! | |
| 172 | |
| 173 Output | |
| 174 ------ | |
| 175 | |
| 176 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 | |
| 177 | |
| 178 - *no_feature*: reads which could not be assigned to any feature (set S as described above was empty). | |
| 179 | |
| 180 - *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). | |
| 181 | |
| 182 - *too_low_aQual*: reads which were not counted due to the -a option, see below | |
| 183 | |
| 184 - *not_aligned*: reads in the SAM file without alignment | |
| 185 | |
| 186 - *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.) | |
| 187 | |
| 188 | |
| 189 Options Summary | |
| 190 --------------- | |
| 191 | |
| 192 Usage: htseq-count [options] sam_file gff_file | |
| 193 | |
| 194 This script takes an alignment file in SAM format and a feature file in GFF | |
| 195 format and calculates for each feature the number of reads mapping to it. See | |
| 196 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
| 197 | |
| 198 Options: | |
| 199 -h, --help show this help message and exit | |
| 200 -m MODE, --mode=MODE mode to handle reads overlapping more than one | |
| 201 feature(choices: union, intersection-strict, | |
| 202 intersection-nonempty; default: union) | |
| 203 -s STRANDED, --stranded=STRANDED | |
| 204 whether the data is from a strand-specific assay. | |
| 205 Specify 'yes', 'no', or 'reverse' (default: yes). | |
| 206 'reverse' means 'yes' with reversed strand | |
| 207 interpretation | |
| 208 -a MINAQUAL, --minaqual=MINAQUAL | |
| 209 skip all reads with alignment quality lower than the | |
| 210 given minimum value (default: 0) | |
| 211 -t FEATURETYPE, --type=FEATURETYPE | |
| 212 feature type (3rd column in GFF file) to be used, all | |
| 213 features of other type are ignored (default, suitable | |
| 214 for Ensembl GTF files: exon) | |
| 215 -i IDATTR, --idattr=IDATTR | |
| 216 GFF attribute to be used as feature ID (default, | |
| 217 suitable for Ensembl GTF files: gene_id) | |
| 218 -o SAMOUT, --samout=SAMOUT | |
| 219 write out all SAM alignment records into an output SAM | |
| 220 file called SAMOUT, annotating each line with its | |
| 221 feature assignment (as an optional field with tag | |
| 222 'XF') | |
| 223 -q, --quiet suppress progress report and warnings | |
| 224 | |
| 225 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology | |
| 226 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General | |
| 227 Public License v3. Part of the 'HTSeq' framework. | |
| 228 </help> | |
| 229 </tool> |