Mercurial > repos > lparsons > htseq_count
annotate htseq-count.xml @ 18:737cda668bdd draft
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
| author | lparsons |
|---|---|
| date | Mon, 22 Jun 2015 12:42:30 -0400 |
| parents | 3102bfcac0d6 |
| children | 8bc865a85024 |
| rev | line source |
|---|---|
| 17 | 1 <tool id="htseq_count" name="htseq-count" version="0.4.1"> |
| 0 | 2 <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description> |
| 3 <requirements> | |
| 12 | 4 <requirement type="package" version="0.6.1">htseq</requirement> |
|
8
65c91537862c
Updated to HTSeq 0.5.4p5, use tool shed repository dependencies
lparsons
parents:
7
diff
changeset
|
5 <requirement type="package" version="0.1.19">samtools</requirement> |
| 16 | 6 <requirement type="package" version="0.7.7">pysam</requirement> |
| 0 | 7 </requirements> |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
8 |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
9 <stdio> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
10 <exit_code range="1:" level="fatal" description="Unknown error occurred" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
11 <regex match="htseq-count: (command ){0,1}not found" source="stderr" level="fatal" description="The HTSeq python package is not properly installed, contact Galaxy administrators" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
12 <regex match="samtools: (command ){0,1}not found" source="stderr" level="fatal" description="The samtools package is not properly installed, contact Galaxy administrators" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
13 <regex match="Error: Feature (.+) does not contain a '(.+)' attribute" source="both" level="fatal" description="Error parsing the GFF file, at least one feature of the specified 'Feature type' does not have a value for the specified 'ID Attribute'" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
14 <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
15 <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
16 <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." /> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
17 </stdio> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
18 |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
19 <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
20 |
| 0 | 21 <command> |
| 22 ##set up input files | |
| 23 #set $reference_fasta_filename = "localref.fa" | |
| 24 #if $samout_conditional.samout: | |
| 25 #if str( $samout_conditional.reference_source.reference_source_selector ) == "history": | |
| 26 ln -s "${samout_conditional.reference_source.ref_file}" "${reference_fasta_filename}" && | |
| 27 samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 && | |
| 28 #else: | |
| 29 #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path ) | |
| 30 #end if | |
| 31 #end if | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
32 htseq-count |
| 12 | 33 --format=$samfile.extension |
| 34 --order=pos | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
35 --mode=$mode |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
36 --stranded=$stranded |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
37 --minaqual=$minaqual |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
38 --type=$featuretype |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
39 --idattr=$idattr |
| 0 | 40 #if $samout_conditional.samout: |
| 41 --samout=$__new_file_path__/${samoutfile.id}_tmp | |
| 42 #end if | |
| 12 | 43 $samfile |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
44 $gfffile |
| 5 | 45 | 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 | 46 #if $samout_conditional.samout: |
| 47 && samtools view -Su -t ${reference_fasta_filename}.fai $__new_file_path__/${samoutfile.id}_tmp | samtools sort -o - sorted > $samoutfile | |
| 48 #end if</command> | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
49 |
| 0 | 50 <inputs> |
|
13
256d3114ce31
Fix input format string and change dependency owners to devteam
lparsons
parents:
12
diff
changeset
|
51 <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/> |
| 0 | 52 <param format="gff" name="gfffile" type="data" label="GFF File"/> |
| 53 <param name="mode" type="select" label="Mode"> | |
| 54 <help>Mode to handle reads overlapping more than one feature.</help> | |
| 55 <option value="union" selected="true">Union</option> | |
| 56 <option value="intersection-strict">Intersection (strict)</option> | |
| 57 <option value="intersection-nonempty">Intersection (nonempty)</option> | |
| 58 </param> | |
| 59 <param name="stranded" type="select" label="Stranded"> | |
| 60 <help>Specify whether the data is from a strand-specific assay. 'Reverse' means yes with reversed strand interpretation.</help> | |
| 61 <option value="yes" selected="true">Yes</option> | |
| 62 <option value="no">No</option> | |
| 63 <option value="reverse">Reverse</option> | |
| 64 </param> | |
| 12 | 65 <param name="minaqual" type="integer" value="10" label="Minimum alignment quality"> |
| 0 | 66 <help>Skip all reads with alignment quality lower than the given minimum value</help> |
| 67 </param> | |
| 5 | 68 <param name="featuretype" type="text" value="exon" label="Feature type"> |
| 0 | 69 <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> |
| 70 </param> | |
| 71 <param name="idattr" type="text" value="gene_id" label="ID Attribute"> | |
| 5 | 72 <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 | 73 </param> |
| 74 <conditional name="samout_conditional"> | |
| 75 <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output"> | |
| 76 <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> | |
| 77 </param> | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
78 <when value="True"> |
| 0 | 79 <conditional name="reference_source"> |
| 80 <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> | |
| 81 <option value="cached">Locally cached</option> | |
| 82 <option value="history">History</option> | |
| 83 </param> | |
| 84 <when value="cached"> | |
| 85 <param name="ref_file" type="select" label="Using reference genome"> | |
| 86 <options from_data_table="sam_fa_indexes"> | |
| 5 | 87 <filter type="data_meta" key="dbkey" ref="samfile" column="1"/> |
| 0 | 88 </options> |
| 89 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> | |
| 90 </param> | |
| 91 </when> | |
| 92 <when value="history"> <!-- FIX ME!!!! --> | |
| 93 <param name="ref_file" type="data" format="fasta" label="Using reference file" /> | |
| 94 </when> | |
| 95 </conditional> | |
| 96 </when> | |
| 97 </conditional> | |
| 98 </inputs> | |
| 99 | |
| 100 <outputs> | |
| 5 | 101 <data format="tabular" name="counts" metadata_source="samfile" label="${tool.name} on ${on_string}"/> |
| 102 <data format="tabular" name="othercounts" metadata_source="samfile" label="${tool.name} on ${on_string} (no feature)"/> | |
| 103 <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)"> | |
| 0 | 104 <filter>samout_conditional['samout']</filter> |
| 105 </data> | |
| 106 </outputs> | |
| 107 | |
| 108 <tests> | |
| 109 <test> | |
| 110 <param name="samfile" value="htseq-test.sam" /> | |
| 111 <param name="gfffile" value="htseq-test.gff" /> | |
| 112 <param name="samout" value="False" /> | |
| 113 <output name="counts" file="htseq-test_counts.tsv" /> | |
| 5 | 114 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
| 0 | 115 </test> |
| 116 <test> | |
| 117 <param name="samfile" value="htseq-test.bam" /> | |
| 118 <param name="gfffile" value="htseq-test.gff" /> | |
| 119 <param name="samout" value="False" /> | |
| 120 <output name="counts" file="htseq-test_counts.tsv" /> | |
| 5 | 121 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
| 122 </test> | |
| 123 <test> | |
| 124 <param name="samfile" value="htseq-test-paired.bam" /> | |
| 125 <param name="singlepaired" value="paired" /> | |
| 126 <param name="gfffile" value="htseq-test.gff" /> | |
| 127 <param name="samout" value="False" /> | |
| 128 <output name="counts" file="htseq-test-paired_counts.tsv" /> | |
| 129 <output name="othercounts" file="htseq-test-paired_othercounts.tsv" /> | |
| 0 | 130 </test> |
| 131 <!-- Seems to be an issue setting the $reference_fasta_filename variable during test | |
| 132 <test> | |
| 133 <param name="samfile" value="htseq-test.sam" /> | |
| 134 <param name="gfffile" value="htseq-test.gff" /> | |
| 135 <param name="samout" value="True" /> | |
| 136 <param name="reference_source_selector" value="history" /> | |
| 137 <param name="ref_file" value="htseq-test_reference.fasta" /> | |
| 138 <output name="counts" file="htseq-test_counts.tsv" /> | |
| 5 | 139 <output name="othercounts" file="htseq-test_othercounts.tsv" /> |
| 0 | 140 <output name="samoutfile" file="htseq-test_samout.bam" /> |
| 141 </test> | |
| 142 --> | |
| 143 </tests> | |
| 144 | |
| 145 <help> | |
| 146 Overview | |
| 147 -------- | |
| 148 | |
| 149 This tool takes an alignment file in SAM or BAM format and feature file in GFF format | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
150 and calculates the number of reads mapping to each feature. It uses the *htseq-count* |
| 0 | 151 script that is part of the HTSeq python module. See |
| 152 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
| 153 | |
| 154 A feature is an interval (i.e., a range of positions) on a chromosome or a union of | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
155 such intervals. In the case of RNA-Seq, the features are typically genes, where |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
156 each gene is considered here as the union of all its exons. One may also consider |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
157 each exon as a feature, e.g., in order to check for alternative splicing. For |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
158 comparative ChIP-Seq, the features might be binding regions from a pre-determined |
| 0 | 159 list. |
| 160 | |
| 161 | |
| 162 Overlap Modes | |
| 163 ------------- | |
| 164 | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
165 Special care must be taken to decide how to deal with reads that overlap more than one feature. |
| 0 | 166 |
| 167 The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*. | |
| 168 | |
| 169 The following figure illustrates the effect of these three modes: | |
| 170 | |
| 14 | 171 .. image:: count_modes.png |
| 0 | 172 |
|
6
08a11d1eaec6
Updated HTSEQ package to version 0.5.4p1, attempted to fix galaxy install where lib64 directory does not exist
lparsons
parents:
5
diff
changeset
|
173 |
| 0 | 174 Strandedness |
| 175 ------------ | |
| 176 | |
| 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! | |
| 178 | |
|
6
08a11d1eaec6
Updated HTSEQ package to version 0.5.4p1, attempted to fix galaxy install where lib64 directory does not exist
lparsons
parents:
5
diff
changeset
|
179 |
| 0 | 180 Output |
| 181 ------ | |
| 182 | |
| 183 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 | |
| 184 | |
| 185 - *no_feature*: reads which could not be assigned to any feature (set S as described above was empty). | |
| 186 | |
| 187 - *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). | |
| 188 | |
| 189 - *too_low_aQual*: reads which were not counted due to the -a option, see below | |
| 190 | |
| 191 - *not_aligned*: reads in the SAM file without alignment | |
| 192 | |
| 193 - *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.) | |
| 194 | |
| 195 | |
| 196 Options Summary | |
| 197 --------------- | |
| 198 | |
| 199 Usage: htseq-count [options] sam_file gff_file | |
| 200 | |
| 201 This script takes an alignment file in SAM format and a feature file in GFF | |
| 202 format and calculates for each feature the number of reads mapping to it. See | |
| 203 http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details. | |
| 204 | |
| 205 Options: | |
| 206 -h, --help show this help message and exit | |
| 207 -m MODE, --mode=MODE mode to handle reads overlapping more than one | |
| 208 feature(choices: union, intersection-strict, | |
| 209 intersection-nonempty; default: union) | |
| 210 -s STRANDED, --stranded=STRANDED | |
| 211 whether the data is from a strand-specific assay. | |
| 212 Specify 'yes', 'no', or 'reverse' (default: yes). | |
| 213 'reverse' means 'yes' with reversed strand | |
| 214 interpretation | |
| 215 -a MINAQUAL, --minaqual=MINAQUAL | |
| 216 skip all reads with alignment quality lower than the | |
| 217 given minimum value (default: 0) | |
| 218 -t FEATURETYPE, --type=FEATURETYPE | |
| 219 feature type (3rd column in GFF file) to be used, all | |
| 220 features of other type are ignored (default, suitable | |
| 221 for Ensembl GTF files: exon) | |
| 222 -i IDATTR, --idattr=IDATTR | |
| 223 GFF attribute to be used as feature ID (default, | |
| 224 suitable for Ensembl GTF files: gene_id) | |
| 225 -o SAMOUT, --samout=SAMOUT | |
| 226 write out all SAM alignment records into an output SAM | |
| 227 file called SAMOUT, annotating each line with its | |
| 228 feature assignment (as an optional field with tag | |
| 229 'XF') | |
| 230 -q, --quiet suppress progress report and warnings | |
| 231 | |
| 232 Written by Simon Anders (sanders@fs.tum.de), European Molecular Biology | |
| 233 Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General | |
| 234 Public License v3. Part of the 'HTSeq' framework. | |
| 235 </help> | |
|
18
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
236 <citations> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
237 <citation type="bibtex"> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
238 @article{anders_htseqpython_2015, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
239 title = {{HTSeq}—a {Python} framework to work with high-throughput sequencing data}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
240 volume = {31}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
241 issn = {1367-4803, 1460-2059}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
242 url = {http://bioinformatics.oxfordjournals.org/content/31/2/166}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
243 doi = {10.1093/bioinformatics/btu638}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
244 abstract = {Motivation: A large choice of tools exists for many standard tasks in the analysis of high-throughput sequencing (HTS) data. However, once a project deviates from standard workflows, custom scripts are needed. |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
245 Results: We present HTSeq, a Python library to facilitate the rapid development of such scripts. HTSeq offers parsers for many common data formats in HTS projects, as well as classes to represent data, such as genomic coordinates, sequences, sequencing reads, alignments, gene model information and variant calls, and provides data structures that allow for querying via genomic coordinates. We also present htseq-count, a tool developed with HTSeq that preprocesses RNA-Seq data for differential expression analysis by counting the overlap of reads with genes. |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
246 Availability and implementation: HTSeq is released as an open-source software under the GNU General Public Licence and available from http://www-huber.embl.de/HTSeq or from the Python Package Index at https://pypi.python.org/pypi/HTSeq. |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
247 Contact: sanders\{at\}fs.tum.de}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
248 language = {en}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
249 number = {2}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
250 urldate = {2015-04-21}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
251 journal = {Bioinformatics}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
252 author = {Anders, Simon and Pyl, Paul Theodor and Huber, Wolfgang}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
253 month = jan, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
254 year = {2015}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
255 pmid = {25260700}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
256 pages = {166--169}, |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
257 file = {Full Text PDF:/Users/lparsons/Library/Application Support/Firefox/Profiles/thd2t4je.default/zotero/storage/84XQB8V6/Anders et al. - 2015 - HTSeq—a Python framework to work with high-through.pdf:application/pdf;Snapshot:/Users/lparsons/Library/Application Support/Firefox/Profiles/thd2t4je.default/zotero/storage/JKUAUCKB/166.html:text/html} |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
258 } |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
259 </citation> |
|
737cda668bdd
planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502
lparsons
parents:
17
diff
changeset
|
260 </citations> |
| 0 | 261 </tool> |