mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
97 lines
3.0 KiB
XML
97 lines
3.0 KiB
XML
<tool id="hgv_add_scores" name="phyloP" version="1.0.0">
|
|
<description>interspecies conservation scores</description>
|
|
<requirements>
|
|
<requirement type="package">add_scores</requirement>
|
|
</requirements>
|
|
<command>
|
|
python '$__tool_directory__/add_scores.py' '$input1' '$out_file1' '${GALAXY_DATA_INDEX_DIR}/add_scores.loc' '${input1.metadata.dbkey}' '${input1.metadata.chromCol}' '${input1.metadata.startCol}'
|
|
</command>
|
|
|
|
<inputs>
|
|
<param format="interval" name="input1" type="data" label="Dataset">
|
|
<validator type="unspecified_build"/>
|
|
<validator type="dataset_metadata_in_file" filename="add_scores.loc" metadata_name="dbkey" metadata_column="0" message="Data is currently not available for the specified build."/>
|
|
</param>
|
|
</inputs>
|
|
|
|
<outputs>
|
|
<data format_source="input1" name="out_file1" />
|
|
</outputs>
|
|
<tests>
|
|
<test>
|
|
<param name="input1" value="add_scores_input1.interval" ftype="interval" dbkey="hg18" />
|
|
<output name="output" file="add_scores_output1.interval" />
|
|
</test>
|
|
<test>
|
|
<param name="input1" value="add_scores_input2.bed" ftype="interval" dbkey="hg18" />
|
|
<output name="output" file="add_scores_output2.interval" />
|
|
</test>
|
|
</tests>
|
|
|
|
<help>
|
|
.. class:: warningmark
|
|
|
|
This currently works only for builds hg18 and hg19.
|
|
|
|
-----
|
|
|
|
**Dataset formats**
|
|
|
|
The input can be any interval_ format dataset. The output is also in interval format.
|
|
(`Dataset missing?`_)
|
|
|
|
.. _interval: ${static_path}/formatHelp.html#interval
|
|
.. _Dataset missing?: ${static_path}/formatHelp.html
|
|
|
|
-----
|
|
|
|
**What it does**
|
|
|
|
This tool adds a column that measures interspecies conservation at each SNP
|
|
position, using conservation scores for primates pre-computed by the
|
|
phyloP program. PhyloP performs an exact P-value computation under a
|
|
continuous Markov substitution model.
|
|
|
|
The chromosome and start position
|
|
are used to look up the scores, so if a larger interval is in the input,
|
|
only the score for the first nucleotide is returned.
|
|
|
|
-----
|
|
|
|
**Example**
|
|
|
|
- input file, with SNPs::
|
|
|
|
chr22 16440426 14440427 C/T
|
|
chr22 15494851 14494852 A/G
|
|
chr22 14494911 14494912 A/T
|
|
chr22 14550435 14550436 A/G
|
|
chr22 14611956 14611957 G/T
|
|
chr22 14612076 14612077 A/G
|
|
chr22 14668537 14668538 C
|
|
chr22 14668703 14668704 A/T
|
|
chr22 14668775 14668776 G
|
|
chr22 14680074 14680075 A/T
|
|
etc.
|
|
|
|
- output file, showing conservation scores for primates::
|
|
|
|
chr22 16440426 14440427 C/T 0.509
|
|
chr22 15494851 14494852 A/G 0.427
|
|
chr22 14494911 14494912 A/T NA
|
|
chr22 14550435 14550436 A/G NA
|
|
chr22 14611956 14611957 G/T -2.142
|
|
chr22 14612076 14612077 A/G 0.369
|
|
chr22 14668537 14668538 C 0.419
|
|
chr22 14668703 14668704 A/T -1.462
|
|
chr22 14668775 14668776 G 0.470
|
|
chr22 14680074 14680075 A/T 0.303
|
|
etc.
|
|
|
|
"NA" means that the phyloP score was not available.
|
|
</help>
|
|
<citations>
|
|
<citation type="doi">10.1007/11732990_17</citation>
|
|
</citations>
|
|
</tool>
|