Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update pharokka to latest version #6651

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion tools/pharokka/macros.xml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<?xml version="1.0"?>
<macros>
<token name="@TOOL_VERSION@">1.3.2</token>
<token name="@TOOL_VERSION@">1.7.4</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@PROFILE@">21.05</token>
<xml name="biotools">
Expand Down
131 changes: 76 additions & 55 deletions tools/pharokka/pharokka.xml
Original file line number Diff line number Diff line change
Expand Up @@ -5,49 +5,50 @@
<macros>
<import>macros.xml</import>
</macros>
<expand macro="biotools" />
<expand macro="requirements" />
<expand macro="version" />
<expand macro="biotools"/>
<expand macro="requirements"/>
<expand macro="version"/>
<command detect_errors="exit_code">
<![CDATA[

##run tool
#if str( $terminase.terminase_selector ) == 'no_terminase':
pharokka.py
-i '$fasta'
<![CDATA[
pharokka.py
-i '$input'
#if $input.ext == "genbank":
--genbank
#end if
-o pharokka_output
-d '$db_cached.fields.path'
-t \${GALAXY_SLOTS:-8}
-t \${GALAXY_SLOTS:-8}
$gene_predictor
$skip_mash
$skip_extra_annotations
$trna_scan_model
$meta
-e '$evalue'
#else:
pharokka.py
-i '$fasta'
-o pharokka_output
-d '$db_cached.fields.path'
-t \${GALAXY_SLOTS:-8}
$gene_predictor
$meta
-e '$evalue'
$dnaapler
-e '$evalue'
$hmm_only
#if $custom_hmm:
--custom_hmm $custom_hmm
#end if
##run tool
#if str( $terminase.terminase_selector ) != 'no_terminase':
--terminase
--terminase_strand '$terminase.terminase_strand'
--terminase_start '$terminase.terminase_start'
#end if
#end if

## create output
#if $zip_output == 'true':
&& zip -r out.zip pharokka_output
#end if
]]>
## create output
#if $zip_output == 'true':
&& zip -r out.zip pharokka_output
#end if
]]>
</command>
<inputs>
<!-- the genome -->
<param type="data" name="fasta" format="fasta" help="Please upload a genome file of a bacteriophage in fasta format." label="Bacteriophage genome" />
<param name="input" type="data" format="fasta,genbank" label="Bacteriophage genome" help="Please upload a genome file of a bacteriophage in fasta format."/>
<param name="db_cached" type="select" label="Using built-in pharokka DB" help="Using built-in pharokka DB">
<options from_data_table="pharokka_db_versioned">
</options>
<validator type="no_options" message="A built-in pharokka DB is not available. Please ask the galaxy admins to install one on the server." />
<validator type="no_options" message="A built-in pharokka DB is not available. Please ask the galaxy admins to install one on the server."/>
</param>
<param name="gene_predictor" type="select" label="User specified gene predictor">
<option value="-g phanotate">
Expand All @@ -56,9 +57,16 @@
<option value="-g prodigal">
Prodigal
</option>
<option value="-g prodigal-gv">
Prodigal-GV
</option>
</param>
<param argument="--trna_scan_model" type="select" label="tRNAscan-SE model" help="More information about the models are available in https://doi.org/10.1093/nar/gkab688">
<option value="--trna_scan_model general" selected="true">general tRNAscan-SE model</option>
<option value="--trna_scan_model bacterial">bacterial tRNAscan-SE model</option>
</param>
<param name="meta" type="boolean" checked="false" truevalue="--meta" falsevalue="" label="Meta mode for metavirome input samples" />
<param name="evalue" type="float" value="1E-5" min="1E-20" max="10" label="E-value threshold for mmseqs2 PHROGs database search. Defaults to 1E-05." />
<param name="meta" type="boolean" truevalue="--meta" falsevalue="" checked="false" label="Meta mode for metavirome input samples"/>
<param name="evalue" type="float" min="1E-20" max="10" value="1E-5" label="E-value threshold for mmseqs2 PHROGs database search. Defaults to 1E-05."/>
<!-- optional arguments -->
<conditional name="terminase">
<param name="terminase_selector" type="select" label="Runs - terminase large subunit - re-orientation mode. Single genome input only and requires --terminase_strand and --terminase_start to be specified.">
Expand All @@ -80,64 +88,77 @@
Negative
</option>
</param>
<param name="terminase_start" type="integer" value="1" label="Start coordinate of the terminase large subunit." />
<param name="terminase_start" type="integer" value="1" label="Start coordinate of the terminase large subunit."/>
</when>
</conditional>

<param argument="--skip_mash" type="boolean" truevalue="--skip_mash" falsevalue="" checked="false"
label="skip finding the closest match for each contig in INPHARED using mash"/>

<param argument="--skip_extra_annotations" type="boolean" truevalue="--skip_extra_annotations" falsevalue="" checked="false"
label="skip running tRNA-scanSE, MinCED and Aragorn" help="Useful in case you only want CDS predictions and functional annotations" />

<param argument="--dnaapler" type="boolean" truevalue="--dnaapler" falsevalue="" checked="false"
label="Automatically detect and reorient your phage to start with the large terminase subunit" />

<param argument="--hmm_only" type="boolean" truevalue="--hmm_only" falsevalue="" checked="false" label="Only runs PyHMMER on PHROGs"
help="It will not run MMseqs2 at all on PHROGs, CARD or VFDB. For phage isolates, this will be much faster, but you will not get CARD or VFDB annotations. For metagenomes, this will be (much) slower though!" />

<param argument="--custom_hmm" type="data" format="hmm" optional="true" label="Use custom HMM profile databases" />
<!-- optional outputs -->
<param name="zip_output" type="boolean" checked="false" truevalue="true" falsevalue="false" label="Create a Zip archive of the complete output for further investigation." />
<param name="zip_output" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Create a Zip archive of the complete output for further investigation."/>
</inputs>
<outputs>
<data name="pharokka_gbk" format="genbank" from_work_dir="pharokka_output/pharokka.gbk" label="${tool.name} on ${on_string}: Genbank" />
<data name="pharokka_gff" format="gff" from_work_dir="pharokka_output/pharokka.gff" label="${tool.name} on ${on_string}: GFF" />
<data name="archive_output" format="zip" from_work_dir="out.zip" label="${tool.name} on ${on_string}: zip of the complete output" >
<data name="pharokka_gbk" format="genbank" from_work_dir="pharokka_output/pharokka.gbk" label="${tool.name} on ${on_string}: Genbank"/>
<data name="pharokka_gff" format="gff" from_work_dir="pharokka_output/pharokka.gff" label="${tool.name} on ${on_string}: GFF"/>
<data name="archive_output" format="zip" from_work_dir="out.zip" label="${tool.name} on ${on_string}: zip of the complete output">
<filter>zip_output</filter>
</data>

</outputs>
<tests>
<!-- test input from DB - no zip -->
<test expect_num_outputs="2">
<param name="db_cached" value="pharokka_db" />
<param name="fasta" value="SAOMS1.fasta" />
<param name="zip_output" value="false" />
<param name="db_cached" value="pharokka_db"/>
<param name="input" value="SAOMS1.fasta"/>
<param name="zip_output" value="false"/>
<!-- check file size and text since output is non-deterministic -->
<output name="pharokka_gbk">
<assert_contents>
<has_size value="353875" delta="10" />
<has_text text="VERSION MW460250_1" />
<has_size value="353875" delta="10"/>
<has_text text="VERSION MW460250_1"/>
</assert_contents>
</output>
<output name="pharokka_gff">
<assert_contents>
<has_size value="191497" delta="10" />
<has_text text="##sequence-region MW460250_1 1 140135" />
<has_size value="191497" delta="10"/>
<has_text text="##sequence-region MW460250_1 1 140135"/>
</assert_contents>
</output>
</test>
<!-- test input from DB -->
<test expect_num_outputs="3">
<param name="db_cached" value="pharokka_db" />
<param name="fasta" value="SAOMS1.fasta" />
<param name="zip_output" value="true" />
<param name="db_cached" value="pharokka_db"/>
<param name="input" value="SAOMS1.fasta"/>
<param name="zip_output" value="true"/>
<!-- check file size and text since output is non-deterministic -->
<output name="pharokka_gbk">
<assert_contents>
<has_size value="353875" delta="10" />
<has_text text="VERSION MW460250_1" />
<has_size value="353875" delta="10"/>
<has_text text="VERSION MW460250_1"/>
</assert_contents>
</output>
<output name="pharokka_gff">
<assert_contents>
<has_size value="191497" delta="10" />
<has_text text="##sequence-region MW460250_1 1 140135" />
<has_size value="191497" delta="10"/>
<has_text text="##sequence-region MW460250_1 1 140135"/>
</assert_contents>
</output>
<!-- check created zip -->
<output name="archive_output">
<assert_contents>
<has_archive_member path=".*\/pharokka\.gff" />
<has_archive_member path=".*\/pharokka\.gbk" />
<has_archive_member path=".*\/pharokka.*\.log" />
<has_archive_member path=".*\/pharokka\.gff"/>
<has_archive_member path=".*\/pharokka\.gbk"/>
<has_archive_member path=".*\/pharokka.*\.log"/>
</assert_contents>
</output>
</test>
Expand All @@ -160,6 +181,6 @@
If you are looking for rapid standardised annotation of bacterial genomes, please use bakta.
]]>
</help>
<expand macro="citations" />
<expand macro="creator" />
<expand macro="citations"/>
<expand macro="creator"/>
</tool>
Loading