Mercurial > repos > iuc > hal_hal2maf
diff hal_hal2maf.xml @ 0:a3ff8225d554 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/haltools commit 6244b9d15a5ad97ae20191e2f8fbafe2050c3cac
| author | iuc |
|---|---|
| date | Fri, 06 Feb 2026 10:38:29 +0000 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/hal_hal2maf.xml Fri Feb 06 10:38:29 2026 +0000 @@ -0,0 +1,333 @@ +<tool id="hal_hal2maf" name="hal2maf" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> + <description>converts HAL to MAF</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command detect_errors="aggressive"><![CDATA[ + #if $file.append == 'true': + ## If an input MAF file is provided to append to, ensure that it is not modified. + cp '$input_maf' writable_maf.maf && + #end if + hal2maf + #if $file.append == 'true': + --append + #end if + #if $genome.reference == 'custom': + --refGenome '$genome.refGenome' + $genome.noAncestors + #end if + #if $filter.option == '--targetGenomes': + --targetGenomes '$filter.targetGenomes' + #else if $filter.option == '--rootGenome': + --rootGenome '$filter.rootGenome' + #end if + #if $convert.mode == 'sequence': + --refSequence '$convert.sequence' + --start $convert.start + --length $convert.length + #else if $convert.mode == 'target': + --refTargets '$convert.refTargets' + #else if $convert.mode == 'global': + --global + #end if + --maxRefGap $maxRefGap + --maxBlockLen $maxBlockLen + $noDupes + $onlySequenceNames + $unique + $printTree + $onlyOrthologs + $keepEmptyRefBlocks + '$input_hal' writable_maf.maf + #if $compression.type == 'gz': + && gzip -c writable_maf.maf > '$output_file' + #else if $compression.type == 'bz2': + && bzip2 -c writable_maf.maf > '$output_file' + #else: + && mv writable_maf.maf '$output_file' + #end if + ]]></command> + <inputs> + <expand macro="input_hal"/> + <expand macro="params_conditional_refGenome"/> + <conditional name="filter"> + <param name="option" type="select" label="Genomes to include in the output"> + <option value="" selected="true">All genomes (default)</option> + <option value="--targetGenomes">Specific target genomes (--targetGenomes)</option> + <option value="--rootGenome">Only genomes in the subtree to a root (--rootGenome)</option> + </param> + <when value=""/> + <when value="--targetGenomes"> + <expand macro="params_targetGenomes"/> + </when> + <when value="--rootGenome"> + <expand macro="params_rootGenome"/> + </when> + </conditional> + <conditional name="convert"> + <param name="mode" type="select" label="Convert options"> + <option value="" selected="true">All sequences (default)</option> + <option value="sequence">A reference sequence (--refSequence)</option> + <option value="target">Using reference intervals from a BED file (--refTargets)</option> + <option value="global">All columns in alignment, ignoring reference-based filters (--global)</option> + </param> + <when value=""/> + <when value="sequence"> + <expand macro="params_sequence"/> + <expand macro="params_start"/> + <expand macro="params_length"/> + </when> + <when value="target"> + <param name="refTargets" type="data" format="bed" label="BED file" help="BED file with reference genome intervals to convert. Only alignment columns overlapping these intervals are included"/> + </when> + <when value="global"/> + </conditional> + <conditional name="file"> + <param name="append" type="select" label="Append new alignment to an existing MAF file"> + <option value="false" selected="true">No, create a new MAF file (default)</option> + <option value="true">Yes, append to an existing MAF file (--append)</option> + </param> + <when value="true"> + <param name="input_maf" type="data" format="maf" label="MAF file"/> + </when> + <when value="false"/> + </conditional> + <param argument="--maxRefGap" type="integer" min="0" value="0" label="Maximum gap length" help="Maximum gap length in reference genome"/> + <param argument="--maxBlockLen" type="integer" min="0" value="1000" label="Maximum block length" help="Maximum length of MAF block in output"/> + <param argument="--noDupes" type="boolean" truevalue="--noDupes" falsevalue="" checked="false" label="Ignore paralogy edges" help="Ignore paralogy edges"/> + <expand macro="params_onlySequenceNames"/> + <param argument="--unique" type="boolean" truevalue="--unique" falsevalue="" checked="false" label="Unique" help="Only write column whose left-most reference coordinate is in the specified range. This is used to ensure that the same column isn't sampled twice (due to duplications) by MAFs generated on distinct ranges"/> + <param argument="--printTree" type="boolean" truevalue="--printTree" falsevalue="" checked="false" label="Print Tree" help="Print a gene tree for every block"/> + <param argument="--onlyOrthologs" type="boolean" truevalue="--onlyOrthologs" falsevalue="" checked="false" label="Only Orthologs" help="Make only orthologs to the reference appear in the MAF blocks"/> + <param argument="--keepEmptyRefBlocks" type="boolean" truevalue="--global" falsevalue="" checked="false" label="Keep empty reference blocks" help="Keep blocks that contain no reference sequence"/> + <expand macro="params_conditional_compression"/> + </inputs> + <outputs> + <data name="output_file" format="maf" label="${tool.name} on ${on_string}: MAF file"> + <change_format> + <when input="compression.type" value="gz" format="maf.gz"/> + <when input="compression.type" value="bz2" format="maf.bz2"/> + </change_format> + </data> + </outputs> + <tests> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="filter"> + <param name="option" value=""/> + </conditional> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_0.Genome_0_seq	293	293	+	1758"/> + <has_text text="s	Genome_1.Genome_1_seq	4571	117	+	5472"/> + <has_n_lines n="90"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="filter"> + <param name="option" value=""/> + </conditional> + <conditional name="compression"> + <param name="type" value="gz"/> + </conditional> + <output name="output_file" ftype="maf.gz" file="hal2maf_output.maf.gz"/> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="filter"> + <param name="option" value=""/> + </conditional> + <conditional name="compression"> + <param name="type" value="bz2"/> + </conditional> + <output name="output_file" ftype="maf.bz2" file="hal2maf_output.maf.bz2"/> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="filter"> + <param name="option" value="--rootGenome"/> + <param name="rootGenome" value="Genome_1"/> + </conditional> + <param name="printTree" value="true"/> + <param name="onlySequenceNames" value="true"/> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_text text="a tree="/> + <has_text text="Genome_1_seq,Genome_1_seq,Genome_2,Genome_3,Genome_3)Genome_0_seq;"/> + <has_text text="Genome_0_seq	293	293	+	1758"/> + <has_text text="s	Genome_1_seq	4864	117	+	5472"/> + <has_n_lines n="52"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <param name="maxBlockLen" value="200"/> + <param name="noDupes" value="true"/> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_3.Genome_3_seq	4102	200	+	6139"/> + <has_text text="s	Genome_1.Genome_1_seq	3130	93	+	5472"/> + <has_text text="s	Genome_0.Genome_0_seq	1748	10	+	1758	CGCGTCGGCG"/> + <has_n_lines n="69"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="genome"> + <param name="reference" value="custom"/> + <param name="refGenome" value="Genome_1"/> + <param name="noAncestors" value="true"/> + </conditional> + <param name="onlyOrthologs" value="true"/> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_1.Genome_1_seq	5135	337	+	5472"/> + <has_text text="s	Genome_2.Genome_2_seq	2498	139	+	4270"/> + <has_text text="s	Genome_3.Genome_3_seq	4571	117	+	6139"/> + <has_n_lines n="230"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="genome"> + <param name="reference" value="custom"/> + <param name="refGenome" value="Genome_1"/> + </conditional> + <param name="unique" value="true"/> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_3.Genome_3_seq	1033	139	+	6139"/> + <has_text text="s	Genome_0.Genome_0_seq	1348	117	+	1758"/> + <has_text text="s	Genome_1.Genome_1_seq	5274	198	+	5472	NNNNNNNNNNNNNNNN"/> + <has_n_lines n="96"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="genome"> + <param name="reference" value="custom"/> + <param name="refGenome" value="Genome_1"/> + </conditional> + <param name="maxRefGap" value="2000"/> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_2.Genome_2_seq	2344	154	+	4270"/> + <has_text text="s	Genome_1.Genome_1_seq	1465	293	+	5472	----------------"/> + <has_text text="s	Genome_1.Genome_1_seq	3516	293	+	5472	NNNNNNNNNNNNNNNN"/> + <has_n_lines n="101"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="convert"> + <param name="mode" value="sequence"/> + <param name="sequence" value="Genome_0_seq"/> + <param name="start" value="4"/> + <param name="length" value="10"/> + </conditional> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_line line="s	Genome_0.Genome_0_seq	4	10	+	1758	TCGGGGGGGA"/> + <has_line line="s	Genome_2.Genome_2_seq	4	10	+	4270	TCGGGGGGGA"/> + <has_line line="s	Genome_3.Genome_3_seq	4	10	+	6139	TCGGGGGGGA"/> + <has_n_lines n="11"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="file"> + <param name="append" value="true"/> + <param name="input_maf" value="hal2maf_append.maf"/> + </conditional> + <conditional name="filter"> + <param name="option" value="--targetGenomes"/> + <param name="targetGenomes" value="Genome_2,Genome_3"/> + </conditional> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_1.Genome_1_seq	0	293	+	5472"/> + <has_text text="s	Genome_3.Genome_3_seq	4395	176	+	6139"/> + <has_text text="s	Genome_1.Genome_1_seq	3223	176	+	5472"/> + <has_n_lines n="152"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="convert"> + <param name="mode" value="global"/> + </conditional> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_1.Genome_1_seq	3516	293	+	5472	NNNNNNNNNNNN"/> + <has_text text="s	Genome_2.Genome_2_seq	1465	293	+	4270	------------"/> + <has_text text="s	Genome_3.Genome_3_seq	4571	117	+	6139"/> + <has_n_lines n="113"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="input_hal" value="halTest.hal"/> + <conditional name="convert"> + <param name="mode" value="target"/> + <param name="refTargets" value="hal2maf.bed"/> + </conditional> + <output name="output_file" ftype="maf"> + <assert_contents> + <has_line line="##maf version=1 scoring=N/A"/> + <has_line line="# hal (Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/> + <has_line line="a"/> + <has_text text="s	Genome_0.Genome_0_seq	0	293	+	1758"/> + <has_text text="s	Genome_2.Genome_2_seq	3516	293	+	4270"/> + <has_text text="s	Genome_3.Genome_3_seq	586	293	+	6139"/> + <has_n_lines n="24"/> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +hal2maf converts an input HAL alignment into a MAF file as output. +The tool supports converting the full alignment or restricting output to a selected reference genome, reference sequence, a set of target genomes, or only genomes belonging to the subtree rooted at a root genome. + +Additional controls allow filtering for orthologs, excluding ancestral sequences, keeping empty reference blocks, limiting block size, and controlling reference gaps. +MAF blocks can also include gene tree annotations if requested. + ]]></help> + <expand macro="citation"/> + <expand macro="creator"/> +</tool> \ No newline at end of file