annotate homer_findMotifsGenome.xml @ 0:ec974e69e0b5 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/homer commit e49d856e0181edc6120220a1b819cba2466a4289"

<tool id="homer_findMotifsGenome" name="findMotifsGenome" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05" license="MIT">
    <description/>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="xrefs"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
## Taken from fastqc:
#import re
#import os
#set input_name = re.sub('[^\w\-\s]', '_', str($input.element_identifier))
ln -s '${input}' '${input_name}' &&
#set output = $input_name + '_motif'
## Process the genome:
#if str( $genome.source ) == "installed":
    #set genome_file = re.sub('[^\w\-\s]', '_', str($genome.all_fasta_source.fields.value)) + '.fa'
    ln -s '$genome.all_fasta_source.fields.path' '$genome_file' &&
#elif str( $genome.source ) == "preparsed":
    #set genome_file = os.path.split(str($genome.homer_preparse_source.fields.path_fasta))[-1]
    ln -s '$genome.homer_preparse_source.fields.path_fasta' '$genome_file' &&
#elif str( $genome.source ) == "history":
    #set genome_file = re.sub('[^\w\-\s]', '_', str($genome.fasta.name)) + '.fa'
    ln -s '$genome.fasta' '$genome_file' &&
#end if
## Command:
findMotifsGenome.pl
## Peak:
'${input_name}'
## Genome:
'$genome_file'
## Ouptut folder:
'${output}'
## Options
#if str( $genome.source ) == "preparsed":
    -preparsedDir '$genome.homer_preparse_source.fields.path'
    #if str( $genome.homer_preparse_source.fields.mask ) == 'True':
        -mask
    #end if
    #if str( $genome.choose_center.center ) == "centered":
        -size '$genome.homer_preparse_source.fields.size'
    #else
        #set sizee = int($genome.choose_center.sizes) + int($genome.homer_preparse_source.fields.size)
        -size '$genome.choose_center.sizes','${sizee}'
    #end if
#else:
    #if $genome.mask
        -mask
    #end if
    #if $genome.fixed_size.size_fixed == "given":
        -size given
    #else:
        #if str( $genome.fixed_size.choose_center.center ) == "centered":
            -size '$genome.fixed_size.size'
        #else
            #set sizee = int($genome.fixed_size.choose_center.sizes) + int($genome.fixed_size.size)
            -size '$genome.fixed_size.choose_center.sizes','${sizee}'
        #end if
    #end if
#end if
-len '$len'
-S $S
-mis $mis
$norevopp
$nomotif
$rna
-mset $motif_options.mset
$motif_options.basic
$motif_options.bits
$motif_options.nocheck
#if $motif_options.mcheck:
    -mcheck '$motif_options.mcheck'
#end if
$motif_options.noknown
#if $motif_options.mknown:
    -mknown '$motif_options.mknown'
#end if
$motif_options.nofacts
$motif_options.seqlogo
$advanced.norm
$advanced.h
#if str($advanced.N):
    -N $advanced.N
#end if
-local $advanced.local
-redundant $advanced.redundant
-maxN $advanced.maxN
#if $advanced.maskMotif:
    -maskMotif '$advanced.maskMotif'
#end if
#if $advanced.opt:
    -opt '$advanced.opt'
#end if
$advanced.rand
#if $advanced.ref:
    -ref '$advanced.ref'
#end if
$advanced.oligo
#if $advanced.fdr:
    -fdr $advanced.fdr
#end if
#if str( $advanced.homer12.version ) == "homer2":
    -nlen '$advanced.homer12.nlen'
    -nmax '$advanced.homer12.nmax'
    $advanced.homer12.neutral
    -e '$advanced.homer12.e'
    $advanced.homer12.quickMask
    -minlp '$advanced.homer12.minlp'
#elif str( $advanced.homer12.version ) == "homer1":
    -depth '$advanced.homer12.depth'
#end if
#if not $nomotif:
    && cp '${output}'/homerResults.html outputHomer.html
    && cp -r '${output}' '${html_homer_file.files_path}'
#end if
#if not $motif_options.noknown:
    && cp '${output}'/knownResults.html outputKnown.html
    && cp -r '${output}' '${html_file.files_path}'
#end if
        ]]></command>
    <inputs>
        <param name="input" type="data" format="bed,encodepeak,tabular" label="Peak file"/>
        <conditional name="genome">
            <param name="source" type="select" label="Will you select a reference genome from your history or use a installed genome?">
                <option value="preparsed">Preparsed (fasta is available and has been preparsed to specific size)</option>
                <option value="installed">Installed (fasta is available but will be preparsed as run time)</option>
                <option value="history">From History (fasta will be preparsed at run time)</option>
            </param>
            <when value="preparsed">
                <param name="homer_preparse_source" type="select" label="Preparsed FASTA">
                    <options from_data_table="homer_preparse">
                        <filter type="sort_by" column="2"/>
                        <filter type="static_value" column="version" value="@IDX_VERSION@"/>
                        <validator type="no_options" message="No preparsed genomes are available"/>
                    </options>
                </param>
                <expand macro="choose_center"/>
            </when>
            <when value="installed">
                <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
                    <options from_data_table="all_fasta">
                        <filter type="sort_by" column="2"/>
                        <validator type="no_options" message="No references are available"/>
                    </options>
                </param>
                <expand macro="mask_size"/>
            </when>
            <when value="history">
                <param name="fasta" type="data" format="fasta" label="Select reference genome"/>
                <expand macro="mask_size"/>
            </when>
        </conditional>
        <param argument="-len" type="text" value="8,10,12" label="comma-separated motif lengths" help="values greater 12 may cause the program to run out of memory - in these cases decrease the number of sequences analyzed (-N), or try analyzing shorter sequence regions (i.e. -size 100)">
            <validator type="regex" message="motif lengths must be comma-separated integers without space">^(\d+,)*(\d+)$</validator>
        </param>
        <param argument="-S" type="integer" min="1" value="25" label="Number of motifs to find"/>
        <param argument="-mis" type="integer" min="0" value="2" label="Number of mismatches during global optimisation"/>
        <param argument="-norevopp" type="boolean" truevalue="-norevopp" falsevalue="" checked="false" label="Don't search reverse strand for motifs"/>
        <param argument="-nomotif" type="boolean" truevalue="-nomotif" falsevalue="" checked="false" label="Don't search for de novo motif enrichment"/>
        <param argument="-rna" type="boolean" truevalue="-rna" falsevalue="" checked="false" label="output RNA motif logos and compare to RNA motif database" help="automatically sets -norevopp"/>
        <section name="motif_options" title="Known Motif Options/Visualization" expanded="False">
            <param argument="-mset" type="select" label="Check against motif collects">
                <option value="auto" selected="True">automatic</option>
                <option value="vertebrates">vertebrates</option>
                <option value="insects">insects</option>
                <option value="worms">worms</option>
                <option value="plants">plants</option>
                <option value="yeast">yeast</option>
                <option value="all">all</option>
            </param>
            <param argument="-basic" type="boolean" truevalue="-basic" falsevalue="" checked="false" label="Just visualize de novo motifs, don't check similarity with known motifs"/>
            <param argument="-bits" type="boolean" truevalue="-bits" falsevalue="" checked="false" label="Scale sequence logos by information content" help="TODO"/>
            <param argument="-nocheck" type="boolean" truevalue="-nocheck" falsevalue="" checked="false" label="Don't search for de novo vs. known motif similarity"/>
            <param argument="-mcheck" type="data" optional="true" format="txt" label="known motifs to check against de novo motifs"/>
            <param argument="-noknown" type="boolean" truevalue="-noknown" falsevalue="" checked="false" label="Don't search for known motif enrichment"/>
            <param argument="-mknown" type="data" optional="true" format="txt" label="Known motifs to check for enrichment"/>
            <param argument="-nofacts" type="boolean" truevalue="-nofacts" falsevalue="" checked="false" label="Omit humor"/>
            <param argument="-seqlogo" type="boolean" truevalue="-seqlogo" falsevalue="" checked="false" label="Use weblogo/seqlogo/ghostscript to generate logos, default uses SVG now"/>
        </section>
        <section name="advanced" title="Advanced options" expanded="false">
            <param name="norm" type="select" label="Sequence normalization options:">
                <option value="-gc" selected="true">use GC% for sequence content normalization</option>
                <option value="-cpg">use CpG% instead of GC% for sequence content normalization</option>
                <option value="-noweight">no CG correction</option>
            </param>
            <param argument="-h" type="boolean" truevalue="-h" falsevalue="" checked="false" label="Use hypergeometric for p-values, binomial is default"/>
            <param argument="-N" type="integer" min="0" value="" optional="true" label="Number of sequences to use for motif finding, default=max(50k, 2x input)"/>
            <param argument="-local" type="integer" min="0" value="0" label="local background size in bp for each side of regions" help="0 means no local background."/>
            <param argument="-redundant" type="float" min="0" max="2" value="2" label="Remove redundant sequences matching greater than # fraction, i.e. -redundant 0.5"/>
            <param argument="-maxN" type="float" min="0" max="1" value="0.7" label="maximum percentage of N's in sequence to consider for motif finding"/>
            <param argument="-maskMotif" type="data" format="txt" multiple="true" optional="true" label="motifs to mask before motif finding"/>
            <param argument="-opt" type="data" format="txt" multiple="true" optional="true" label="motifs to optimize or change length of"/>
            <param argument="-rand" type="boolean" truevalue="-rand" falsevalue="" checked="false" label="randomize target and background sequences labels"/>
            <param argument="-ref" optional="true" type="data" format="tabular,bed,encodepeak" label="use file for target and background - first argument is list of peak ids for targets"/>
            <param argument="-oligo" type="boolean" truevalue="-oligo" falsevalue="" checked="false" label="Perform analysis of individual oligo enrichment"/>
            <param argument="-fdr" type="integer" min="0" value="" label="Number of randomizations to calculate empirical FDR for de novo discovery" optional="true"/>
            <conditional name="homer12">
                <param name="version" type="select" label="Which homer version do you want to use">
                    <option value="homer2" selected="true">homer2 (default)</option>
                    <option value="homer1">homer1 (to force the use of the original homer)</option>
                </param>
                <when value="homer2">
                    <param argument="-nlen" type="integer" min="0" value="3" label="length of lower-order oligos to normalize in background"/>
                    <param argument="-nmax" type="integer" min="0" value="160" label="Max normalization iterations"/>
                    <param argument="-neutral" type="boolean" truevalue="-neutral" falsevalue="" checked="false" label="weight sequences to neutral frequencies, i.e. 25%, 6.25%, etc."/>
                    <param argument="-olen" type="integer" min="0" value="" optional="true" label="lower-order oligo normalization for oligo table, use if -nlen isn't working well"/>
                    <param argument="-e" type="float" min="0" max="1" value="0" label="" help="Maximum expected motif instance per bp in random sequence"/>
                    <param argument="-quickMask" type="boolean" truevalue="-quickMask" falsevalue="" checked="false" label="skip full masking after finding motifs, similar to original homer"/>
                    <param argument="-minlp" type="float" value="-10" label="stop looking for motifs when seed logp score gets above this number"/>
                </when>
                <when value="homer1">
                    <param argument="-depth" type="select" label="time spent on local optimization default">
                        <option value="low">low</option>
                        <option value="med" selected="true">med</option>
                        <option value="high">high</option>
                        <option value="allnight">allnight</option>
                    </param>
                </when>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data format="html" name="html_file" from_work_dir="outputKnown.html" label="${tool.name} on ${on_string}: Known motifs">
            <filter>motif_options['noknown'] is False</filter>
        </data>
        <data format="html" name="html_homer_file" from_work_dir="outputHomer.html" label="${tool.name} on ${on_string}: De novo motifs">
            <filter>nomotif is False</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="input" value="fake_phix_peaks.bed"/>
            <conditional name="genome">
                <param name="source" value="installed"/>
                <param name="all_fasta_source" value="phiX174"/>
            </conditional>
            <output name="html_file" file="motif_test1/knownResults.html" ftype="html" lines_diff="2"/>
            <output name="html_homer_file">
                <assert_contents>
                    <has_text text="fake_phix_peaks_bed_motif/ - Homer de novo Motif Results"/>
                    <has_text text="Total target sequences = 1"/>
                    <has_text text="Jaspar"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <param name="input" value="CTCF_peaks_shifted.bed"/>
            <conditional name="genome">
                <param name="source" value="history"/>
                <param name="fasta" value="chr2_subset.fa"/>
            </conditional>
            <output name="html_file">
                <assert_contents>
                    <has_text text="CTCF_peaks_shifted_bed_motif - Homer Known Motif Enrichment Results"/>
                    <has_text text="Total Target Sequences = 40"/>
                    <has_text text="CTCF(Zf)/CD4+-CTCF-ChIP-Seq(Barski_et_al.)/Homer"/>
                </assert_contents>
            </output>
            <output name="html_homer_file">
                <assert_contents>
                    <has_text text="CTCF_peaks_shifted_bed_motif/ - Homer de novo Motif Results"/>
                    <has_text text="Total target sequences = 40"/>
                    <has_text_matching expression="CTCF(Zf)|CTCF/MA|BORIS|CTCFL"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <param name="input" value="CTCF_peaks_shifted.bed"/>
            <param name="mask" value="true"/>
            <conditional name="genome">
                <param name="source" value="history"/>
                <param name="fasta" value="chr2_subset.fa"/>
            </conditional>
            <output name="html_file">
                <assert_contents>
                    <has_text text="CTCF_peaks_shifted_bed_motif - Homer Known Motif Enrichment Results"/>
                    <has_text text="Total Target Sequences = 34"/>
                    <has_text text="CTCF(Zf)/CD4+-CTCF-ChIP-Seq(Barski_et_al.)/Homer"/>
                </assert_contents>
            </output>
            <output name="html_homer_file">
                <assert_contents>
                    <has_text text="CTCF_peaks_shifted_bed_motif/ - Homer de novo Motif Results"/>
                    <has_text text="Total target sequences = 34"/>
                    <has_text_matching expression="CTCF(Zf)|CTCF/MA|BORIS|CTCFL"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="CTCF_peaks_shifted.bed"/>
            <conditional name="genome">
                <param name="source" value="history"/>
                <param name="fasta" value="chr2_subset.fa"/>
            </conditional>
            <section name="motif_options">
                <param name="mset" value="plants"/>
            </section>
            <param name="nomotif" value="true"/>
            <output name="html_file">
                <assert_contents>
                    <has_text text="CTCF_peaks_shifted_bed_motif - Homer Known Motif Enrichment Results"/>
                    <has_text text="Total Target Sequences = 40"/>
                    <has_text text="RAP26"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

    This is a wrapper for findMotifsGenome.pl from HOMER but not all options are included.

    Program will find de novo and known motifs in regions in the genome.

Usage::

    findMotifsGenome.pl <pos file> <genome> <output directory> [additional options]

Example::

    findMotifsGenome.pl peaks.txt mm8r peakAnalysis -size 200 -len 8

Possible Genomes::

                -- or --
        Custom: provide the path to genome FASTA files (directory or single file)
                Heads up: will create the directory "preparsed/" in same location.

Basic options::

        -mask (mask repeats/lower case sequence, can also add 'r' to genome, i.e. mm9r)
        -bg <background position file> (genomic positions to be used as background, default=automatic)
                removes background positions overlapping with target positions unless -keepOverlappingBg is used
                -chopify (chop up large background regions to the avg size of target regions)
        -len <#>[,<#>,<#>...] (motif length, default=8,10,12) [NOTE: values greater 12 may cause the program
                to run out of memory - in these cases decrease the number of sequences analyzed (-N),
                or try analyzing shorter sequence regions (i.e. -size 100)]
        -size <#> (fragment size to use for motif finding, default=200)
                -size <#,#> (i.e. -size -100,50 will get sequences from -100 to +50 relative from center)
                -size given (uses the exact regions you give it)
        -S <#> (Number of motifs to optimize, default: 25)
        -mis <#> (global optimization: searches for strings with # mismatches, default: 2)
        -norevopp (don't search reverse strand for motifs)
        -nomotif (don't search for de novo motif enrichment)
        -rna (output RNA motif logos and compare to RNA motif database, automatically sets -norevopp)

Scanning sequence for motifs::

        -find <motif file> (This will cause the program to only scan for motifs)

Known Motif Options/Visualization::

        -mset <vertebrates|insects|worms|plants|yeast|all> (check against motif collects, default: auto)
        -basic (just visualize de novo motifs, don't check similarity with known motifs)
        -bits (scale sequence logos by information content, default: doesn't scale)
        -nocheck (don't search for de novo vs. known motif similarity)
        -mcheck <motif file> (known motifs to check against de novo motifs,
        -float (allow adjustment of the degeneracy threshold for known motifs to improve p-value[dangerous])
        -noknown (don't search for known motif enrichment, default: -known)
        -mknown <motif file> (known motifs to check for enrichment,
        -nofacts (omit humor)
        -seqlogo (use weblogo/seqlogo/ghostscript to generate logos, default uses SVG now)

Sequence normalization options::

        -gc (use GC% for sequence content normalization, now the default)
        -cpg (use CpG% instead of GC% for sequence content normalization)
        -noweight (no CG correction)
        Also -nlen <#>, -olen <#>, see homer2 section below.

Advanced options::

        -h (use hypergeometric for p-values, binomial is default)
        -N <#> (Number of sequences to use for motif finding, default=max(50k, 2x input)
        -local <#> (use local background, # of equal size regions around peaks to use i.e. 2)
        -redundant <#> (Remove redundant sequences matching greater than # percent, i.e. -redundant 0.5)
        -maxN <#> (maximum percentage of N's in sequence to consider for motif finding, default: 0.7)
        -maskMotif <motif file1> [motif file 2]... (motifs to mask before motif finding)
        -opt <motif file1> [motif file 2]... (motifs to optimize or change length of)
        -rand (randomize target and background sequences labels)
        -ref <peak file> (use file for target and background - first argument is list of peak ids for targets)
        -oligo (perform analysis of individual oligo enrichment)
        -dumpFasta (Dump fasta files for target and background sequences for use with other programs)
        -preparse (force new background files to be created)
        -preparsedDir <directory> (location to search for preparsed file and/or place new files)
        -keepFiles (keep temporary files)
        -fdr <#> (Calculate empirical FDR for de novo discovery #=number of randomizations)

homer2 specific options::

        -homer2 (use homer2 instead of original homer, default)
        -nlen <#> (length of lower-order oligos to normalize in background, default: -nlen 3)
                -nmax <#> (Max normalization iterations, default: 160)
                -neutral (weight sequences to neutral frequencies, i.e. 25%, 6.25%, etc.)
        -olen <#> (lower-order oligo normalization for oligo table, use if -nlen isn't working well)
        -p <#> (Number of processors to use, default: 1)
        -e <#> (Maximum expected motif instance per bp in random sequence, default: 0.01)
        -cache <#> (size in MB for statistics cache, default: 500)
        -quickMask (skip full masking after finding motifs, similar to original homer)
        -minlp <#> (stop looking for motifs when seed logp score gets above #, default: -10)

Original homer specific options::

        -homer1 (to force the use of the original homer)
        -depth [low|med|high|allnight] (time spent on local optimization default: med)


    ]]></help>
    <expand macro="citation"/>
</tool>