Mercurial > repos > kevyin > homer
changeset 4:74c1fc7bb164 draft
display tag directories with html
| author | kevyin |
|---|---|
| date | Tue, 27 Nov 2012 02:34:33 -0500 |
| parents | 4ea55669f00e |
| children | 8cfd322a5907 |
| files | README annotatePeaks.xml bed2pos.xml datatypes_conf.xml findPeaks.xml homerDatatypes.py makeTagDirectory.py makeTagDirectory.xml pos2bed.xml |
| diffstat | 9 files changed, 449 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,13 @@ +Homer wrapper for Galaxy + +Code repo: https://bitbucket.org/gvl/homer + +=========================================: +LICENSE for this wrapper: +=========================================: +Kevin Ying +Garvan Institute: http://www.garvan.org.au +GVL: https://genome.edu.au/wiki/GVL + +http://opensource.org/licenses/mit-license.php +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/annotatePeaks.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,41 @@ +<tool id="homer_annotatePeaks" name="homer_annotatePeaks" version="0.0.2"> + <requirements> + <requirement type="package">homer</requirement> + </requirements> + <description></description> + <!--<version_command></version_command>--> + <command> + annotatePeaks.pl $input_bed $genome_selector 1> $out_annotated + 2> $out_log || echo "Error running annotatePeaks." >&2 + </command> + <inputs> + <param format="tabular,bed" name="input_bed" type="data" label="Homer peak positions or BED format" /> + <param name="genome_selector" type="select" label="Genome version"> + <option value="hg19" selected="true">hg19</option> + </param> + </inputs> + <outputs> + <!--<data format="html" name="html_outfile" label="index" />--> + <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />--> + <data format="csv" name="out_annotated" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#_genome_${genome_selector}" /> + <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#_genome_${genome_selector}.log" /> + </outputs> + <tests> + <test> + <!--<param name="input_file" value="extract_genomic_dna.fa" />--> + <!--<output name="html_file" file="sample_output.html" ftype="html" />--> + </test> + </tests> + + <help> + + .. class:: infomark + + **Homer annoatePeaks** + More information on accepted formats + http://biowhat.ucsd.edu/homer/ngs/annotation.html + + + </help> +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bed2pos.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,34 @@ +<tool id="homer_bed2pos" name="homer_bed2pos" version="0.0.2"> + <requirements> + <requirement type="package">homer</requirement> + </requirements> + <description></description> + <!--<version_command></version_command>--> + <command> + bed2pos.pl $input_bed 1> $out_pos + 2> $out_log || echo "Error running bed2pos." >&2 + </command> + <inputs> + <param format="tabular,bed" name="input_bed" type="data" label="BED file" /> + </inputs> + <outputs> + <!--<data format="html" name="html_outfile" label="index" />--> + <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />--> + <data format="tabular" name="out_pos" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#" /> + <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#.log" /> + </outputs> + <tests> + <test> + <!--<param name="input_file" value="extract_genomic_dna.fa" />--> + <!--<output name="html_file" file="sample_output.html" ftype="html" />--> + </test> + </tests> + + <help> + .. class:: infomark + + **Homer bed2pos.pl** + http://biowhat.ucsd.edu/homer/ngs/miscellaneous.html + </help> +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datatypes_conf.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,9 @@ +<?xml version="1.0"?> +<datatypes> + <datatype_files> + <datatype_file name="homerDatatypes.py"/> + </datatype_files> + <registration> + <datatype extension="homerTagDirectory" type="galaxy.datatypes.homerDatatypes:HomerTagDirectory" display_in_upload="False" mimetype="text/html"/> + </registration> +</datatypes>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/findPeaks.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,52 @@ +<tool id="homer_findPeaks" name="homer_findPeaks" version="0.1.0"> + <requirements> + <requirement type="package">homer</requirement> + </requirements> + <description>Homer's peakcaller. Requires tag directories (see makeTagDirectory)</description> + <!--<version_command></version_command>--> + <command> + findPeaks $tagDir.extra_files_path $options -o $outputPeakFile + + #if $control_tagDir: + -i $control_tagDir.extra_files_path + #end if + + 2> $out_log || echo "Error running findPeaks." >&2 + </command> + <inputs> + <param format="homerTagDirectory" name="tagDir" type="data" label="tag directory" /> + <param format="homerTagDirectory" name="control_tagDir" type="data" optional="True" label="Control tag directory" /> + <param type="text" name="options" label="Extra options" value="" > + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="__sq__"/> + </mapping> + </sanitizer> + </param> + </inputs> + <outputs> + <!--<data format="html" name="html_outfile" label="index" />--> + <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />--> + <data format="txt" name="outputPeakFile" label="${tool.name} on #echo os.path.splitext(str($tagDir.name))[0]#.txt" /> + <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($tagDir.name))[0]#.log" /> + </outputs> + <tests> + <test> + <!--<param name="input_file" value="extract_genomic_dna.fa" />--> + <!--<output name="html_file" file="sample_output.html" ftype="html" />--> + </test> + </tests> + + <help> + + .. class:: infomark + + **Homer findPeaks** + http://biowhat.ucsd.edu/homer/ngs/peaks.html + + </help> +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/homerDatatypes.py Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,122 @@ +""" +homer composite datatypes +NOTE: makeTagDirectory doesn't actually use this!!!! It uses html as the format + I've never got it to properly display the contents of the datatype for after + clicking the "eye" icon, so using html instead + +Use at your peril +Kevin Ying +for the homer wrapper + +Dec 2012 +""" + +import logging, os, sys, time, tempfile, shutil, string, glob +import data +from galaxy import util +from cgi import escape +import urllib, binascii +from galaxy.web import url_for +from galaxy.datatypes import metadata +from galaxy.datatypes.metadata import MetadataElement +from galaxy.datatypes.data import Text +from galaxy.datatypes.tabular import Tabular +from galaxy.datatypes.images import Html +from galaxy.datatypes.interval import Interval +from galaxy.util.hash_util import * + +gal_Log = logging.getLogger(__name__) +verbose = False + +class HomerTagDirectory(Html): + """ + base class to use for homer tag directory datatypes + composite datatype elements + stored in extra files path + """ + + #MetadataElement( name="base_name", desc="base name for all transformed versions of this genetic dataset", default='HomerTagDirectory', + #readonly=True, set_in_upload=False) + + composite_type = 'auto_primary_file' + #allow_datatype_change = False + file_ext = 'homerTagDirectory' + + def __init__(self, **kwd): + Html.__init__(self, **kwd) + self.add_composite_file('tagInfo.txt', description="tagInfo") + self.add_composite_file('tagAutocorrelation.txt', description="tagAutocorrelation") + self.add_composite_file('tagCountDistribution.txt', description="tagCountDistribution") + self.add_composite_file('tagLengthDistribution.txt', description="tagLengthDistribution") + + def generate_primary_file(self, dataset=None): + rval = ['<html><head><title>Homer Tag Directory Galaxy Composite Dataset </title></head><p/>'] + rval.append('<div>This composite dataset is composed of the following files:<p/><ul>') + for composite_name, composite_file in self.get_composite_files( dataset = dataset ).iteritems(): + fn = composite_name + opt_text = '' + if composite_file.optional: + opt_text = ' (optional)' + if composite_file.get('description'): + rval.append( '<li><a href="%s" type="application/binary">%s (%s)</a>%s</li>' % ( fn, fn, composite_file.get('description'), opt_text ) ) + else: + rval.append( '<li><a href="%s" type="application/binary">%s</a>%s</li>' % ( fn, fn, opt_text ) ) + rval.append( '</ul></div></html>' ) + return "\n".join( rval ) + + + def regenerate_primary_file(self,dataset): + """ + cannot do this until we are setting metadata + """ + #bn = dataset.metadata.base_name + efp = dataset.extra_files_path + flist = os.listdir(efp) + rval = ['<html><head><title>Files for Composite Dataset %s</title></head><body><p/>Composite %s contains:<p/><ul>' % (dataset.name,dataset.name)] + for i,fname in enumerate(flist): + sfname = os.path.split(fname)[-1] + f,e = os.path.splitext(fname) + rval.append( '<li><a href="%s">%s</a></li>' % ( sfname, sfname) ) + rval.append( '</ul></body></html>' ) + f = file(dataset.file_name,'w') + f.write("\n".join( rval )) + f.write('\n') + f.close() + + def get_mime(self): + """Returns the mime type of the datatype""" + return 'text/html' + + def set_meta( self, dataset, **kwd ): + + """ + for homer maketagdirectory eg + + """ + Html.set_meta( self, dataset, **kwd ) + if kwd.get('overwrite') == False: + if verbose: + gal_Log.debug('@@@ HomerTagDirectory set_meta called with overwrite = False') + return True + try: + efp = dataset.extra_files_path + except: + if verbose: + gal_Log.debug('@@@ HomerTagDirectory set_meta failed %s - dataset %s has no efp ?' % (sys.exc_info()[0], dataset.name)) + return False + try: + flist = os.listdir(efp) + except: + if verbose: gal_Log.debug('@@@ HomerTagDirectory set_meta failed %s - dataset %s has no efp ?' % (sys.exc_info()[0],dataset.name)) + return False + if len(flist) == 0: + if verbose: + gal_Log.debug('@@@ HomerTagDirectory set_meta failed - %s efp %s is empty?' % (dataset.name,efp)) + return False + self.regenerate_primary_file(dataset) + if not dataset.info: + dataset.info = 'Galaxy HomerTagDirectory datatype object' + if not dataset.blurb: + dataset.blurb = 'Composite file - Homer Galaxy toolkit' + return True +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/makeTagDirectory.py Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,94 @@ +""" + + +""" +import re +import os +import sys +import subprocess +import optparse +import shutil +import tempfile + +def getFileString(fpath, outpath): + """ + format a nice file size string + """ + size = '' + fp = os.path.join(outpath, fpath) + s = '? ?' + if os.path.isfile(fp): + n = float(os.path.getsize(fp)) + if n > 2**20: + size = ' (%1.1f MB)' % (n/2**20) + elif n > 2**10: + size = ' (%1.1f KB)' % (n/2**10) + elif n > 0: + size = ' (%d B)' % (int(n)) + s = '%s %s' % (fpath, size) + return s + +class makeTagDirectory(): + """wrapper + """ + + def __init__(self,opts=None, args=None): + self.opts = opts + self.args = args + + def run_makeTagDirectory(self): + """ + makeTagDirectory <Output Directory Name> [options] <alignment file1> [alignment file 2] + + """ + if self.opts.format != "bam": + cl = [self.opts.executable] + args + ["-format" , self.opts.format] + else: + cl = [self.opts.executable] + args + print cl + p = subprocess.Popen(cl) + retval = p.wait() + + + html = self.gen_html(args[0]) + #html = self.gen_html() + return html,retval + + def gen_html(self, dr=os.getcwd()): + flist = os.listdir(dr) + print flist + """ add a list of all files in the tagdirectory + """ + res = ['<div class="module"><h2>Files created by makeTagDirectory</h2><table cellspacing="2" cellpadding="2">\n'] + + flist.sort() + for i,f in enumerate(flist): + if not(os.path.isdir(f)): + fn = os.path.split(f)[-1] + res.append('<tr><td><a href="%s">%s</a></td></tr>\n' % (fn,getFileString(fn, dr))) + + res.append('</table>\n') + + return res + +if __name__ == '__main__': + op = optparse.OptionParser() + op.add_option('-e', '--executable', default='makeTagDirectory') + op.add_option('-o', '--htmloutput', default=None) + op.add_option('-f', '--format', default="sam") + opts, args = op.parse_args() + #assert os.path.isfile(opts.executable),'## makeTagDirectory.py error - cannot find executable %s' % opts.executable + + #if not os.path.exists(opts.outputdir): + #os.makedirs(opts.outputdir) + f = makeTagDirectory(opts, args) + + html,retval = f.run_makeTagDirectory() + f = open(opts.htmloutput, 'w') + f.write(''.join(html)) + f.close() + if retval <> 0: + print >> sys.stderr, serr # indicate failure + + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/makeTagDirectory.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,50 @@ +<tool id="homer_makeTagDirectory" name="homer_makeTagDirectory" version="1.0.0"> + <requirements> + <requirement type="package" >homer</requirement> + </requirements> + <description>Simple wrapper for makeTagDirectory. Used by findPeaks</description> + <!--<version_command></version_command>--> + <command interpreter="python">makeTagDirectory.py ${tagDir.files_path} + #for $alignF in $alignmentFiles + $alignF.file -f $alignF.file.ext + #end for + -o $tagDir + 2> $out_log || echo "Error running homer_makeTagDirectory." >&2 + + </command> + <inputs> + <param name="title" label="Name for the output tag directory" type="text" default="Homer TagDirectory" /> + <repeat name="alignmentFiles" title="Alignment Files"> + <param name="file" label="Add file" type="data" format="sam,bed" /> + </repeat> + </inputs> + <outputs> + <!--<data format="homerTagDirectory" name="tagDir" label="${title} tag directory" />--> + <data format="html" name="tagDir" label="${title} tag directory" /> + <data format="txt" name="out_log" label="${title}.log" /> + <!--<data format="html" name="html_outfile" label="index" />--> + <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />--> + </outputs> + + + <tests> + <!--<test>--> + <!--<param name="input_file" value="extract_genomic_dna.fa" />--> + <!--<output name="html_file" file="sample_output.html" ftype="html" />--> + <!--</test>--> + </tests> + + <help> + + .. class:: infomark + + After the job finishes, save the zip file, unzip and open "index.html" + + The actual meme-chip command is displayed under "Command line summary" + + Defaults: + http://meme.nbcr.net/meme/doc/meme-chip.html + + </help> +</tool> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pos2bed.xml Tue Nov 27 02:34:33 2012 -0500 @@ -0,0 +1,34 @@ +<tool id="homer_pos2bed" name="homer_pos2bed" version="0.0.2"> + <requirements> + <requirement type="package">homer</requirement> + </requirements> + <description></description> + <!--<version_command></version_command>--> + <command> + pos2bed.pl $input_peak 1> $out_bed + 2> $out_log || echo "Error running pos2bed." >&2 + </command> + <inputs> + <param format="tabular" name="input_peak" type="data" label="Homer peak positions" /> + </inputs> + <outputs> + <!--<data format="html" name="html_outfile" label="index" />--> + <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />--> + <data format="bed" name="out_bed" label="${tool.name} on #echo os.path.splitext(str($input_peak.name))[0]#.bed" /> + <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($input_peak.name))[0]#.log" /> + </outputs> + <tests> + <test> + <!--<param name="input_file" value="extract_genomic_dna.fa" />--> + <!--<output name="html_file" file="sample_output.html" ftype="html" />--> + </test> + </tests> + + <help> + .. class:: infomark + + **Homer pos2bed.pl** + http://biowhat.ucsd.edu/homer/ngs/miscellaneous.html + </help> +</tool> +