# HG changeset patch # User rmarenco # Date 1475262864 14400 # Node ID c02720d1afee66a6a3d53b011e462c54cbc0d149 # Parent 3233451a3bd6e188873b6b7d03f4f9210ff1e3e2 planemo upload for repository https://github.com/goeckslab/hub-archive-creator commit 1adbf397de1fc7af4d91e026093d7fff983e21cf diff -r 3233451a3bd6 -r c02720d1afee Bam.py --- a/Bam.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Bam.py Fri Sep 30 15:14:24 2016 -0400 @@ -32,12 +32,11 @@ self.priority = self.data_bam["order_index"] self.index_bam = self.data_bam["index"] - # TODO: Think about how to avoir repetition of the color treatment + # TODO: Think about how to avoid repetition of the color treatment self.track_color = self.data_bam["track_color"] - logging.debug("Color of bam: {0}".format(self.track_color)) - - #print "Creating TrackHub BAM from (falsePath: %s; name: %s)" % ( self.input_bam_false_path, self.name_bam) + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = self.data_bam["group_name"] # First: Add the bam file # Second: Add the bam index file, in the same folder (https://genome.ucsc.edu/goldenpath/help/bam.html) @@ -55,7 +54,9 @@ track_name=self.name_bam, long_label=self.name_bam, track_type='bam', visibility='pack', priority=self.priority, track_file=bam_index_file_path, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name + ) # # dataURL = "tracks/%s" % self.name_bam # diff -r 3233451a3bd6 -r c02720d1afee Bam.pyc Binary file Bam.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Bed.py --- a/Bed.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Bed.py Fri Sep 30 15:14:24 2016 -0400 @@ -24,6 +24,9 @@ self.name_bed_generic = self.data_bed_generic["name"] self.priority = self.data_bed_generic["order_index"] self.track_color = self.data_bed_generic["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = self.data_bed_generic["group_name"] + # Sort processing subtools.sort(self.inputBedGeneric, self.sortedBedFile.name) @@ -44,7 +47,8 @@ long_label=self.name_bed_generic, track_type='bigBed', visibility='dense', priority=self.priority, track_file=myBigBedFilePath, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) # dataURL = "tracks/%s" % trackName # diff -r 3233451a3bd6 -r c02720d1afee Bed.pyc Binary file Bed.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee BedSimpleRepeats.py --- a/BedSimpleRepeats.py Sun Sep 25 11:25:38 2016 -0400 +++ b/BedSimpleRepeats.py Fri Sep 30 15:14:24 2016 -0400 @@ -18,6 +18,8 @@ self.name_bed_simple_repeats = data_bed_simple_repeats["name"] self.priority = data_bed_simple_repeats["order_index"] self.track_color = data_bed_simple_repeats["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = data_bed_simple_repeats["group_name"] sortedBedFile = tempfile.NamedTemporaryFile(suffix=".sortedBed") @@ -44,7 +46,8 @@ long_label=self.name_bed_simple_repeats, track_type='bigBed 4 +', visibility='dense', priority=self.priority, track_file=myBigBedFilePath, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) # dataURL = "tracks/%s" % trackName # diff -r 3233451a3bd6 -r c02720d1afee BedSimpleRepeats.pyc Binary file BedSimpleRepeats.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee BigWig.py --- a/BigWig.py Sun Sep 25 11:25:38 2016 -0400 +++ b/BigWig.py Fri Sep 30 15:14:24 2016 -0400 @@ -19,6 +19,8 @@ self.name_bigwig = data_bigwig["name"] self.priority = data_bigwig["order_index"] self.track_color = data_bigwig["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = data_bigwig["group_name"] #print "Creating TrackHub BigWig from (falsePath: %s; name: %s)" % ( self.input_bigwig_path, self.name_bigwig ) @@ -34,7 +36,8 @@ track_type='bigWig', visibility='full', priority=self.priority, track_file=myBigWigFilePath, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) # dataURL = "tracks/%s" % trackName # diff -r 3233451a3bd6 -r c02720d1afee BigWig.pyc Binary file BigWig.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Datatype.py --- a/Datatype.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Datatype.py Fri Sep 30 15:14:24 2016 -0400 @@ -76,7 +76,7 @@ file_path=None, track_name=None, long_label=None, thick_draw_item='off', short_label=None, track_type=None, visibility=None, priority=None, - track_file=None, track_color='#000000'): + track_file=None, track_color='#000000', group_name="Default"): # TODO: Remove the hardcoded "tracks" by the value used as variable from myTrackFolderPath data_url = "tracks/%s" % file_path @@ -104,7 +104,8 @@ visibility=visibility, thickDrawItem=thick_draw_item, priority=priority, - track_color=rgb_ucsc + track_color=rgb_ucsc, + group_name=group_name ) # Return the Bam Track Object diff -r 3233451a3bd6 -r c02720d1afee Datatype.pyc Binary file Datatype.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Gff3.py --- a/Gff3.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Gff3.py Fri Sep 30 15:14:24 2016 -0400 @@ -20,6 +20,8 @@ self.name_gff3 = data_gff3["name"] self.priority = data_gff3["order_index"] self.track_color = data_gff3["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = data_gff3["group_name"] # TODO: See if we need these temporary files as part of the generated files unsorted_genePred_file = tempfile.NamedTemporaryFile(bufsize=0, suffix=".genePred") @@ -59,6 +61,7 @@ track_type='bigGenePred', visibility='dense', priority=self.priority, track_file=myBigBedFilePath, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) print("- Gff3 %s created" % self.name_gff3) diff -r 3233451a3bd6 -r c02720d1afee Gff3.pyc Binary file Gff3.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Gtf.py --- a/Gtf.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Gtf.py Fri Sep 30 15:14:24 2016 -0400 @@ -21,6 +21,8 @@ self.name_gtf = data_gtf["name"] self.priority = data_gtf["order_index"] self.track_color = data_gtf["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = data_gtf["group_name"] #print "Creating TrackHub GTF from (falsePath: %s; name: %s)" % ( self.input_gtf_false_path, self.name_gtf) @@ -61,6 +63,7 @@ long_label=self.name_gtf, track_type='bigGenePred', visibility='dense', priority=self.priority, track_file=myBigBedFilePath, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) print("- Gtf %s created" % self.name_gtf) diff -r 3233451a3bd6 -r c02720d1afee Gtf.pyc Binary file Gtf.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Psl.py --- a/Psl.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Psl.py Fri Sep 30 15:14:24 2016 -0400 @@ -17,6 +17,8 @@ self.name_psl = data_psl["name"] self.priority = data_psl["order_index"] self.track_color = data_psl["track_color"] + # TODO: Think about how to avoid repetition of the group_name everywhere + self.group_name = data_psl["group_name"] # Temporary files unsorted_bed_formatted_psl_file = tempfile.NamedTemporaryFile(suffix='.psl') @@ -52,6 +54,7 @@ track_type='bigPsl', visibility='dense', priority=self.priority, track_file=my_big_psl_file_path, - track_color=self.track_color) + track_color=self.track_color, + group_name=self.group_name) print("- BigPsl %s created" % self.name_psl) \ No newline at end of file diff -r 3233451a3bd6 -r c02720d1afee Psl.pyc Binary file Psl.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee Track.py --- a/Track.py Sun Sep 25 11:25:38 2016 -0400 +++ b/Track.py Fri Sep 30 15:14:24 2016 -0400 @@ -1,6 +1,6 @@ #!/usr/bin/python - +# TODO: Is this still useful? class Track(object): """Class to manage the track informations needed for Track Hub, in the TrackDb text file""" diff -r 3233451a3bd6 -r c02720d1afee Track.pyc Binary file Track.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee TrackDb.py --- a/TrackDb.py Sun Sep 25 11:25:38 2016 -0400 +++ b/TrackDb.py Fri Sep 30 15:14:24 2016 -0400 @@ -4,7 +4,7 @@ """docstring for TrackDb""" def __init__(self, trackName="", longLabel="", shortLabel="", trackDataURL="", trackType="", visibility="", - thickDrawItem='off', priority="0", track_color="#000000"): + thickDrawItem='off', priority="0", track_color="#000000", group_name="Default"): super(TrackDb, self).__init__() self.trackName = trackName @@ -16,3 +16,4 @@ self.thickDrawItem = thickDrawItem self.priority = priority self.track_color = track_color + self.group_name = group_name diff -r 3233451a3bd6 -r c02720d1afee TrackDb.pyc Binary file TrackDb.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee TrackHub.py --- a/TrackHub.py Sun Sep 25 11:25:38 2016 -0400 +++ b/TrackHub.py Fri Sep 30 15:14:24 2016 -0400 @@ -33,11 +33,23 @@ self.default_pos = None self.user_email = user_email + # Set containing the groups already added. Updated by addGroup() + self.groups = set() + # TODO: Modify according to the files passed in parameter + # ---- Templates ---- + # Template trackDb mylookup = TemplateLookup(directories=[os.path.join(tool_directory, 'templates/trackDb')], output_encoding='utf-8', encoding_errors='replace') self.trackDbTemplate = mylookup.get_template("layout.txt") + # Template groups + mylookup = TemplateLookup(directories=[os.path.join(self.tool_directory, 'templates/groupsTxt')], + output_encoding='utf-8', encoding_errors='replace') + self.groupsTemplate = mylookup.get_template("layout.txt") + + # ---- End Templates ---- + self.extra_files_path = extra_files_path self.outputFile = outputFile @@ -68,16 +80,43 @@ def addTrack(self, trackDbObject=None): # Create the trackDb.txt file in the specie folder, if not exists # Else append the new track + # TODO: Get this out of the function trackDbTxtFilePath = os.path.join(self.mySpecieFolderPath, 'trackDb.txt') # Append to trackDbTxtFilePath the trackDbTemplate populate with the newTrack object with open(trackDbTxtFilePath, 'a+') as trackDbFile: trackDbs = [trackDbObject] + + # TODO: The addGroup does not belong here. Move it when the group becomes more than just a label + # Add the group as well, if exists in trackDbObject + self.addGroup(trackDbObject.group_name) + htmlMakoRendered = self.trackDbTemplate.render( trackDbs=trackDbs ) trackDbFile.write(htmlMakoRendered) + def addGroup(self, group_name="Default"): + # If not already present in self.groups, add to groups.txt + # Create the trackDb.txt file in the specie folder, if not exists + # Else append the new track + # TODO: Get this out of the function + groupsTxtFilePath = os.path.join(self.mySpecieFolderPath, 'groups.txt') + + # If the group is already present, we don't need to add it + if group_name in self.groups: + return + + # Append to trackDbTxtFilePath the trackDbTemplate populate with the newTrack object + with open(groupsTxtFilePath, 'a+') as groupFile: + # Add the group as well, if exists in trackDbObject + + htmlMakoRendered = self.groupsTemplate.render( + label=group_name + ) + groupFile.write(htmlMakoRendered) + self.groups.add(group_name) + def terminate(self): # Just a test to output a simple HTML # TODO: Create a class to handle the file object @@ -182,8 +221,8 @@ # Create the file groups.txt # TODO: If not inputs for this, do no create the file - groupsTxtFilePath = os.path.join(mySpecieFolderPath, 'groups.txt') - self.__fillGroupsTxtFile__(groupsTxtFilePath) + # groupsTxtFilePath = os.path.join(mySpecieFolderPath, 'groups.txt') + # self.__fillGroupsTxtFile__(groupsTxtFilePath) # Create the folder tracks into the specie folder tracksFolderPath = os.path.join(mySpecieFolderPath, "tracks") diff -r 3233451a3bd6 -r c02720d1afee TrackHub.pyc Binary file TrackHub.pyc has changed diff -r 3233451a3bd6 -r c02720d1afee hubArchiveCreator.py --- a/hubArchiveCreator.py Sun Sep 25 11:25:38 2016 -0400 +++ b/hubArchiveCreator.py Fri Sep 30 15:14:24 2016 -0400 @@ -126,7 +126,6 @@ # We remove the spaces in ["name"] of inputs_data sanitize_name_inputs(inputs_data) - # TODO: Check here all the binaries / tools we need. Exception if missing # Create the Track Hub folder diff -r 3233451a3bd6 -r c02720d1afee hubArchiveCreator.xml --- a/hubArchiveCreator.xml Sun Sep 25 11:25:38 2016 -0400 +++ b/hubArchiveCreator.xml Fri Sep 30 15:14:24 2016 -0400 @@ -12,7 +12,8 @@ ucsc-genepredtobiggenepred ucsc-gff3togenepred ucsc-gtftogenepred - ucsc-psltobigpsl + + ucsc-twobitinfo samtools @@ -21,6 +22,7 @@ gtfToGenePred genePredToBed genePredToBigGenePred + pslToBigPsl samtools @@ -60,48 +62,59 @@ #end def - #for $i, $f in enumerate( $format ) - #set track_color = str($f.formatChoice.track_color) + #for $i_g, $g in enumerate( $group ) + #for $i, $f in enumerate( $g.format ) + + ## For each format, we have a few mandatory fields we store in a dict + #set track_color = str($f.formatChoice.track_color) + #set group_name = str($g.group_name) - #if $f.formatChoice.format_select == "bam" - --bam $f.formatChoice.BAM - #set bam_index = $f.formatChoice.BAM.metadata.bam_index - #silent $prepare_json($f.formatChoice.BAM, $i, {"index": $bam_index, - "track_color": $track_color}) - #end if - #if $f.formatChoice.format_select == "bed" - #if $f.formatChoice.bedChoice.bed_select == "bed" - --bed $f.formatChoice.bedChoice.BED - #silent $prepare_json($f.formatChoice.bedChoice.BED, $i, - {"track_color": $track_color}) - #end if - #if $f.formatChoice.bedChoice.bed_select == "bed_simple_repeats_option" - --bedSimpleRepeats $f.formatChoice.bedChoice.BED_simple_repeats - #silent $prepare_json($f.formatChoice.bedChoice.BED_simple_repeats, $i, - {"track_color": $track_color}) + #set extra_data_dict = {"track_color": $track_color, + "group_name": $group_name} + + #if $f.formatChoice.format_select == "bam" + --bam $f.formatChoice.BAM + #set bam_index = $f.formatChoice.BAM.metadata.bam_index + + ## Add Bam format specific fields + #silent extra_data_dict.update({"index": $bam_index}) + + #silent $prepare_json($f.formatChoice.BAM, $i, extra_data_dict) #end if - #end if - #if $f.formatChoice.format_select == "psl" - --psl $f.formatChoice.PSL - #silent $prepare_json($f.formatChoice.PSL, $i, - {"track_color": $track_color}) - #end if - #if $f.formatChoice.format_select == "bigwig" - --bigwig $f.formatChoice.BIGWIG - #silent $prepare_json($f.formatChoice.BIGWIG, $i, - {"track_color": $track_color}) - #end if - #if $f.formatChoice.format_select == "gff3" - --gff3 $f.formatChoice.GFF3 - #silent $prepare_json($f.formatChoice.GFF3, $i, - {"track_color": $track_color}) - #end if - #if $f.formatChoice.format_select == "gtf" - ## Add also GTF from Agustus? See https://github.com/ENCODE-DCC/kentUtils/issues/8 - --gtf $f.formatChoice.GTF - #silent $prepare_json($f.formatChoice.GTF, $i, - {"track_color": $track_color}) - #end if + #if $f.formatChoice.format_select == "bed" + #if $f.formatChoice.bedChoice.bed_select == "bed" + --bed $f.formatChoice.bedChoice.BED + #silent $prepare_json($f.formatChoice.bedChoice.BED, $i, + extra_data_dict) + #end if + #if $f.formatChoice.bedChoice.bed_select == "bed_simple_repeats_option" + --bedSimpleRepeats $f.formatChoice.bedChoice.BED_simple_repeats + #silent $prepare_json($f.formatChoice.bedChoice.BED_simple_repeats, $i, + extra_data_dict) + #end if + #end if + #if $f.formatChoice.format_select == "psl" + --psl $f.formatChoice.PSL + #silent $prepare_json($f.formatChoice.PSL, $i, + extra_data_dict) + #end if + #if $f.formatChoice.format_select == "bigwig" + --bigwig $f.formatChoice.BIGWIG + #silent $prepare_json($f.formatChoice.BIGWIG, $i, + extra_data_dict) + #end if + #if $f.formatChoice.format_select == "gff3" + --gff3 $f.formatChoice.GFF3 + #silent $prepare_json($f.formatChoice.GFF3, $i, + extra_data_dict) + #end if + #if $f.formatChoice.format_select == "gtf" + ## Add also GTF from Agustus? See https://github.com/ENCODE-DCC/kentUtils/issues/8 + --gtf $f.formatChoice.GTF + #silent $prepare_json($f.formatChoice.GTF, $i, + extra_data_dict) + #end if + #end for #end for ## We combine the fasta file dataset name with his false path in a JSON object @@ -139,126 +152,129 @@ type="data" label="Reference genome" /> - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 3233451a3bd6 -r c02720d1afee templates/groupsTxt/layout.txt --- a/templates/groupsTxt/layout.txt Sun Sep 25 11:25:38 2016 -0400 +++ b/templates/groupsTxt/layout.txt Fri Sep 30 15:14:24 2016 -0400 @@ -1,4 +1,5 @@ -name ${mapName} -label ${labelMapping} -priority ${prioriy} -defaultIsClosed ${isClosed} +name ${label.lower().replace(' ', '_')} +label ${label} +priority 2 +defaultIsClosed 0 + diff -r 3233451a3bd6 -r c02720d1afee templates/trackDb/layout.txt --- a/templates/trackDb/layout.txt Sun Sep 25 11:25:38 2016 -0400 +++ b/templates/trackDb/layout.txt Fri Sep 30 15:14:24 2016 -0400 @@ -9,5 +9,6 @@ thickDrawItem ${trackDb.thickDrawItem} priority ${trackDb.priority} color ${trackDb.track_color} + group ${trackDb.group_name.lower().replace(' ', '_')} % endfor diff -r 3233451a3bd6 -r c02720d1afee tool_dependencies.xml --- a/tool_dependencies.xml Sun Sep 25 11:25:38 2016 -0400 +++ b/tool_dependencies.xml Fri Sep 30 15:14:24 2016 -0400 @@ -105,4 +105,27 @@ The tools downloaded by this dependency definition are free for academic use. + + + + + + + + http://hgdownload.cse.ucsc.edu/admin/exe/macOSX.${architecture}/pslToBigPsl + + + http://hgdownload.cse.ucsc.edu/admin/exe/linux.${architecture}/pslToBigPsl + + + + $INSTALL_DIR/bin/pslToBigPsl + + + $INSTALL_DIR/bin + + + + The tools downloaded by this dependency definition are free for academic use. +