Mercurial > repos > fubar > jbrowse2
changeset 13:1d86925dbb4c draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/jbrowse2 commit 873a12803692b0a84814a6dc08331d772d0e5492-dirty
| author | fubar |
|---|---|
| date | Mon, 22 Jan 2024 11:52:19 +0000 |
| parents | 247e17ce504b |
| children | 7c2e28e144f3 |
| files | abjbrowse2.py abjbrowse2.xml jbrowse2.py macros.xml |
| diffstat | 4 files changed, 2398 insertions(+), 5 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/abjbrowse2.py Mon Jan 22 11:52:19 2024 +0000 @@ -0,0 +1,1097 @@ +#!/usr/bin/env python +import argparse +import binascii +import datetime +import hashlib +import json +import logging +import os +import re +import shutil +import struct +import subprocess +import tempfile +import xml.etree.ElementTree as ET +from collections import defaultdict + +logging.basicConfig(level=logging.INFO) +log = logging.getLogger('jbrowse') +TODAY = datetime.datetime.now().strftime("%Y-%m-%d") +GALAXY_INFRASTRUCTURE_URL = None + + +class ColorScaling(object): + + COLOR_FUNCTION_TEMPLATE = """ + function(feature, variableName, glyphObject, track) {{ + var score = {score}; + {opacity} + return 'rgba({red}, {green}, {blue}, ' + opacity + ')'; + }} + """ + + COLOR_FUNCTION_TEMPLATE_QUAL = r""" + function(feature, variableName, glyphObject, track) {{ + var search_up = function self(sf, attr){{ + if(sf.get(attr) !== undefined){{ + return sf.get(attr); + }} + if(sf.parent() === undefined) {{ + return; + }}else{{ + return self(sf.parent(), attr); + }} + }}; + + var search_down = function self(sf, attr){{ + if(sf.get(attr) !== undefined){{ + return sf.get(attr); + }} + if(sf.children() === undefined) {{ + return; + }}else{{ + var kids = sf.children(); + for(var child_idx in kids){{ + var x = self(kids[child_idx], attr); + if(x !== undefined){{ + return x; + }} + }} + return; + }} + }}; + + var color = ({user_spec_color} || search_up(feature, 'color') || search_down(feature, 'color') || {auto_gen_color}); + var score = (search_up(feature, 'score') || search_down(feature, 'score')); + {opacity} + if(score === undefined){{ opacity = 1; }} + var result = /^#?([a-f\d]{{2}})([a-f\d]{{2}})([a-f\d]{{2}})$/i.exec(color); + var red = parseInt(result[1], 16); + var green = parseInt(result[2], 16); + var blue = parseInt(result[3], 16); + if(isNaN(opacity) || opacity < 0){{ opacity = 0; }} + return 'rgba(' + red + ',' + green + ',' + blue + ',' + opacity + ')'; + }} + """ + + OPACITY_MATH = { + 'linear': """ + var opacity = (score - ({min})) / (({max}) - ({min})); + """, + 'logarithmic': """ + var opacity = Math.log10(score - ({min})) / Math.log10(({max}) - ({min})); + """, + 'blast': """ + var opacity = 0; + if(score == 0.0) {{ + opacity = 1; + }} else {{ + opacity = (20 - Math.log10(score)) / 180; + }} + """ + } + + BREWER_COLOUR_IDX = 0 + BREWER_COLOUR_SCHEMES = [ + (166, 206, 227), + (31, 120, 180), + (178, 223, 138), + (51, 160, 44), + (251, 154, 153), + (227, 26, 28), + (253, 191, 111), + (255, 127, 0), + (202, 178, 214), + (106, 61, 154), + (255, 255, 153), + (177, 89, 40), + (228, 26, 28), + (55, 126, 184), + (77, 175, 74), + (152, 78, 163), + (255, 127, 0), + ] + + BREWER_DIVERGING_PALLETES = { + 'BrBg': ("#543005", "#003c30"), + 'PiYg': ("#8e0152", "#276419"), + 'PRGn': ("#40004b", "#00441b"), + 'PuOr': ("#7f3b08", "#2d004b"), + 'RdBu': ("#67001f", "#053061"), + 'RdGy': ("#67001f", "#1a1a1a"), + 'RdYlBu': ("#a50026", "#313695"), + 'RdYlGn': ("#a50026", "#006837"), + 'Spectral': ("#9e0142", "#5e4fa2"), + } + + def __init__(self): + self.brewer_colour_idx = 0 + + def rgb_from_hex(self, hexstr): + # http://stackoverflow.com/questions/4296249/how-do-i-convert-a-hex-triplet-to-an-rgb-tuple-and-back + return struct.unpack('BBB', binascii.unhexlify(hexstr)) + + def min_max_gff(self, gff_file): + min_val = None + max_val = None + with open(gff_file, 'r') as handle: + for line in handle: + try: + value = float(line.split('\t')[5]) + min_val = min(value, (min_val or value)) + max_val = max(value, (max_val or value)) + + if value < min_val: + min_val = value + + if value > max_val: + max_val = value + except Exception: + pass + return min_val, max_val + + def hex_from_rgb(self, r, g, b): + return '#%02x%02x%02x' % (r, g, b) + + def _get_colours(self): + r, g, b = self.BREWER_COLOUR_SCHEMES[self.brewer_colour_idx % len(self.BREWER_COLOUR_SCHEMES)] + self.brewer_colour_idx += 1 + return r, g, b + + def parse_menus(self, track): + trackConfig = {'menuTemplate': [{}, {}, {}, {}]} + + if 'menu' in track['menus']: + menu_list = [track['menus']['menu']] + if isinstance(track['menus']['menu'], list): + menu_list = track['menus']['menu'] + + for m in menu_list: + tpl = { + 'action': m['action'], + 'label': m.get('label', '{name}'), + 'iconClass': m.get('iconClass', 'dijitIconBookmark'), + } + if 'url' in m: + tpl['url'] = m['url'] + if 'content' in m: + tpl['content'] = m['content'] + if 'title' in m: + tpl['title'] = m['title'] + + trackConfig['menuTemplate'].append(tpl) + + return trackConfig + + def parse_colours(self, track, trackFormat, gff3=None): + # Wiggle tracks have a bicolor pallete + trackConfig = {'style': {}} + if trackFormat == 'wiggle': + + trackConfig['style']['pos_color'] = track['wiggle']['color_pos'] + trackConfig['style']['neg_color'] = track['wiggle']['color_neg'] + + if trackConfig['style']['pos_color'] == '__auto__': + trackConfig['style']['neg_color'] = self.hex_from_rgb(*self._get_colours()) + trackConfig['style']['pos_color'] = self.hex_from_rgb(*self._get_colours()) + + # Wiggle tracks can change colour at a specified place + bc_pivot = track['wiggle']['bicolor_pivot'] + if bc_pivot not in ('mean', 'zero'): + # The values are either one of those two strings + # or a number + bc_pivot = float(bc_pivot) + trackConfig['bicolor_pivot'] = bc_pivot + elif 'scaling' in track: + if track['scaling']['method'] == 'ignore': + if track['scaling']['scheme']['color'] != '__auto__': + trackConfig['style']['color'] = track['scaling']['scheme']['color'] + else: + trackConfig['style']['color'] = self.hex_from_rgb(*self._get_colours()) + else: + # Scored method + algo = track['scaling']['algo'] + # linear, logarithmic, blast + scales = track['scaling']['scales'] + # type __auto__, manual (min, max) + scheme = track['scaling']['scheme'] + # scheme -> (type (opacity), color) + # ================================== + # GENE CALLS OR BLAST + # ================================== + if trackFormat == 'blast': + red, green, blue = self._get_colours() + color_function = self.COLOR_FUNCTION_TEMPLATE.format(**{ + 'score': "feature._parent.get('score')", + 'opacity': self.OPACITY_MATH['blast'], + 'red': red, + 'green': green, + 'blue': blue, + }) + trackConfig['style']['color'] = color_function.replace('\n', '') + elif trackFormat == 'gene_calls': + # Default values, based on GFF3 spec + min_val = 0 + max_val = 1000 + # Get min/max and build a scoring function since JBrowse doesn't + if scales['type'] == 'automatic' or scales['type'] == '__auto__': + min_val, max_val = self.min_max_gff(gff3) + else: + min_val = scales.get('min', 0) + max_val = scales.get('max', 1000) + + if scheme['color'] == '__auto__': + user_color = 'undefined' + auto_color = "'%s'" % self.hex_from_rgb(*self._get_colours()) + elif scheme['color'].startswith('#'): + user_color = "'%s'" % self.hex_from_rgb(*self.rgb_from_hex(scheme['color'][1:])) + auto_color = 'undefined' + else: + user_color = 'undefined' + auto_color = "'%s'" % self.hex_from_rgb(*self._get_colours()) + + color_function = self.COLOR_FUNCTION_TEMPLATE_QUAL.format(**{ + 'opacity': self.OPACITY_MATH[algo].format(**{'max': max_val, 'min': min_val}), + 'user_spec_color': user_color, + 'auto_gen_color': auto_color, + }) + + trackConfig['style']['color'] = color_function.replace('\n', '') + return trackConfig + + +def etree_to_dict(t): + if t is None: + return {} + + d = {t.tag: {} if t.attrib else None} + children = list(t) + if children: + dd = defaultdict(list) + for dc in map(etree_to_dict, children): + for k, v in dc.items(): + dd[k].append(v) + d = {t.tag: {k: v[0] if len(v) == 1 else v for k, v in dd.items()}} + if t.attrib: + d[t.tag].update(('@' + k, v) for k, v in t.attrib.items()) + if t.text: + text = t.text.strip() + if children or t.attrib: + if text: + d[t.tag]['#text'] = text + else: + d[t.tag] = text + return d + + +# score comes from feature._parent.get('score') or feature.get('score') + +INSTALLED_TO = os.path.dirname(os.path.realpath(__file__)) + + +def metadata_from_node(node): + metadata = {} + try: + if len(node.findall('dataset')) != 1: + # exit early + return metadata + except Exception: + return {} + + for (key, value) in node.findall('dataset')[0].attrib.items(): + metadata['dataset_%s' % key] = value + + for (key, value) in node.findall('history')[0].attrib.items(): + metadata['history_%s' % key] = value + + for (key, value) in node.findall('metadata')[0].attrib.items(): + metadata['metadata_%s' % key] = value + + for (key, value) in node.findall('tool')[0].attrib.items(): + metadata['tool_%s' % key] = value + + # Additional Mappings applied: + metadata['dataset_edam_format'] = '<a target="_blank" href="http://edamontology.org/{0}">{1}</a>'.format(metadata['dataset_edam_format'], metadata['dataset_file_ext']) + metadata['history_user_email'] = '<a href="mailto:{0}">{0}</a>'.format(metadata['history_user_email']) + metadata['history_display_name'] = '<a target="_blank" href="{galaxy}/history/view/{encoded_hist_id}">{hist_name}</a>'.format( + galaxy=GALAXY_INFRASTRUCTURE_URL, + encoded_hist_id=metadata['history_id'], + hist_name=metadata['history_display_name'] + ) + metadata['tool_tool'] = '<a target="_blank" href="{galaxy}/datasets/{encoded_id}/show_params">{tool_id}</a>'.format( + galaxy=GALAXY_INFRASTRUCTURE_URL, + encoded_id=metadata['dataset_id'], + tool_id=metadata['tool_tool_id'], + # tool_version=metadata['tool_tool_version'], + ) + return metadata + + +class JbrowseConnector(object): + + def __init__(self, jbrowse, outdir, genomes): + self.cs = ColorScaling() + self.jbrowse = jbrowse + self.outdir = outdir + self.genome_paths = genomes + self.tracksToIndex = [] + + # This is the id of the current assembly + self.assembly_ids = {} + self.current_assembly_id = [] + + # If upgrading, look at the existing data + self.check_existing(self.outdir) + + self.clone_jbrowse(self.jbrowse, self.outdir) + + self.process_genomes() + + def subprocess_check_call(self, command, output=None): + if output: + log.debug('cd %s && %s > %s', self.outdir, ' '.join(command), output) + subprocess.check_call(command, cwd=self.outdir, stdout=output) + else: + log.debug('cd %s && %s', self.outdir, ' '.join(command)) + subprocess.check_call(command, cwd=self.outdir) + + def subprocess_popen(self, command): + log.debug('cd %s && %s', self.outdir, command) + p = subprocess.Popen(command, shell=True, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + output, err = p.communicate() + retcode = p.returncode + if retcode != 0: + log.error('cd %s && %s', self.outdir, command) + log.error(output) + log.error(err) + raise RuntimeError("Command failed with exit code %s" % (retcode)) + + def subprocess_check_output(self, command): + log.debug('cd %s && %s', self.outdir, ' '.join(command)) + return subprocess.check_output(command, cwd=self.outdir) + + def symlink_or_copy(self, src, dest): + if 'GALAXY_JBROWSE_SYMLINKS' in os.environ and bool(os.environ['GALAXY_JBROWSE_SYMLINKS']): + cmd = ['ln', '-s', src, dest] + else: + cmd = ['cp', src, dest] + + return self.subprocess_check_call(cmd) + + def symlink_or_copy_load_action(self): + if 'GALAXY_JBROWSE_SYMLINKS' in os.environ and bool(os.environ['GALAXY_JBROWSE_SYMLINKS']): + return 'symlink' + else: + return 'copy' + + def check_existing(self, destination): + existing = os.path.join(destination, 'data', "config.json") + if os.path.exists(existing): + with open(existing, 'r') as existing_conf: + conf = json.load(existing_conf) + if 'assemblies' in conf: + for assembly in conf['assemblies']: + if 'name' in assembly: + self.assembly_ids[assembly['name']] = None + + def process_genomes(self): + for genome_node in self.genome_paths: + # We only expect one input genome per run. This for loop is just + # easier to write than the alternative / catches any possible + # issues. + self.add_assembly(genome_node['path'], genome_node['label']) + + def add_assembly(self, path, label, default=True): + # Find a non-existing filename for the new genome + # (to avoid colision when upgrading an existing instance) + rel_seq_path = os.path.join('data', 'assembly') + seq_path = os.path.join(self.outdir, rel_seq_path) + fn_try = 1 + while (os.path.exists(seq_path + '.fasta') or os.path.exists(seq_path + '.fasta.gz') + or os.path.exists(seq_path + '.fasta.gz.fai') or os.path.exists(seq_path + '.fasta.gz.gzi')): + rel_seq_path = os.path.join('data', 'assembly%s' % fn_try) + seq_path = os.path.join(self.outdir, rel_seq_path) + fn_try += 1 + + # Find a non-existing label for the new genome + # (to avoid colision when upgrading an existing instance) + lab_try = 1 + uniq_label = label + while uniq_label in self.assembly_ids: + uniq_label = label + str(lab_try) + lab_try += 1 + + # Find a default scaffold to display + # TODO this may not be necessary in the future, see https://github.com/GMOD/jbrowse-components/issues/2708 + with open(path, 'r') as fa_handle: + fa_header = fa_handle.readline()[1:].strip().split(' ')[0] + + self.assembly_ids[uniq_label] = fa_header + if default: + self.current_assembly_id = uniq_label + + copied_genome = seq_path + '.fasta' + shutil.copy(path, copied_genome) + + # Compress with bgzip + cmd = ['bgzip', copied_genome] + self.subprocess_check_call(cmd) + + # FAI Index + cmd = ['samtools', 'faidx', copied_genome + '.gz'] + self.subprocess_check_call(cmd) + + self.subprocess_check_call([ + 'jbrowse', 'add-assembly', + '--load', 'inPlace', + '--name', uniq_label, + '--type', 'bgzipFasta', + '--target', os.path.join(self.outdir, 'data'), + '--skipCheck', + rel_seq_path + '.fasta.gz']) + + return uniq_label + + def text_index(self): + # Index tracks + args = [ + 'jbrowse', 'text-index', + '--target', os.path.join(self.outdir, 'data'), + '--assemblies', self.current_assembly_id, + ] + + tracks = ','.join(self.tracksToIndex) + if tracks: + args += ['--tracks', tracks] + + self.subprocess_check_call(args) + + def _blastxml_to_gff3(self, xml, min_gap=10): + gff3_unrebased = tempfile.NamedTemporaryFile(delete=False) + cmd = ['python', os.path.join(INSTALLED_TO, 'blastxml_to_gapped_gff3.py'), + '--trim', '--trim_end', '--include_seq', '--min_gap', str(min_gap), xml] + log.debug('cd %s && %s > %s', self.outdir, ' '.join(cmd), gff3_unrebased.name) + subprocess.check_call(cmd, cwd=self.outdir, stdout=gff3_unrebased) + gff3_unrebased.close() + return gff3_unrebased.name + + def _prepare_track_style(self, xml_conf): + + style_data = { + "type": "LinearBasicDisplay" + } + + if 'display' in xml_conf['style']: + style_data['type'] = xml_conf['style']['display'] + del xml_conf['style']['display'] + + style_data['displayId'] = "%s_%s" % (xml_conf['label'], style_data['type']) + + style_data.update(xml_conf['style']) + + return {'displays': [style_data]} + + def add_blastxml(self, data, trackData, blastOpts, **kwargs): + gff3 = self._blastxml_to_gff3(data, min_gap=blastOpts['min_gap']) + + if 'parent' in blastOpts and blastOpts['parent'] != 'None': + gff3_rebased = tempfile.NamedTemporaryFile(delete=False) + cmd = ['python', os.path.join(INSTALLED_TO, 'gff3_rebase.py')] + if blastOpts.get('protein', 'false') == 'true': + cmd.append('--protein2dna') + cmd.extend([os.path.realpath(blastOpts['parent']), gff3]) + log.debug('cd %s && %s > %s', self.outdir, ' '.join(cmd), gff3_rebased.name) + subprocess.check_call(cmd, cwd=self.outdir, stdout=gff3_rebased) + gff3_rebased.close() + + # Replace original gff3 file + shutil.copy(gff3_rebased.name, gff3) + os.unlink(gff3_rebased.name) + + rel_dest = os.path.join('data', trackData['label'] + '.gff') + dest = os.path.join(self.outdir, rel_dest) + + self._sort_gff(gff3, dest) + os.unlink(gff3) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest + '.gz', config=style_json) + + def add_bigwig(self, data, trackData, wiggleOpts, **kwargs): + + rel_dest = os.path.join('data', trackData['label'] + '.bw') + dest = os.path.join(self.outdir, rel_dest) + self.symlink_or_copy(os.path.realpath(data), dest) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest, config=style_json) + + # Anything ending in "am" (Bam or Cram) + def add_xam(self, data, trackData, xamOpts, index=None, ext="bam", **kwargs): + + index_ext = "bai" + if ext == "cram": + index_ext = "crai" + + rel_dest = os.path.join('data', trackData['label'] + '.%s' % ext) + dest = os.path.join(self.outdir, rel_dest) + + self.symlink_or_copy(os.path.realpath(data), dest) + + if index is not None and os.path.exists(os.path.realpath(index)): + # xai most probably made by galaxy and stored in galaxy dirs, need to copy it to dest + self.subprocess_check_call(['cp', os.path.realpath(index), dest + '.%s' % index_ext]) + else: + # Can happen in exotic condition + # e.g. if bam imported as symlink with datatype=unsorted.bam, then datatype changed to bam + # => no index generated by galaxy, but there might be one next to the symlink target + # this trick allows to skip the bam sorting made by galaxy if already done outside + if os.path.exists(os.path.realpath(data) + '.%s' % index_ext): + self.symlink_or_copy(os.path.realpath(data) + '.%s' % index_ext, dest + '.%s' % index_ext) + else: + log.warn('Could not find a bam index (.%s file) for %s', (index_ext, data)) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest, config=style_json) + + def add_vcf(self, data, trackData, vcfOpts={}, zipped=False, **kwargs): + + if zipped: + rel_dest = os.path.join('data', trackData['label'] + '.vcf.gz') + dest = os.path.join(self.outdir, rel_dest) + shutil.copy(os.path.realpath(data), dest) + else: + rel_dest = os.path.join('data', trackData['label'] + '.vcf') + dest = os.path.join(self.outdir, rel_dest) + shutil.copy(os.path.realpath(data), dest) + + cmd = ['bgzip', dest] + self.subprocess_check_call(cmd) + cmd = ['tabix', dest + '.gz'] + self.subprocess_check_call(cmd) + + rel_dest = os.path.join('data', trackData['label'] + '.vcf.gz') + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest, config=style_json) + + def add_gff(self, data, format, trackData, gffOpts, **kwargs): + rel_dest = os.path.join('data', trackData['label'] + '.gff') + dest = os.path.join(self.outdir, rel_dest) + + self._sort_gff(data, dest) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest + '.gz', config=style_json) + + def add_bed(self, data, format, trackData, gffOpts, **kwargs): + rel_dest = os.path.join('data', trackData['label'] + '.bed') + dest = os.path.join(self.outdir, rel_dest) + + self._sort_bed(data, dest) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest + '.gz', config=style_json) + + def add_paf(self, data, trackData, pafOpts, **kwargs): + rel_dest = os.path.join('data', trackData['label'] + '.paf') + dest = os.path.join(self.outdir, rel_dest) + + self.symlink_or_copy(os.path.realpath(data), dest) + + added_assembly = self.add_assembly(pafOpts['genome'], pafOpts['genome_label'], default=False) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest, assemblies=[self.current_assembly_id, added_assembly], config=style_json) + + def add_hic(self, data, trackData, hicOpts, **kwargs): + rel_dest = os.path.join('data', trackData['label'] + '.hic') + dest = os.path.join(self.outdir, rel_dest) + + self.symlink_or_copy(os.path.realpath(data), dest) + + style_json = self._prepare_track_style(trackData) + + self._add_track(trackData['label'], trackData['key'], trackData['category'], rel_dest, config=style_json) + + def add_sparql(self, url, query, query_refnames, trackData): + + json_track_data = { + "type": "FeatureTrack", + "trackId": id, + "name": trackData['label'], + "adapter": { + "type": "SPARQLAdapter", + "endpoint": { + "uri": url, + "locationType": "UriLocation" + }, + "queryTemplate": query + }, + "category": [ + trackData['category'] + ], + "assemblyNames": [ + self.current_assembly_id + ] + } + + if query_refnames: + json_track_data['adapter']['refNamesQueryTemplate']: query_refnames + + self.subprocess_check_call([ + 'jbrowse', 'add-track-json', + '--target', os.path.join(self.outdir, 'data'), + json_track_data]) + + # Doesn't work as of 1.6.4, might work in the future + # self.subprocess_check_call([ + # 'jbrowse', 'add-track', + # '--trackType', 'sparql', + # '--name', trackData['label'], + # '--category', trackData['category'], + # '--target', os.path.join(self.outdir, 'data'), + # '--trackId', id, + # '--config', '{"queryTemplate": "%s"}' % query, + # url]) + + def _add_track(self, id, label, category, path, assemblies=[], config=None): + + assemblies_opt = self.current_assembly_id + if assemblies: + assemblies_opt = ','.join(assemblies) + + cmd = [ + 'jbrowse', 'add-track', + '--load', 'inPlace', + '--name', label, + '--category', category, + '--target', os.path.join(self.outdir, 'data'), + '--trackId', id, + '--assemblyNames', assemblies_opt + ] + + if config: + cmd.append('--config') + cmd.append(json.dumps(config)) + + cmd.append(path) + + self.subprocess_check_call(cmd) + + def _sort_gff(self, data, dest): + # Only index if not already done + if not os.path.exists(dest): + cmd = "gff3sort.pl --precise '%s' | grep -v \"^$\" > '%s'" % (data, dest) + self.subprocess_popen(cmd) + + self.subprocess_check_call(['bgzip', '-f', dest]) + self.subprocess_check_call(['tabix', '-f', '-p', 'gff', dest + '.gz']) + + def _sort_bed(self, data, dest): + # Only index if not already done + if not os.path.exists(dest): + cmd = ['sort', '-k1,1', '-k2,2n', data] + with open(dest, 'w') as handle: + self.subprocess_check_call(cmd, output=handle) + + self.subprocess_check_call(['bgzip', '-f', dest]) + self.subprocess_check_call(['tabix', '-f', '-p', 'bed', dest + '.gz']) + + def process_annotations(self, track): + + category = track['category'].replace('__pd__date__pd__', TODAY) + outputTrackConfig = { + 'category': category, + } + + mapped_chars = { + '>': '__gt__', + '<': '__lt__', + "'": '__sq__', + '"': '__dq__', + '[': '__ob__', + ']': '__cb__', + '{': '__oc__', + '}': '__cc__', + '@': '__at__', + '#': '__pd__', + "": '__cn__' + } + + for i, (dataset_path, dataset_ext, track_human_label, extra_metadata) in enumerate(track['trackfiles']): + # Unsanitize labels (element_identifiers are always sanitized by Galaxy) + for key, value in mapped_chars.items(): + track_human_label = track_human_label.replace(value, key) + + log.info('Processing track %s / %s (%s)', category, track_human_label, dataset_ext) + outputTrackConfig['key'] = track_human_label + # We add extra data to hash for the case of REST + SPARQL. + if 'conf' in track and 'options' in track['conf'] and 'url' in track['conf']['options']: + rest_url = track['conf']['options']['url'] + else: + rest_url = '' + + # I chose to use track['category'] instead of 'category' here. This + # is intentional. This way re-running the tool on a different date + # will not generate different hashes and make comparison of outputs + # much simpler. + hashData = [str(dataset_path), track_human_label, track['category'], rest_url, self.current_assembly_id] + hashData = '|'.join(hashData).encode('utf-8') + outputTrackConfig['label'] = hashlib.md5(hashData).hexdigest() + '_%s' % i + outputTrackConfig['metadata'] = extra_metadata + + outputTrackConfig['style'] = track['style'] + + if 'menus' in track['conf']['options']: + menus = self.cs.parse_menus(track['conf']['options']) + outputTrackConfig.update(menus) + + if dataset_ext in ('gff', 'gff3'): + self.add_gff(dataset_path, dataset_ext, outputTrackConfig, + track['conf']['options']['gff']) + elif dataset_ext == 'bed': + self.add_bed(dataset_path, dataset_ext, outputTrackConfig, + track['conf']['options']['gff']) + elif dataset_ext == 'bigwig': + self.add_bigwig(dataset_path, outputTrackConfig, + track['conf']['options']['wiggle']) + elif dataset_ext == 'bam': + real_indexes = track['conf']['options']['pileup']['bam_indices']['bam_index'] + if not isinstance(real_indexes, list): + # <bam_indices> + # <bam_index>/path/to/a.bam.bai</bam_index> + # </bam_indices> + # + # The above will result in the 'bam_index' key containing a + # string. If there are two or more indices, the container + # becomes a list. Fun! + real_indexes = [real_indexes] + + self.add_xam(dataset_path, outputTrackConfig, + track['conf']['options']['pileup'], + index=real_indexes[i], ext="bam") + elif dataset_ext == 'cram': + real_indexes = track['conf']['options']['cram']['cram_indices']['cram_index'] + if not isinstance(real_indexes, list): + # <bam_indices> + # <bam_index>/path/to/a.bam.bai</bam_index> + # </bam_indices> + # + # The above will result in the 'bam_index' key containing a + # string. If there are two or more indices, the container + # becomes a list. Fun! + real_indexes = [real_indexes] + + self.add_xam(dataset_path, outputTrackConfig, + track['conf']['options']['cram'], + index=real_indexes[i], ext="cram") + elif dataset_ext == 'blastxml': + self.add_blastxml(dataset_path, outputTrackConfig, track['conf']['options']['blast']) + elif dataset_ext == 'vcf': + self.add_vcf(dataset_path, outputTrackConfig) + elif dataset_ext == 'vcf_bgzip': + self.add_vcf(dataset_path, outputTrackConfig, zipped=True) + elif dataset_ext == 'rest': + self.add_rest(track['conf']['options']['rest']['url'], outputTrackConfig) + elif dataset_ext == 'synteny': + self.add_paf(dataset_path, outputTrackConfig, + track['conf']['options']['synteny']) + elif dataset_ext == 'hic': + self.add_hic(dataset_path, outputTrackConfig, + track['conf']['options']['hic']) + elif dataset_ext == 'sparql': + sparql_query = track['conf']['options']['sparql']['query'] + for key, value in mapped_chars.items(): + sparql_query = sparql_query.replace(value, key) + sparql_query_refnames = track['conf']['options']['sparql']['query_refnames'] + for key, value in mapped_chars.items(): + sparql_query_refnames = sparql_query_refnames.replace(value, key) + self.add_sparql(track['conf']['options']['sparql']['url'], sparql_query, sparql_query_refnames, outputTrackConfig) + else: + log.warn('Do not know how to handle %s', dataset_ext) + + # Return non-human label for use in other fields + yield outputTrackConfig['label'] + + def add_default_session(self, data): + """ + Add some default session settings: set some assemblies/tracks on/off + """ + tracks_data = [] + + # TODO using the default session for now, but check out session specs in the future https://github.com/GMOD/jbrowse-components/issues/2708 + + # We need to know the track type from the config.json generated just before + config_path = os.path.join(self.outdir, 'data', 'config.json') + track_types = {} + with open(config_path, 'r') as config_file: + config_json = json.load(config_file) + + for track_conf in config_json['tracks']: + track_types[track_conf['trackId']] = track_conf['type'] + + for on_track in data['visibility']['default_on']: + # TODO several problems with this currently + # - we are forced to copy the same kind of style config as the per track config from _prepare_track_style (not exactly the same though) + # - we get an error when refreshing the page + # - this could be solved by session specs, see https://github.com/GMOD/jbrowse-components/issues/2708 + style_data = { + "type": "LinearBasicDisplay", + "height": 100 + } + + if on_track in data['style']: + if 'display' in data['style'][on_track]: + style_data['type'] = data['style'][on_track]['display'] + del data['style'][on_track]['display'] + + style_data.update(data['style'][on_track]) + + if on_track in data['style_labels']: + # TODO fix this: it should probably go in a renderer block (SvgFeatureRenderer) but still does not work + # TODO move this to per track displays? + style_data['labels'] = data['style_labels'][on_track] + + tracks_data.append({ + "type": track_types[on_track], + "configuration": on_track, + "displays": [ + style_data + ] + }) + + # The view for the assembly we're adding + view_json = { + "type": "LinearGenomeView", + "tracks": tracks_data + } + + refName = None + if data.get('defaultLocation', ''): + loc_match = re.search(r'^(\w+):(\d+)\.+(\d+)$', data['defaultLocation']) + if loc_match: + refName = loc_match.group(1) + start = int(loc_match.group(2)) + end = int(loc_match.group(3)) + elif self.assembly_ids[self.current_assembly_id] is not None: + refName = self.assembly_ids[self.current_assembly_id] + start = 0 + end = 1000000 # Booh, hard coded! waiting for https://github.com/GMOD/jbrowse-components/issues/2708 + + if refName is not None: + # TODO displayedRegions is not just zooming to the region, it hides the rest of the chromosome + view_json['displayedRegions'] = [{ + "refName": refName, + "start": start, + "end": end, + "reversed": False, + "assemblyName": self.current_assembly_id + }] + + session_name = data.get('session_name', "New session") + if not session_name: + session_name = "New session" + + # Merge with possibly existing defaultSession (if upgrading a jbrowse instance) + session_json = {} + if 'defaultSession' in config_json: + session_json = config_json['defaultSession'] + + session_json["name"] = session_name + + if 'views' not in session_json: + session_json['views'] = [] + + session_json['views'].append(view_json) + + config_json['defaultSession'] = session_json + + with open(config_path, 'w') as config_file: + json.dump(config_json, config_file, indent=2) + + def add_general_configuration(self, data): + """ + Add some general configuration to the config.json file + """ + + config_path = os.path.join(self.outdir, 'data', 'config.json') + with open(config_path, 'r') as config_file: + config_json = json.load(config_file) + + config_data = {} + + config_data['disableAnalytics'] = data.get('analytics', 'false') == 'true' + + config_data['theme'] = { + "palette": { + "primary": { + "main": data.get('primary_color', '#0D233F') + }, + "secondary": { + "main": data.get('secondary_color', '#721E63') + }, + "tertiary": { + "main": data.get('tertiary_color', '#135560') + }, + "quaternary": { + "main": data.get('quaternary_color', '#FFB11D') + }, + }, + "typography": { + "fontSize": int(data.get('font_size', 10)) + }, + } + + config_json['configuration'].update(config_data) + + with open(config_path, 'w') as config_file: + json.dump(config_json, config_file, indent=2) + + def clone_jbrowse(self, jbrowse_dir, destination): + """Clone a JBrowse directory into a destination directory. + """ + + copytree(jbrowse_dir, destination) + + try: + shutil.rmtree(os.path.join(destination, 'test_data')) + except OSError as e: + log.error("Error: %s - %s." % (e.filename, e.strerror)) + + if not os.path.exists(os.path.join(destination, 'data')): + # It can already exist if upgrading an instance + os.makedirs(os.path.join(destination, 'data')) + log.info("makedir %s" % (os.path.join(destination, 'data'))) + + os.symlink('./data/config.json', os.path.join(destination, 'config.json')) + + +def copytree(src, dst, symlinks=False, ignore=None): + for item in os.listdir(src): + s = os.path.join(src, item) + d = os.path.join(dst, item) + if os.path.isdir(s): + shutil.copytree(s, d, symlinks, ignore) + else: + shutil.copy2(s, d) + + +def parse_style_conf(item): + if 'type' in item.attrib and item.attrib['type'] in ['boolean', 'integer']: + if item.attrib['type'] == 'boolean': + return item.text in ("yes", "true", "True") + elif item.attrib['type'] == 'integer': + return int(item.text) + else: + return item.text + + +if __name__ == '__main__': + parser = argparse.ArgumentParser(description="", epilog="") + parser.add_argument('xml', type=argparse.FileType('r'), help='Track Configuration') + + parser.add_argument('--jbrowse', help='Folder containing a jbrowse release') + parser.add_argument('--outdir', help='Output directory', default='out') + parser.add_argument('--version', '-V', action='version', version="%(prog)s 0.8.0") + args = parser.parse_args() + + tree = ET.parse(args.xml.name) + root = tree.getroot() + + # This should be done ASAP + GALAXY_INFRASTRUCTURE_URL = root.find('metadata/galaxyUrl').text + # Sometimes this comes as `localhost` without a protocol + if not GALAXY_INFRASTRUCTURE_URL.startswith('http'): + # so we'll prepend `http://` and hope for the best. Requests *should* + # be GET and not POST so it should redirect OK + GALAXY_INFRASTRUCTURE_URL = 'http://' + GALAXY_INFRASTRUCTURE_URL + + jc = JbrowseConnector( + jbrowse=args.jbrowse, + outdir=args.outdir, + genomes=[ + { + 'path': os.path.realpath(x.attrib['path']), + 'meta': metadata_from_node(x.find('metadata')), + 'label': x.attrib['label'] + } + for x in root.findall('metadata/genomes/genome') + ] + ) + + default_session_data = { + 'visibility': { + 'default_on': [], + 'default_off': [], + }, + 'style': {}, + 'style_labels': {} + } + + # TODO add metadata to tracks + for track in root.findall('tracks/track'): + track_conf = {} + track_conf['trackfiles'] = [] + + trackfiles = track.findall('files/trackFile') + if trackfiles: + for x in track.findall('files/trackFile'): + if trackfiles: + metadata = metadata_from_node(x.find('metadata')) + + track_conf['trackfiles'].append(( + os.path.realpath(x.attrib['path']), + x.attrib['ext'], + x.attrib['label'], + metadata + )) + else: + # For tracks without files (rest, sparql) + track_conf['trackfiles'].append(( + '', # N/A, no path for rest or sparql + track.attrib['format'], + track.find('options/label').text, + {} + )) + + track_conf['category'] = track.attrib['cat'] + track_conf['format'] = track.attrib['format'] + track_conf['style'] = {item.tag: parse_style_conf(item) for item in track.find('options/style')} + + track_conf['style'] = {item.tag: parse_style_conf(item) for item in track.find('options/style')} + + track_conf['style_labels'] = {item.tag: parse_style_conf(item) for item in track.find('options/style_labels')} + + track_conf['conf'] = etree_to_dict(track.find('options')) + keys = jc.process_annotations(track_conf) + + for key in keys: + default_session_data['visibility'][track.attrib.get('visibility', 'default_off')].append(key) + + default_session_data['style'][key] = track_conf['style'] # TODO do we need this anymore? + default_session_data['style_labels'][key] = track_conf['style_labels'] + + default_session_data['defaultLocation'] = root.find('metadata/general/defaultLocation').text + default_session_data['session_name'] = root.find('metadata/general/session_name').text + + general_data = { + 'analytics': root.find('metadata/general/analytics').text, + 'primary_color': root.find('metadata/general/primary_color').text, + 'secondary_color': root.find('metadata/general/secondary_color').text, + 'tertiary_color': root.find('metadata/general/tertiary_color').text, + 'quaternary_color': root.find('metadata/general/quaternary_color').text, + 'font_size': root.find('metadata/general/font_size').text, + } + + jc.add_default_session(default_session_data) + jc.add_general_configuration(general_data) + jc.text_index() +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/abjbrowse2.xml Mon Jan 22 11:52:19 2024 +0000 @@ -0,0 +1,1295 @@ +<tool id="jbrowse2" name="JBrowse2" version="@TOOL_VERSION@+@WRAPPER_VERSION@"> + <description>genome browser</description> + <macros> + <import>macros.xml</import> + </macros> + <edam_topics> + <edam_topic>topic_3307</edam_topic> + <edam_topic>topic_0092</edam_topic> + </edam_topics> + <edam_operations> + <edam_operation>operation_0573</edam_operation> + <edam_operation>operation_0564</edam_operation> + </edam_operations> + <xrefs> + <xref type="bio.tools">jbrowse</xref> + </xrefs> + <expand macro="requirements"/> + <version_command>python '${__tool_directory__}/jbrowse2.py' --version</version_command> + <command detect_errors="aggressive"><![CDATA[ +mkdir -p $output.files_path && +#if $action.action_select != "create": + cp -R $action.update_jbrowse.extra_files_path/data $output.files_path/data && +#end if + +## Copy the XML file into the directory, mostly for debugging +## but nice if users want to reproduce locally +cp $trackxml $output.files_path/galaxy.xml && + +export JBROWSE2_SOURCE_DIR=\$(dirname \$(which jbrowse))/../opt/jbrowse2 && + +## Once that's done, we run the python script to handle the real work +python '$__tool_directory__/jbrowse2.py' + +--jbrowse \${JBROWSE2_SOURCE_DIR} + +--outdir $output.files_path +$trackxml && + +cp $output.files_path/index.html $output; + +## Ugly testing hack since I cannot get <extra_files> to test the files I want to test. Hmph. +#if str($uglyTestingHack) == "enabled": + cp $trackxml $output +#end if + ]]></command> + <configfiles> + <configfile name="trackxml"><![CDATA[<?xml version="1.0"?> +<root> + <metadata> + <genomes> + #if str($reference_genome.genome_type_select) == "indexed": + <genome path="${reference_genome.genomes.fields.path}" label="${reference_genome.genomes.fields.name}"> + <metadata /> + </genome>s + #else + <genome path="$reference_genome.genome" label="${reference_genome.genome.element_identifier}"> + <metadata> + <dataset id="${__app__.security.encode_id($reference_genome.genome.id)}" hid="${reference_genome.genome.hid}" + size="${reference_genome.genome.get_size(nice_size=True)}" + edam_format="${reference_genome.genome.datatype.edam_format}" + file_ext="${reference_genome.genome.ext}" /> + <history id="${__app__.security.encode_id($reference_genome.genome.history_id)}" + #if $reference_genome.genome.history.user: + user_email="${reference_genome.genome.history.user.email}" + user_id="${reference_genome.genome.history.user_id}" + display_name="${reference_genome.genome.history.get_display_name()}"/> + #else + user_email="anonymous" + user_id="-1" + display_name="Unnamed History"/> + #end if + <metadata + #for (key, value) in $reference_genome.genome.get_metadata().items(): + #if "_types" not in $key: + #if isinstance($value, list): + #set value_str = "[%s]" % ','.join([str(val) for val in value]) + ${key}="$value_str" + #else + ${key}="${value}" + #end if + #end if + #end for + /> + <tool + tool_id="${reference_genome.genome.creating_job.tool_id}" + tool_version="${reference_genome.genome.creating_job.tool_version}" + /> + </metadata> + </genome> + #end if + </genomes> + <general> + <defaultLocation>${jbgen.defaultLocation}</defaultLocation> + <analytics>${jbgen.enableAnalytics}</analytics> + <primary_color>${jbgen.primary_color}</primary_color> + <secondary_color>${jbgen.secondary_color}</secondary_color> + <tertiary_color>${jbgen.tertiary_color}</tertiary_color> + <quaternary_color>${jbgen.quaternary_color}</quaternary_color> + <font_size>${jbgen.font_size}</font_size> + <session_name>${jbgen.session_name}</session_name> + </general> + <galaxyUrl>${__app__.config.galaxy_infrastructure_url}</galaxyUrl> + </metadata> + <tracks> + #for $tg in $track_groups: + #for $track in $tg.data_tracks: + <track cat="${tg.category}" format="${track.data_format.data_format_select}" visibility="${track.data_format.track_visibility}"> + #if $track.data_format.data_format_select != "sparql": + <files> + #for $dataset in $track.data_format.annotation: + <trackFile path="${dataset}" ext="${dataset.ext}" label="${dataset.element_identifier}"> + <metadata> + <dataset id="${__app__.security.encode_id($dataset.id)}" hid="${dataset.hid}" + size="${dataset.get_size(nice_size=True)}" + edam_format="${dataset.datatype.edam_format}" + file_ext="${dataset.ext}" /> + <history id="${__app__.security.encode_id($dataset.history_id)}" + #if $dataset.history.user: + user_email="${dataset.history.user.email}" + user_id="${dataset.history.user_id}" + display_name="${dataset.history.get_display_name()}"/> + #else + user_email="anonymous" + user_id="-1" + display_name="Unnamed History"/> + #end if + <metadata + #for (key, value) in $dataset.get_metadata().items(): + #if "_types" not in $key and $value is not None and len(str($value)) < 5000: + #if isinstance($value, list): + #set value_str = "[%s]" % ','.join([str(val) for val in value]) + ${key}="$value_str" + #else + ${key}="${value}" + #end if + #end if + #end for + /> + <tool + tool_id="${dataset.creating_job.tool_id}" + tool_version="${dataset.creating_job.tool_version}" + /> + </metadata> + </trackFile> + #end for + </files> + #end if + + <options> + <style> + <display>${track.data_format.jbstyle.track_style.display}</display> + ## TODO change this to a for loop? + #if 'show_labels' in $track.data_format.jbstyle.track_style + <trackShowLabels type="boolean">${track.data_format.jbstyle.track_style.show_labels}</trackShowLabels> + #end if + #if 'show_descriptions' in $track.data_format.jbstyle.track_style + <trackShowDescriptions type="boolean">${track.data_format.jbstyle.track_style.show_descriptions}</trackShowDescriptions> + #end if + #if 'display_mode' in $track.data_format.jbstyle.track_style + <trackDisplayMode>${track.data_format.jbstyle.track_style.display_mode}</trackDisplayMode> + #end if + #if 'max_height' in $track.data_format.jbstyle.track_style + <trackMaxHeight type="integer">${track.data_format.jbstyle.track_style.max_height}</trackMaxHeight> + #end if + #if 'autoscale' in $track.data_format.jbstyle.track_style + <autoscale>${track.data_format.jbstyle.track_style.autoscale}</autoscale> + #end if + #if 'resolution' in $track.data_format.jbstyle.track_style + <resolution type="integer">${track.data_format.jbstyle.track_style.resolution}</resolution> + #end if + #if 'summaryScoreMode' in $track.data_format.jbstyle.track_style + <summaryScoreMode>${track.data_format.jbstyle.track_style.summaryScoreMode}</summaryScoreMode> + #end if + #if 'scaleType' in $track.data_format.jbstyle.track_style + <scaleType>${track.data_format.jbstyle.track_style.scaleType}</scaleType> + #end if + #if 'filled' in $track.data_format.jbstyle.track_style + <filled type="boolean">${track.data_format.jbstyle.track_style.filled}</filled> + #end if + #if 'displayCrossHatches' in $track.data_format.jbstyle.track_style + <displayCrossHatches type="boolean">${track.data_format.jbstyle.track_style.displayCrossHatches}</displayCrossHatches> + #end if + #if 'minScore' in $track.data_format.jbstyle.track_style and $track.data_format.jbstyle.track_style.minScore + <minScore type="integer">${track.data_format.jbstyle.track_style.minScore}</minScore> + #end if + #if 'maxScore' in $track.data_format.jbstyle.track_style and $track.data_format.jbstyle.track_style.maxScore + <maxScore type="integer">${track.data_format.jbstyle.track_style.maxScore}</maxScore> + #end if + ## TODO other coloring/etc options in each renderer (e.g https://github.com/GMOD/jbrowse-components/blob/main/plugins/svg/src/SvgFeatureRenderer/configSchema.ts) + </style> + <style_labels> + ## TODO other label options: https://github.com/GMOD/jbrowse-components/blob/main/plugins/svg/src/SvgFeatureRenderer/configSchema.ts + #if 'label' in $track.data_format.jbstyle.track_style + <name>${track.data_format.jbstyle.track_style.label}</name> + #end if + #if 'description' in $track.data_format.jbstyle.track_style + <description>${track.data_format.jbstyle.track_style.description}</description> + #end if + </style_labels> + #if str($track.data_format.data_format_select) == "gene_calls" or str($track.data_format.data_format_select) == "blast" or str($track.data_format.data_format_select) == "sparql": + <scaling> + #if str($track.data_format.jbcolor_scale.color_score.color_score_select) == "none": + <method>ignore</method> + <scheme> + #if str($track.data_format.jbcolor_scale.color_score.color.color_select) == "automatic": + <color>__auto__</color> + #else + <color>${track.data_format.jbcolor_scale.color_score.color.style_color}</color> + #end if + </scheme> + #else + <method>score</method> + <algo>${track.data_format.jbcolor_scale.color_score.score_scaling}</algo> + <scales> + <type>${track.data_format.jbcolor_scale.color_score.score_scales.scale_select}</type> + + #if str($track.data_format.jbcolor_scale.color_score.score_scales.scale_select) == "manual": + <min>${track.data_format.jbcolor_scale.color_score.score_scales.minimum}</min> + <max>${track.data_format.jbcolor_scale.color_score.score_scales.maximum}</max> + #end if + </scales> + <scheme> + <type>${track.data_format.jbcolor_scale.color_score.color_scheme.score_scheme}</type> + ## auto_color + #if str($track.data_format.jbcolor_scale.color_score.color_scheme.score_scheme) == "opacity": + #if str($track.data_format.jbcolor_scale.color_score.color_scheme.color.color_select) == "automatic": + <color>__auto__</color> + #else + <color>${track.data_format.jbcolor_scale.color_score.color_scheme.color.style_color}</color> + #end if + #end if + </scheme> + #end if + </scaling> + <menus> + #for $menu_item in $track.data_format.jbmenu.track_menu: + <menu> + <action>${menu_item.menu_action}</action> + #if str($menu_item.menu_label) != "": + <label>${menu_item.menu_label}</label> + #end if + #if str($menu_item.menu_title) != "": + <title>${menu_item.menu_title}</title> + #end if + #if str($menu_item.menu_url) != "": + <url>${menu_item.menu_url.replace("&", "&").replace("\"", """)}</url> + #end if + #if str($menu_item.menu_icon) != "": + <iconClass>${menu_item.menu_icon}</iconClass> + #end if + </menu> + #end for + </menus> + #end if + + #if str($track.data_format.data_format_select) == "wiggle": + <wiggle> + <type>${track.data_format.xyplot}</type> + <variance_band>${track.data_format.var_band}</variance_band> + #if str($track.data_format.scaling.scale_select) == "auto_local": + <autoscale>local</autoscale> + #else if str($track.data_format.scaling.scale_select) == "auto_global": + <autoscale>global</autoscale> + #else: + <min>${track.data_format.scaling.minimum}</min> + <max>${track.data_format.scaling.maximum}</max> + #end if + <scale>${track.data_format.scale_select2}</scale> + + ## Wiggle tracks need special color config + #if str($track.data_format.jbcolor.color.color_select) != "automatic": + <color_pos>${track.data_format.jbcolor.color.style_pos_color}</color_pos> + <color_neg>${track.data_format.jbcolor.color.style_neg_color}</color_neg> + #else: + <color_pos>__auto__</color_pos> + <color_neg>__auto__</color_neg> + #end if + + ## Bicolor pivot config + #if str($track.data_format.jbcolor.bicolor_pivot.bicolor_pivot_select) == "zero": + <bicolor_pivot>zero</bicolor_pivot> + #else if str($track.data_format.jbcolor.bicolor_pivot.bicolor_pivot_select) == "mean": + <bicolor_pivot>mean</bicolor_pivot> + #else: + <bicolor_pivot>${track.data_format.jbcolor.bicolor_pivot.pivot_point}</bicolor_pivot> + #end if + </wiggle> + #else if str($track.data_format.data_format_select) == "pileup": + <pileup> + <bam_indices> + #for $dataset in $track.data_format.annotation: + <bam_index>${dataset.metadata.bam_index}</bam_index> + #end for + </bam_indices> + </pileup> + #else if str($track.data_format.data_format_select) == "cram": + <cram> + <cram_indices> + #for $dataset in $track.data_format.annotation: + <cram_index>${dataset.metadata.cram_index}</cram_index> + #end for + </cram_indices> + </cram> + #else if str($track.data_format.data_format_select) == "blast": + <blast> + #if str($track.data_format.blast_parent) != "": + <parent>${track.data_format.blast_parent}</parent> + #end if + <protein>${track.data_format.is_protein}</protein> + <min_gap>${track.data_format.min_gap}</min_gap> + <index>${track.data_format.index}</index> + </blast> + #else if str($track.data_format.data_format_select) == "gene_calls": + <gff> + #if $track.data_format.match_part.match_part_select: + <match>${track.data_format.match_part.name}</match> + #end if + <index>${track.data_format.index}</index> + </gff> + #else if str($track.data_format.data_format_select) == "synteny": + <synteny> + <genome>${track.data_format.synteny_genome}</genome> + <genome_label>${track.data_format.synteny_genome.element_identifier}</genome_label> + </synteny> + #else if str($track.data_format.data_format_select) == "hic": + <hic> + </hic> + #else if str($track.data_format.data_format_select) == "sparql": + <label>${track.data_format.label}</label> + <sparql> + <url>${track.data_format.url}</url> + <query>${track.data_format.query}</query> + <query_refnames>${track.data_format.query_refnames}</query_refnames> + </sparql> + #end if + </options> + </track> + #end for + #end for + </tracks> +</root> +]]></configfile> + </configfiles> + <inputs> + <conditional name="reference_genome"> + <param help="Built-in references" label="Reference genome to display" name="genome_type_select" type="select"> + <option selected="True" value="indexed">Use a built-in genome</option> + <option value="history">Use a genome from history</option> + </param> + <when value="indexed"> + <param + help="If your genome of interest is not listed, contact the Galaxy team" + label="Select a reference genome" + name="genomes" + type="select" + > + <options from_data_table="all_fasta"> + <filter column="2" type="sort_by" /> + <validator message="No genomes are available for the selected input dataset" type="no_options" /> + </options> + </param> + </when> + <when value="history"> + <param + format="fasta" + label="Select the reference genome" + name="genome" + type="data" /> + </when> + </conditional> + <!-- TODO auto add GC track when implemented + https://github.com/GMOD/jbrowse-components/pull/2683 + https://github.com/GMOD/jbrowse-components/pull/3328 + --> + + <!-- TODO genetic code not yet supported in jbrowse2 + https://github.com/GMOD/jbrowse-components/issues/1765 + --> + + <conditional name="action"> + <param type="select" label="JBrowse-in-Galaxy Action" name="action_select"> + <option value="create">New JBrowse Instance</option> + <option value="update">Update exising JBrowse Instance</option> + </param> + <when value="create" /> + <when value="update"> + <param name="update_jbrowse" type="data" format="html" label="Previous JBrowse Instance" /> + </when> + </conditional> + + <repeat name="track_groups" title="Track Group"> + <param label="Track Category" + name="category" + type="text" + value="Default" + help="Organise your tracks into Categories for a nicer end-user experience. You can use #date# and it will be replaced with the current date in 'yyyy-mm-dd' format, which is very useful for repeatedly updating a JBrowse instance when member databases / underlying tool versions are updated." optional="False"/> + <repeat name="data_tracks" title="Annotation Track"> + <conditional name="data_format" label="Track Options"> + <param type="select" label="Track Type" name="data_format_select"> + <option value="gene_calls">GFF/GFF3/BED Features</option> + <option value="pileup">BAM Pileups</option> + <option value="cram">CRAM</option> + <option value="blast">Blast XML</option> + <option value="wiggle">BigWig XY</option> + <option value="vcf">VCF SNPs</option> + <option value="synteny">Synteny</option> + <option value="hic">HiC</option> + <option value="sparql">SPARQL</option> + </param> + <when value="blast"> + <expand macro="input_conditional" label="BlastXML Track Data" format="blastxml" /> + + <param label="Features used in Blast Search" + help="in GFF3. This is used so we know where to map features. E.g. where results of which CDS Protein32 match up to. The query IDs in your blast results should MATCH some feature IDs in your GFF3 file. This is an optional field and is most useful if using JBrowse to display protein blast results on a DNA genome. blastn results don't need this, blastp results on a protein sequence don't need this." + format="gff3" + name="blast_parent" + optional="true" + type="data"/> + + <param label="Minimum Gap Size" + help="before a new match_part feature is created" + name="min_gap" + type="integer" + value="10" + min="2" /> + <param label="Is this a protein blast search?" + type="boolean" + name="is_protein" + truevalue="true" + falsevalue="false" /> + + <param label="Index this track" name="index" type="boolean" checked="false" truevalue="true" falsevalue="false" /> + + <expand macro="track_styling_feature" + classname="feature" + label="description" + description="Hit_titles" + height="600px"/> + <expand macro="color_selection" + token_scaling_lin_select="false" + token_scaling_log_select="true" /> + <expand macro="track_menu" /> + <expand macro="track_visibility" /> + </when> + <when value="vcf"> + <expand macro="input_conditional" label="SNP Track Data" format="vcf,vcf_bgzip" /> + <expand macro="track_styling_vcf"/> + <expand macro="track_visibility" /> + </when> + <when value="gene_calls"> + <expand macro="input_conditional" label="GFF/GFF3/BED Track Data" format="gff,gff3,bed" /> + <conditional name="match_part" label="match/match_part data"> + <param label="This is match/match_part data" + type="boolean" + name="match_part_select" + truevalue="true" + falsevalue="false" /> + <when value="true"> + <param label="Match Part Feature Type" + name="name" + type="text" + value="match" + help="Match_parts have several options for the parent feature type, such as cDNA_match, match, translated_nucleotide_match, etc. Please select the appropriate one here. You can leave empty to try autodetection (only works with CanvasFeatures track type)." + optional="True"/> + </when> + <when value="false" /> + </conditional> + + <param label="Index this track" name="index" type="boolean" checked="false" truevalue="true" falsevalue="false" /> + + <expand macro="track_styling_feature" + classname="feature" + label="product,name,id" + description="note,description" + height="10px"/> + <expand macro="color_selection" /> + <expand macro="track_menu" /> + <expand macro="track_visibility" /> + </when> + <when value="pileup"> + <expand macro="input_conditional" label="BAM Track Data" format="bam" /> + <expand macro="track_styling_xam"/> + <expand macro="track_visibility" /> + </when> + <when value="cram"> + <expand macro="input_conditional" label="CRAM Track Data" format="cram" /> + <expand macro="track_styling_xam"/> + <expand macro="track_visibility" /> + </when> + <when value="wiggle"> + <expand macro="input_conditional" label="BigWig Track Data" format="bigwig" /> + + <param label="Use XYPlot" + help="instead of continuous colored band" + type="boolean" + name="xyplot" + truevalue="JBrowse/View/Track/Wiggle/XYPlot" + falsevalue="JBrowse/View/Track/Wiggle/Density" /> + <param label="Show variance band" + help="Only for XYPlots" + type="boolean" + name="var_band" + truevalue="true" + falsevalue="false" /> + + <conditional name="scaling" label="Scaling"> + <param type="select" label="Track Scaling" name="scale_select"> + <option value="auto_local" selected="true">Autoscale (local)</option> + <option value="auto_global">Autoscale (global)</option> + <option value="fixed">Specify Min/Max</option> + </param> + <when value="auto_local"></when> + <when value="auto_global"></when> + <when value="fixed"> + <param label="Track minimum" name="minimum" + type="integer" value="0" /> + <param label="Track maximum" name="maximum" + type="integer" value="100" /> + </when> + </conditional> + <param type="select" label="Visual Scaling" name="scale_select2"> + <option value="linear" selected="true">Linear</option> + <option value="log">Logarithmic (Dynamically Calculated)</option> + </param> + + <expand macro="color_selection_minmax" /> + + <expand macro="track_styling_bigwig"/> + <expand macro="track_visibility" /> + </when> + + <when value="synteny"> + <param label="Other genome sequence" + format="fasta" + name="synteny_genome" + type="data" /> + <!-- TODO add .out (MashMap) .chain (UCSC), .delta (mummer) and .anchors (mcscan) inputs --> + <expand macro="input_conditional" label="Synteny data" format="paf" /> + <expand macro="track_visibility" /> + </when> + + <when value="hic"> + <!-- TODO no hic datatype by default, but input for hicConvertFormat? hic_matrix datatype on .eu --> + <expand macro="input_conditional" label="HiC data" format="hic" /> + <expand macro="track_visibility" /> + </when> + + <when value="sparql"> + <param type="text" label="SPARQL Server URL" name="url" /> + <param type="text" label="Track Label" name="label" value="SPARQL Genes" /> + <param type="text" label="SPARQL Query" name="query" area="true"> + <sanitizer> + <mapping initial="galaxy.util.mapped_chars"> + <add source=" " target=" " /> + <add source=">" target="__gt__" /> + <add source="<" target="__lt__" /> + </mapping> + <valid initial="default"> + <add value="|" /> + <add value="#" /> + <add value="{"/> + <add value="}"/> + <add value="!"/> + <add value="?"/> + <add value="&"/> + <add value="+"/> + <add value="="/> + <add value="'"/> + <add value='"'/> + </valid> + </sanitizer> + </param> + <param type="text" label="SPARQL reference names query" help="This query should return a line for each reference name in a `refName` column" name="query_refnames" area="true"> + <sanitizer> + <mapping initial="galaxy.util.mapped_chars"> + <add source=" " target=" " /> + <add source=">" target="__gt__" /> + <add source="<" target="__lt__" /> + </mapping> + <valid initial="default"> + <add value="|" /> + <add value="#" /> + <add value="{"/> + <add value="}"/> + <add value="!"/> + <add value="?"/> + <add value="&"/> + <add value="+"/> + <add value="="/> + <add value="'"/> + <add value='"'/> + </valid> + </sanitizer> + </param> + <expand macro="track_visibility" /> + </when> + </conditional> + </repeat> + </repeat> + + <expand macro="general_options" /> + + <param type="hidden" name="uglyTestingHack" value="" /> + </inputs> + <outputs> + <!-- TODO create a jbrowse2 datatype --> + <data format="html" name="output" label="JBrowse2 on $on_string"/> + </outputs> + <tests> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="genome path="></has_text> + <has_text text="dataset id="></has_text> + <has_text text="history id="></has_text> + <has_text text="metadata"></has_text> + <has_text text="tool_id"></has_text> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + <repeat name="track_groups"> + <param name="category" value="Default" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="bed/test-3.bed,bed/test-6.bed"/> + </conditional> + </repeat> + </repeat> + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="genome path="></has_text> + <has_text text="dataset id="></has_text> + <has_text text="history id="></has_text> + <has_text text="metadata"></has_text> + <has_text text="tool_id"></has_text> + <has_text text="trackFile path="></has_text> + <has_text text="ext="bed" label="test-3.bed""></has_text> + <has_text text="NeatHTMLFeatures"></has_text> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + <repeat name="track_groups"> + <param name="category" value="Auto Coloured" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/A.gff,gff3/B.gff,gff3/C.gff,gff3/D.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <repeat name="track_groups"> + <param name="category" value="Ignore Scale" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + <conditional name="color"> + <param name="color_select" value="manual"/> + <param name="style_color" value="#ff00ff"/> + </conditional> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <repeat name="track_groups"> + <param name="category" value="Scaled Colour" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="score"/> + <param name="score_scaling" value="linear"/> + <conditional name="score_scales"> + <param name="scale_select" value="automatic"/> + </conditional> + <conditional name="color_scheme"> + <param name="score_scheme" value="opacity"/> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </conditional> + </conditional> + </section> + </conditional> + </repeat> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="score"/> + <param name="score_scaling" value="linear"/> + <conditional name="score_scales"> + <param name="scale_select" value="automatic"/> + </conditional> + <conditional name="color_scheme"> + <param name="score_scheme" value="opacity"/> + <conditional name="color"> + <param name="color_select" value="manual"/> + <param name="style_color" value="#0000ff"/> + </conditional> + </conditional> + </conditional> + </section> + </conditional> + </repeat> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="score"/> + <param name="score_scaling" value="linear"/> + <conditional name="score_scales"> + <param name="scale_select" value="manual"/> + <param name="minimum" value="0"/> + <param name="maximum" value="1000"/> + </conditional> + <conditional name="color_scheme"> + <param name="score_scheme" value="opacity"/> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </conditional> + </conditional> + </section> + </conditional> + </repeat> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="score"/> + <param name="score_scaling" value="linear"/> + <conditional name="score_scales"> + <param name="scale_select" value="manual"/> + <param name="minimum" value="0"/> + <param name="maximum" value="1000"/> + </conditional> + <conditional name="color_scheme"> + <param name="score_scheme" value="opacity"/> + <conditional name="color"> + <param name="color_select" value="manual"/> + <param name="style_color" value="#ff0000"/> + </conditional> + </conditional> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <repeat name="track_groups"> + <param name="category" value="Realistic" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/interpro.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + </conditional> + </repeat> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/2.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="true"/> + <param name="name" value="cDNA_match"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="Auto Coloured"/> + <has_text text="A.gff"/> + <has_text text="B.gff"/> + <has_text text="C.gff"/> + <has_text text="D.gff"/> + <has_text text="Scaled Colour"/> + <has_text text="1.gff"/> + <has_text text="2.gff"/> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + + <repeat name="track_groups"> + <param name="category" value="With menu or index" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + <section name="jbmenu"> + <repeat name="track_menu"> + <param name="menu_action" value="iframeDialog"/> + <param name="menu_label" value="Some menu item"/> + <param name="menu_title" value="Frame title"/> + <param name="menu_url" value="https://example.com/#!/?id={name}&q={type}&z="{end}""/> + <param name="menu_icon" value="dijitIconNewTask"/> + </repeat> + <repeat name="track_menu"> + <param name="menu_action" value="newWindow"/> + <param name="menu_label" value="Another menu item"/> + <param name="menu_title" value="Frame title 2"/> + <param name="menu_url" value="https://example.com/#!/?id={name}&q={type}&z="{end}""/> + </repeat> + </section> + </conditional> + </repeat> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <param name="index" value="true"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="With menu or index"/> + <has_text text="Some menu item"/> + <has_text text="Frame title"/> + <has_text text="dijitIconNewTask"/> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + + <repeat name="track_groups"> + <param name="category" value="With canvas config" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <conditional name="track_config"> + <param name="track_class" value="JBrowse/View/Track/CanvasFeatures"/> + <section name="canvas_options"> + <param name="transcriptType" value="transcript"/> + <param name="subParts" value="exon"/> + <param name="impliedUTRs" value="true"/> + </section> + </conditional> + <section name="jbcolor_scale"> + <conditional name="color_score"> + <param name="color_score_select" value="none"/> + </conditional> + <conditional name="color"> + <param name="color_select" value="automatic"/> + </conditional> + </section> + </conditional> + </repeat> + </repeat> + + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="With canvas config"></has_text> + <has_text text="<transcriptType>transcript</transcriptType>"></has_text> + <has_text text="<subParts>exon</subParts>"></has_text> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + + <repeat name="track_groups"> + <param name="category" value="With custom track config" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="gene_calls"/> + <param name="annotation" value="gff3/1.gff"/> + <conditional name="match_part"> + <param name="match_part_select" value="false"/> + </conditional> + <section name="jb_custom_config"> + <repeat name="option"> + <param name="opt_key" value="displayMode"/> + <conditional name="opt_value"> + <param name="val_type" value="text"/> + <param name="val" value="collapsed"/> + </conditional> + </repeat> + <repeat name="option"> + <param name="opt_key" value="histograms.height"/> + <conditional name="opt_value"> + <param name="val_type" value="integer"/> + <param name="val" value="150"/> + </conditional> + </repeat> + <repeat name="option"> + <param name="opt_key" value="maxFeatureScreenDensity"/> + <conditional name="opt_value"> + <param name="val_type" value="float"/> + <param name="val" value="0.1"/> + </conditional> + </repeat> + <repeat name="option"> + <param name="opt_key" value="style.strandArrow"/> + <conditional name="opt_value"> + <param name="val_type" value="boolean"/> + <param name="val" value="false"/> + </conditional> + </repeat> + </section> + </conditional> + </repeat> + </repeat> + + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="1.gff"/> + <has_text text="collapsed"/> + <has_text text="150"/> + <has_text text="maxFeatureScreenDensity"/> + <has_text text="style.strandArrow"/> + </assert_contents> + </output> + </test> + <test> + <param name="reference_genome|genome_type_select" value="history"/> + <param name="reference_genome|genome" value="merlin.fa"/> + + <repeat name="track_groups"> + <param name="category" value="Auto Coloured" /> + <repeat name="data_tracks"> + <conditional name="data_format"> + <param name="data_format_select" value="pileup"/> + <param name="annotation" value="bam/merlin-sample.bam"/> + </conditional> + </repeat> + </repeat> + + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="merlin-sample.bam"/> + <has_text text="sort_order="coordinate""/> + <has_text text="bam_index"/> + </assert_contents> + </output> + </test> + <test> + <!-- data_table --> + <param name="reference_genome|genome_type_select" value="indexed"/> + <param name="reference_genome|genome" value="merlin"/> + <param name="uglyTestingHack" value="enabled" /> + <output name="output"> + <assert_contents> + <has_text text="merlin.fa"/> + </assert_contents> + </output> + </test> + <!-- TODO add a synteny test --> + <!-- TODO add a cram test --> + <!-- TODO add an hic test --> + <!-- TODO add a vcf_bgzip test --> + </tests> + <!-- TODO update doc --> + <help><![CDATA[ +JBrowse-in-Galaxy +================= + +JBrowse-in-Galaxy offers a highly configurable, workflow-compatible +alternative to Trackster. + +Overview +-------- + +JBrowse is a fast, embeddable genome browser built completely with +JavaScript and HTML5. + +The JBrowse-in-Galaxy (JiG) tool was written to help build complex +JBrowse installations straight from Galaxy, taking advantage of the +latest Galaxy features such as dataset collections, sections, and colour +pickers. It allows you to build up a JBrowse instance without worrying +about how to run the command line tools to format your data, and which +options need to be supplied and where. Additionally it comes with many +javascript functions to handle colouring of features which would be +nearly impossible to write without the assistance of this tool. + +The JBrowse-in-Galaxy tool is maintained by `the Galaxy IUC +<https://github.com/galaxyproject/tools-iuc/issues>`__, who you can help you +with missing features or bugs in the tool. + +Options +------- + +The first option you encounter is the **Fasta Sequence(s)**. This option +now accepts multiple fasta files, allowing you to build JBrowse +instances that contain data for multiple genomes or chrosomomes +(generally known as "landmark features" in gff3 terminology.) Up to 30 +will be shown from the dropdown selector within JBrowse, this is a known +issue. + +**Genetic Code** is a new feature in v0.4 of JiG / v1.12.0 of JBrowse, +which allows users to specify a non standard genetic code, and have +JBrowse highlight the correct start and stop codons. + +**Track Groups** represent a set of tracks in a single category. These +can be used to let your users understand relationships between large +groups of tracks. + +.. image:: sections.png + +Annotation Tracks +----------------- + +Within Track Groups, you have one or more **Annotation Tracks**. Each +Annotation Track is a groups of datasets which have similar styling. +This allows you to rapidly build up JBrowse instances without having to +configure tracks individually. A massive improvement over previous +versions. For example, if you have five different GFF3 files from +various gene callers that you wish to display, you can take advantage of +this feature to style all of them similarly. + +There are a few different types of tracks supported, each with their own +set of options: + +GFF3/BED +~~~~~~~~ + +These are your standard feature tracks. They usually highlight genes, +mRNAs and other features of interest along a genomic region. The +underlying tool and this help documentation focus primarily on GFF3 +data, and have not been tested extensively with other formats. Automatic +min/max detection will fail under BED datasets. + +The data may be of a subclass we call **match/match part** data. This +consists of top level ``match`` features, with a child ``match_part`` +feature, and is often used in displaying alignments. (See "Alignments" +section on the `GFF3 +specification <https://github.com/The-Sequence-Ontology/Specifications/blob/master/gff3.md>`__ for more +information). If the data is match/match part, you will need to specify +the top level match feature name, as it can be one of a few different SO +terms, and JiG does not yet have the ability to understand SO terms. + +Next up is the **Styling Options** section, which lets you control a few +properties on how the track is styled. Most of these you will not need +to configure and can safely leave on defaults. Occasionally you will +want to change what information is shown in the end product. + +.. image:: styling.png + +In the above image you can see some black text, and some blue text. The +source of the black text is configured with the **style.label** option, +and the source of the blue text is configured with the +**style.description** option. + +Feature Score Scaling & Colouring Options +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +First, you need to choose between ignoring the score attribute of GFF3 +files, or using it. If you choose to ignore it, all features will be +coloured with a solid colour. If you choose to use it, features will +have slightly different colours based on their scores. + +.. image:: opacity.png + +If you choose **Ignore score**, you may choose between automatically +choosing a colour, or manually specifying one. The automatically chosen +colours vary along a brewer palette and generally look quite nice with +no human intervention required. The manual colour choice is somewhat +self explanatory. Clicking on the small coloured square will bring up a +colour palette. + +If you choose **Base on score**, you're faced with a dizzying array of +options. First is the function to map the colour choices to colour +values. JiG comes with a few functions built in such as linear scaling, +logarithmic scaling, and blast scaling. + +The **linear scaling** method says "take these values, and they map +directly to a range of output values". **Logarithmic scaling** says +"please take the log of the score before mapping", and **Blast scaling** +is further specialised to handle blast data more nicely. These are +convenience functions to help transform the wide array of possible +values in the GFF3 score attribute to more meaningful numbers. If you +need more comprehensive score scaling, it is recommended that you +pre-process your GFF3 files somehow. + +Once you've selected a scaling method, you can choose to manually +specify the minimum and maximum expected values, or you can let JiG +determine them for you automatically. + +Finally, opacity is the only mapping we currently provide. Future +iterations will attempt to improve upon this and provide more colour +scales. The Opacity option maps the highest scoring features to full +opacity, and everything else to lower ones. + +BAM Pileups +~~~~~~~~~~~ + +We support BAM files and can automatically generate SNP tracks based on +that bam data. + +.. image:: bam.png + +This is *strongly discouraged* for high coverage density datasets. +Unfortunately there are no other configuration options exposed for bam +files. + +BlastXML +~~~~~~~~ + +.. image:: blast.png + +JiG now supports both blastn and blastp datasets. JiG internally uses a +blastXML to gapped GFF3 tool to convert your blastxml datasets into a +format amenable to visualization in JBrowse. This tool is also +available separately from the IUC on the toolshed. + +**Minimum Gap Size** reflects how long a gap must be before it becomes a +real gap in the processed gff3 file. In the picture above, various sizes +of gaps can be seen. If the minimum gap size was set much higher, say +100nt, many of the smaller gaps would disappear, and the features on +both sides would be merged into one, longer feature. This setting is +inversely proportional to runtime and output file size. *Do not set this +to a low value for large datasets*. By setting this number lower, you +will have extremely large outputs and extremely long runtimes. The +default was configured based off of the author's experience, but the +author only works on small viruses. It is *strongly* recommended that +you filter your blast results before display, e.g. picking out the top +10 hits or so. + +**Protein blast search** option merely informs underlying tools that +they should adjust feature locations by 3x. + +Styling Options +^^^^^^^^^^^^^^^ + +Please see the styling options for GFF3 datasets, they are identical. + +Feature Score Scaling & Coloring Options +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Please see the score scaling and colouring options for GFF3 datasets, +they are identical. Remember to set your score scaling to "blast" method +if you do use it. + +Bigwig XY +~~~~~~~~~ + +.. image:: bigwig.png + +**XYPlot** + +BigWig tracks can be displayed as a "density" plot which is continuous +line which varies in colour, or as an "XYplot." XYplots are preferable +for users to visually identify specific features in a bigwig track, +however density tracks are more visually compact. + +**Variance Band** is an option available to XYPlots, and can be seen in +the third and fourth tracks in the above picture. This overlays a mean +line, and 1 and 2 standard deviation areas. + +**Track Scaling** is different from colour scaling, instead it +configures how the track behaves inside of JBrowse. **Autoscaling +globally** means that JBrowse will determine the minimum and maximum for +the track, and fix the bounds of the viewport to that. E.g. if your +track ranges from 1-1000, and the region you're currently zoomed to only +goes from 0-50, then the viewport range will still show 1-1000. This is +good for global genomic context. However you may wish to consider +**autoscaling locally** instead. In the example of a region which varies +from 0-50, autoscaling locally would cause the individual track's +viewport to re-adjust and show just the 0-50 region. If neither of these +options are palatable, you may manually hardcode the minimum and +maximums for the track to scale to. + +Colour Options +^^^^^^^^^^^^^^ + +BigWig tracks have two colours in JBrowse, a positive and a negative +colour. + +As always you may manually choose a colour, or let JiG choose for you. + +One of the more interesting options is the **Bicolor pivot**. This +option allows you to control the point at which JBrowse switches from +the positive colour to the negative. In the above graphic, you can see +this has been configured to "mean" for the first two (orange and blue) +tracks. + +VCFs/SNPs +~~~~~~~~~ + +These tracks do not support any special configuration. + +@ATTRIBUTION@ +]]></help> + <expand macro="citations"/> +</tool> +
--- a/jbrowse2.py Sat Jan 20 10:04:08 2024 +0000 +++ b/jbrowse2.py Mon Jan 22 11:52:19 2024 +0000 @@ -1175,7 +1175,9 @@ refName = None if data.get("defaultLocation", ""): ddl = data["defaultLocation"] - loc_match = re.search(r"^(\w.+):(\d+)\.+(\d+)$", ddl) + loc_match = re.search( + r"^([^:]+):(\d+)\.+(\d+)$", ddl + ) # was re.search(r"^(\w.+):(\d+)\.+(\d+)$" if loc_match: refName = loc_match.group(1) start = int(loc_match.group(2)) @@ -1190,7 +1192,7 @@ start = 0 end = 10000 # Booh, hard coded! waiting for https://github.com/GMOD/jbrowse-components/issues/2708 logging.info( - "@@@ no defaultlocation found for default session - suggest adding one!" + "@@@ no defaultlocation found for default session - please add one" ) if refName is not None: @@ -1211,7 +1213,7 @@ ) else: logging.info( - "@@@ no assembly name found default session - suggest adding one!" + "@@@ no contig name found for default session - please add one!" ) session_name = data.get("session_name", "New session") for key, value in mapped_chars.items():
--- a/macros.xml Sat Jan 20 10:04:08 2024 +0000 +++ b/macros.xml Mon Jan 22 11:52:19 2024 +0000 @@ -28,7 +28,6 @@ <token name="@ATTRIBUTION@"><![CDATA[ **Attribution** This Galaxy tool relies on the JBrowse2, maintained by the GMOD Community. The Galaxy wrapper is developed by the IUC -This xml currently fails silently when profile=22.05 is set. ]]> </token> <xml name="genome_selector" @@ -139,7 +138,7 @@ <xml name="general_options"> <section name="jbgen" title="General JBrowse Options [Advanced]" expanded="false"> - <param label="Default location" type="text" name="defaultLocation" value="" help="Initial location to be shown for users who have never visited the browser before. Example: 'ctgA:1234..5678'"/> + <param label="Subset to display to new users" type="text" name="defaultLocation" value="" help="Initial subset to be shown for users who have never visited the browser before. Example: 'ctgA:1234..5678'"/> <param label="Session name" type="text" name="session_name" value="New session" help="Displayed at the top of the window"/> <param label="Enable analytics" help="Will send usage data to Google Analytics, see https://github.com/GMOD/jbrowse-components/issues/1166" name="enableAnalytics" type="boolean" checked="false" truevalue="true" falsevalue="false" />