| Previous changeset 45:0ec526d2d8c1 (2024-03-01) Next changeset 47:3e53204c2419 (2024-03-06) |
|
Commit message:
planemo upload for repository https://github.com/usegalaxy-eu/temporary-tools/tree/master/jbrowse2 commit 3a43e9e0ffce0966101203102e769d1ced28618a |
|
modified:
__pycache__/jbrowse2.cpython-310.pyc autogenJB2.py autogenJB2.xml jb2_webserver.py jbrowse2.py jbrowse2.xml macros.xml readme.rst test-data/gff3/merlin.gff3 test-data/vcf/merlin.vcf |
|
added:
klBraLanc5.haps_combined.decontam.20230620.fasta.fa.gz |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 __pycache__/jbrowse2.cpython-310.pyc |
| b |
| Binary file __pycache__/jbrowse2.cpython-310.pyc has changed |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 autogenJB2.py --- a/autogenJB2.py Fri Mar 01 05:15:41 2024 +0000 +++ b/autogenJB2.py Mon Mar 04 09:47:19 2024 +0000 |
| [ |
| b'@@ -1,5 +1,6 @@\n import argparse\n import logging\n+import os\n import sys\n \n from jbrowse2 import JbrowseConnector as jbC\n@@ -11,8 +12,7 @@\n def makeDefaultLocation():\n \n refName = jc.genome_firstcontig\n- defloc = "%s:100..10000" % refName\n- print (\'defloc\',defloc)\n+ defloc = "%s:100..10000" % refName\n return defloc\n \n \n@@ -21,61 +21,66 @@\n parser.add_argument("--sessName", help="Session name", default="AutoJBrowse")\n parser.add_argument(\n "--trackmeta",\n- help="Repeatable of \'filename, filext,filepath, ... ,\' for JBrowse2 tracks",\n+ help="Repeatable \'filename,filext,filepath,[bai/crai path for filesystem bam/cram]\' for JBrowse2 tracks",\n default=[],\n action="append",\n )\n parser.add_argument(\n "--referencemeta",\n- help="Repeatable \'filename, filext, filepath, ... ,\' for JBrowse2 reference tracks",\n+ help="Repeatable \'filename, filext, filepath, ... ,\' for JBrowse2 reference tracks - usually only one needed",\n default=[],\n action="append",\n )\n parser.add_argument(\n "--pafmeta",\n- help="Repeatable. Each is a \'filename, filext, filepath, ... ,\' for a JBrowse2 paf track",\n+ help="Repeatable. Each is a \'pafname, filext, filepath, ... ,\' for a JBrowse2 paf track",\n default=[],\n action="append",\n )\n parser.add_argument(\n "--pafreferencemeta",\n- help="Repeatable. Each is a \'pafname,filepath,refname,filepath,refname....\'. Every paf must have a corresponding one ",\n+ help="Repeatable. Each is a \'pafname,refpath,refname\' Every pafname must have one or more",\n default=[],\n action="append",\n )\n- parser.add_argument("--jbrowse2path", help="Path to JBrowse2 directory in biocontainer or Conda")\n+ parser.add_argument(\n+ "--jbrowse2path", help="Path to JBrowse2 directory in biocontainer or Conda"\n+ )\n parser.add_argument("--outdir", help="Output directory", required=True)\n parser.add_argument("--version", "-V", action="version", version="%(prog)s 2.10.2")\n args = parser.parse_args()\n sessName = args.sessName\n # --trackmeta $jbrowseme[$key],$jbrowseme[$key].ext,\'$key\'\n- trackList = [x.strip().split(",") for x in args.trackmeta if x > \'\']\n- refList = [x.strip().split(",") for x in args.referencemeta if x > \'\']\n- print("tracklist = %s\\nreflist = %s" % (trackList,refList))\n+ trackList = [x.strip().split(",") for x in args.trackmeta if x > ""]\n+ refList = [x.strip().split(",") for x in args.referencemeta if x > ""]\n if len(refList) > 0:\n- listgenomes = [f for f in refList if f[1] in [\'fasta\', \'fasta.gz\']]\n+ listgenomes = [f for f in refList if f[1] in ["fasta", "fasta.gz"]]\n # assume no pafs here\n- print(\'genomes=%s\' % listgenomes)\n if len(listgenomes) > 0:\n- genome_paths = [\n- x[0] for x in listgenomes\n- ] # expect genome_1_genomename.fasta etc\n+ genome_paths = [x[0] for x in listgenomes]\n genome_names = [x[2] for x in listgenomes]\n+ guseuri = []\n+ for x in genome_paths:\n+ if x.startswith(\'http://\') or x.startswith(\'https://\'):\n+ guseuri.append(\'yes\')\n+ else:\n+ guseuri.append(\'no\')\n jc = jbC(\n outdir=args.outdir,\n jbrowse2path=args.jbrowse2path,\n genomes=[\n {\n "path": x,\n- "meta": {\n- "name": genome_names[i],\n- "dataset_dname": genome_names[i],\n- },\n+ "label": genome_names[i],\n+ "useuri": guseuri[i],\n+ "meta": {"name": genome_names[i],\n+ "dataset_dname": genome_names[i]\n+ '..b'== "bam":\n+ ipath = track[3]\n+ if not os.path.exists(ipath):\n+ ipath = os.path.realpath(os.path.join(jc.outdir, trackname + \'.bai\'))\n+ cmd = ["samtools", "index", "-b", "-o", ipath, os.path.realpath(track[0])]\n+ sys.stdout.write(\'#### calling %s\' % \' \'.join(cmd))\n+ jc.subprocess_check_call(cmd)\n+ track_conf = {"conf": {"options": {"bam": {"bam_index": ipath}}}}\n+ elif trext == "cram":\n+ ipath = track[3]\n+ if not os.path.exists(ipath):\n+ jc.logging.info(\'calling %s\' % \' \'.join(cmd))\n+ ipath = os.path.realpath(os.path.join(\'./\', trackname + \'.crai\'))\n+ cmd = ["samtools", "index", "-c", "-o", ipath, os.path.realpath(track[0])]\n+ sys.stdout.write(\'#### calling %s\' % \' \'.join(cmd))\n+ jc.subprocess_check_call(cmd)\n+ track_conf = {"conf": {"options": {"cram": {"cram_index": ipath}}}}\n else:\n track_conf = {}\n track_conf["format"] = trext\n track_conf["name"] = trackname\n track_conf["label"] = trackname\n- track_conf["trackfiles"] = [(tpath, trext, trackname,{}),]\n+ useu = tpath.startswith(\'http://\') or tpath.startswith(\'https://\')\n+ useuri = \'no\'\n+ if useu:\n+ useuri = \'yes\'\n+ track_conf["trackfiles"] = [\n+ (tpath, trext, useuri, trackname, {}),\n+ ]\n track_conf["category"] = "Autogenerated"\n keys = jc.process_annotations(track_conf)\n \n if keys:\n for key in keys:\n- if trext in ["bigwig", "gff3", "gff", "vcf", "maf",]:\n+ if trext in [\n+ "bigwig",\n+ "gff3",\n+ "gff",\n+ "vcf",\n+ "maf",\n+ ]:\n default_session_data["visibility"]["default_on"].append(key)\n else:\n- default_session_data["visibility"]["default_off"].append(key)\n- # if track_conf.get("style", None):\n- # default_session_data["style"][key] = track_conf[\n- # "style"\n- # ] # TODO do we need this anymore?\n- # if track_conf.get("style_lables", None):\n- # default_session_data["style_labels"][key] = track_conf.get(\n- # "style_labels", None\n- # )\n+ default_session_data["visibility"]["default_off"].append(\n+ key\n+ )\n # general_data = {\n # "analytics": root.find("metadata/general/analytics").text,\n # "primary_color": root.find("metadata/general/primary_color").text,\n@@ -152,9 +176,13 @@\n jc.config_json["tracks"] = jc.tracksToAdd\n jc.write_config()\n defLoc = makeDefaultLocation()\n- default_session_data.update({"defaultLocation": defLoc, "session_name": sessName})\n+ default_session_data.update(\n+ {"defaultLocation": defLoc, "session_name": sessName}\n+ )\n track_conf.update(default_session_data)\n jc.add_default_session(default_session_data)\n # jc.text_index() not sure what broke here.\n else:\n- print("!! empty collection supplied - nothing to process")\n+ sys.stderr.write(\n+ "!!!! Collection has no suitable trackfiles for autogenJB2 - nothing to process"\n+ )\n' |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 autogenJB2.xml --- a/autogenJB2.xml Fri Mar 01 05:15:41 2024 +0000 +++ b/autogenJB2.xml Mon Mar 04 09:47:19 2024 +0000 |
| [ |
| @@ -13,7 +13,17 @@ export JBROWSE2_PATH=\$(dirname \$(which jbrowse))/../opt/jbrowse2 && python '$__tool_directory__/autogenJB2.py' #for $key in $autoCollection.keys(): - #if $autoCollection[$key].ext == 'fasta': + #if $autoCollection[$key].is_collection: + #set subCol=$autoCollection[$key] + #set pafs=[($subCol[x],$subcol[x].ext,x) for x in $subCol.keys() if $subCol[x].ext == 'paf'] + #if len($pafs) > 0: + --pafmeta '$pafs[0]' + #set refs = [($pafs[0][2],$subCol[x],x) for x in $subCol.keys() if $subCol[x].ext == 'fasta'] + #for $ref in $refs: + --pafreferencemeta '$ref' + #end for + #end if + #else if $autoCollection[$key].ext == 'fasta': --referencemeta '$autoCollection[$key],$autoCollection[$key].ext,$key' #else if $autoCollection[$key].ext in ['bed', 'bigwig', 'cool', 'gff', 'gff3', 'hic', 'maf', 'mcool', 'scool', 'vcf'] --trackmeta '$autoCollection[$key],$autoCollection[$key].ext,$key' @@ -45,23 +55,21 @@ <data format="html" name="output" label="AutoJBrowse2"/> </outputs> <tests> - <test> + <test> <param name="uglyTestingHack" value="enabled" /> <param name="autoCollection"> <collection type="list"> <element name="Merlin" value="merlin.fa" ftype="fasta"/> - <element name="merlin-sample.bam" value="bam/merlin-sample.bam" ftype="bam"/> + <element name="test-6.bed" value="bed/test-6.bed" ftype="bed"/> </collection> </param> - <output name="output"> - <assert_contents> - <has_text text='"name": "Merlin",'/> - <has_text text='"name": "merlin-sample.bam",'/> - <has_text text='"uri": "Merlin.fa.gz.fai"'/> - <has_text text='"uri": "bam_0_merlin-sample.bam.bam.bai"'/> - - </assert_contents> - </output> + <output name="output"> + <assert_contents> + <has_text text='"name": "Merlin",'/> + <has_text text='"name": "test-6.bed",'/> + <has_text text='"uri": "Merlin.fa.gz.fai"'/> + </assert_contents> + </output> </test> </tests> <help><![CDATA[ |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 jb2_webserver.py --- a/jb2_webserver.py Fri Mar 01 05:15:41 2024 +0000 +++ b/jb2_webserver.py Mon Mar 04 09:47:19 2024 +0000 |
| b |
| @@ -42,7 +42,7 @@ from http.server import SimpleHTTPRequestHandler -DEFAULT_PORT = 8080 +DEFAULT_PORT = 8081 def copy_byte_range(infile, outfile, start=None, stop=None, bufsize=16 * 1024): @@ -156,7 +156,7 @@ if __name__ == "__main__": parser = argparse.ArgumentParser( - description="Simple Python Web Server with Range Support" + description="Tiny Python Web Server supporting range requests, for local viewing of unzipped Galaxy JBrowse2 configurations" ) parser.add_argument( "--root", |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 jbrowse2.py --- a/jbrowse2.py Fri Mar 01 05:15:41 2024 +0000 +++ b/jbrowse2.py Mon Mar 04 09:47:19 2024 +0000 |
| [ |
| b'@@ -11,6 +11,7 @@\n import struct\n import subprocess\n import tempfile\n+import urllib.request\n import xml.etree.ElementTree as ET\n from collections import defaultdict\n \n@@ -446,7 +447,10 @@\n \n def process_genomes(self):\n assemblies = []\n+ useuri = False\n for i, genome_node in enumerate(self.genome_paths):\n+ if genome_node["useuri"].strip().lower() == "yes":\n+ useuri = True\n genome_name = genome_node["meta"]["dataset_dname"].strip()\n if len(genome_name.split()) > 1:\n genome_name = genome_name.split()[0]\n@@ -454,7 +458,9 @@\n if genome_name not in self.genome_names:\n # ignore dupes - can have multiple pafs with same references?\n fapath = genome_node["path"]\n- assem = self.make_assembly(fapath, genome_name)\n+ if not useuri:\n+ fapath = os.path.realpath(fapath)\n+ assem = self.make_assembly(fapath, genome_name, useuri)\n assemblies.append(assem)\n self.genome_names.append(genome_name)\n if self.genome_name is None:\n@@ -462,41 +468,67 @@\n genome_name # first one for all tracks - other than paf\n )\n self.genome_firstcontig = None\n- fl = open(fapath, "r").readline().strip().split(">")\n- if len(fl) > 1:\n- fl = fl[1]\n- if len(fl.split()) > 1:\n- self.genome_firstcontig = fl.split()[0].strip()\n+ if not useuri:\n+ # https://lazarus.name/jbrowse/fish/bigwig_0_coverage_bedgraph_cov_count_count_bw.bigwig\n+ # https://lazarus.name/jbrowse/fish/klBraLanc5.haps_combined.decontam.20230620.fasta.fa.gz\n+ fl = open(fapath, "r").readline()\n+ fls = fl.strip().split(">")\n+ if len(fls) > 1:\n+ fl = fls[1]\n+ if len(fl.split()) > 1:\n+ self.genome_firstcontig = fl.split()[0].strip()\n+ else:\n+ self.genome_firstcontig = fl\n else:\n- self.genome_firstcontig = fl\n+ fl = urrlib.request.urlopen(faname+".fai").readline()\n+ if fl: # is first row of the text fai so the first contig name\n+ self.genome_firstcontig = fl.decode(\'utf8\').strip().split()[0]\n if self.config_json.get("assemblies", None):\n self.config_json["assemblies"] += assemblies\n else:\n self.config_json["assemblies"] = assemblies\n \n- def make_assembly(self, fapath, gname):\n+ def make_assembly(self, fapath, gname, useuri):\n+ if useuri:\n+ faname = fapath\n+ adapter = {\n+ "type": "BgzipFastaAdapter",\n+ "fastaLocation": {\n+ "uri": faname,\n+ "locationType": "UriLocation",\n+ },\n+ "faiLocation": {\n+ "uri": faname + ".fai",\n+ "locationType": "UriLocation",\n+ },\n+ "gziLocation": {\n+ "uri": faname + ".gzi",\n+ "locationType": "UriLocation",\n+ },\n+ }\n+ else:\n+ faname = gname + ".fa.gz"\n+ fadest = os.path.realpath(os.path.join(self.outdir, faname))\n+ cmd = "bgzip -i -c %s -I %s.gzi > %s && samtools faidx %s" % (\n+ fapath,\n+ fadest,\n+ fadest,\n+ fadest,\n+ )\n+ self.subprocess_popen(cmd)\n \n- faname = gname + ".fa.gz"\n- fadest = os.path.realpath(os.path.join(self.outdir, faname)'..b'21,6 +1280,7 @@\n "assemblyName": self.genome_name,\n "start": 0,\n "end": 100000,\n+ "refName": "x",\n }\n \n if data.get("defaultLocation", ""):\n@@ -1307,9 +1367,9 @@\n json.dump(self.config_json, config_file, indent=2)\n \n def clone_jbrowse(self):\n- """Clone a JBrowse directory into a destination directory. This also works in Biocontainer testing now """\n+ """Clone a JBrowse directory into a destination directory. This also works in Biocontainer testing now"""\n dest = self.outdir\n- #self.subprocess_check_call([\'jbrowse\', \'create\', dest, \'--tag\', f"{JB_VER}"])\n+ # self.subprocess_check_call([\'jbrowse\', \'create\', dest, \'--tag\', f"{JB_VER}"])\n shutil.copytree(self.jbrowse2path, dest, dirs_exist_ok=True)\n for fn in [\n "asset-manifest.json",\n@@ -1341,7 +1401,9 @@\n if __name__ == "__main__":\n parser = argparse.ArgumentParser(description="", epilog="")\n parser.add_argument("--xml", help="Track Configuration")\n- parser.add_argument("--jbrowse2path", help="Path to JBrowse2 directory in biocontainer or Conda")\n+ parser.add_argument(\n+ "--jbrowse2path", help="Path to JBrowse2 directory in biocontainer or Conda"\n+ )\n parser.add_argument("--outdir", help="Output directory", default="out")\n parser.add_argument("--version", "-V", action="version", version="%(prog)s 2.0.1")\n args = parser.parse_args()\n@@ -1360,7 +1422,9 @@\n jbrowse2path=args.jbrowse2path,\n genomes=[\n {\n- "path": os.path.realpath(x.attrib["path"]),\n+ "path": x.attrib["path"],\n+ "label": x.attrib["label"],\n+ "useuri": x.attrib["useuri"],\n "meta": metadata_from_node(x.find("metadata")),\n }\n for x in root.findall("metadata/genomes/genome")\n@@ -1395,10 +1459,12 @@\n trackfiles = track.findall("files/trackFile")\n if trackfiles:\n for x in track.findall("files/trackFile"):\n+ track_conf["useuri"] = x.attrib["useuri"]\n if is_multi_bigwig:\n multi_bigwig_paths.append(\n (\n x.attrib["label"],\n+ x.attrib["useuri"],\n os.path.realpath(x.attrib["path"]),\n )\n )\n@@ -1406,14 +1472,23 @@\n if trackfiles:\n metadata = metadata_from_node(x.find("metadata"))\n track_conf["dataset_id"] = metadata["dataset_id"]\n- track_conf["trackfiles"].append(\n- (\n- os.path.realpath(x.attrib["path"]),\n+ if x.attrib["useuri"].lower() == "yes":\n+ tfa = (\n+ x.attrib["path"],\n x.attrib["ext"],\n+ x.attrib["useuri"],\n x.attrib["label"],\n metadata,\n )\n- )\n+ else:\n+ tfa = (\n+ os.path.realpath(x.attrib["path"]),\n+ x.attrib["ext"],\n+ x.attrib["useuri"],\n+ x.attrib["label"],\n+ metadata,\n+ )\n+ track_conf["trackfiles"].append(tfa)\n \n if is_multi_bigwig:\n metadata = metadata_from_node(x.find("metadata"))\n@@ -1447,7 +1522,6 @@\n except TypeError:\n track_conf["style"] = {}\n pass\n- track_conf["conf"] = etree_to_dict(track.find("options"))\n keys = jc.process_annotations(track_conf)\n \n if keys:\n' |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 jbrowse2.xml --- a/jbrowse2.xml Fri Mar 01 05:15:41 2024 +0000 +++ b/jbrowse2.xml Mon Mar 04 09:47:19 2024 +0000 |
| [ |
| b'@@ -1,4 +1,4 @@\n- <tool id="jbrowse2" name="jbrowse2" version="@TOOL_VERSION@+@WRAPPER_VERSION@_5" profile="22.05">\n+ <tool id="jbrowse2" name="jbrowse2" version="@TOOL_VERSION@+@WRAPPER_VERSION@_6" profile="22.05">\n <description>genome browser</description>\n <macros>\n <import>macros.xml</import>\n@@ -17,35 +17,75 @@\n \n export JBROWSE2_PATH=\\$(dirname \\$(which jbrowse))/../opt/jbrowse2 &&\n \n-## Once that\'s done, we run the python script to handle the real work\n-python \'$__tool_directory__/jbrowse2.py\'\n---jbrowse2path \\${JBROWSE2_PATH}\n---outdir \'$output.files_path\'\n---xml \'$trackxml\' &&\n-#if $jbgen.zipOut == "true":\n- (cd \'$output.files_path\' && zip -r - . ) > \'$output\'\n-#else\n- cp \'$output.files_path/index.html\' \'$output\'\n-#end if\n-## Ugly testing hack since I cannot get <extra_files> to test the files I want to test. Hmph.\n-#if str($uglyTestingHack) == "enabled":\n- && cp \'$trackxml\' \'$output\'\n+#if $jbgen.ucol.formcoll=="collect":\n+ python \'$__tool_directory__/autogenJB2.py\'\n+ #for $key in $autoCollection.keys():\n+ #if $autoCollection[$key].is_collection:\n+ #set subCol=$autoCollection[$key]\n+ #set pafs=[($subCol[x],$subcol[x].ext,x) for x in $subCol.keys() if $subCol[x].ext == \'paf\']\n+ #if len($pafs) > 0:\n+ --pafmeta \'$pafs[0]\'\n+ #set refs = [($pafs[0][2],$subCol[x],x) for x in $subCol.keys() if $subCol[x].ext == \'fasta\']\n+ #for $ref in $refs:\n+ --pafreferencemeta \'$ref\'\n+ #end for\n+ #end if\n+ #else if $autoCollection[$key].ext == \'fasta\':\n+ --referencemeta \'$autoCollection[$key],$autoCollection[$key].ext,$key\'\n+ #else if $autoCollection[$key].ext in [\'bed\', \'bigwig\', \'cool\', \'gff\', \'gff3\', \'hic\', \'maf\', \'mcool\', \'scool\', \'vcf\']\n+ --trackmeta \'$autoCollection[$key],$autoCollection[$key].ext,$key\'\n+ #else if $autoCollection[$key].ext in [\'bam\',]\n+ --trackmeta \'$autoCollection[$key],$autoCollection[$key].ext,$key,$autoCollection[$key].metadata.bam_index\'\n+ #else if $autoCollection[$key].ext in [\'cram\',]\n+ --trackmeta \'$autoCollection[$key],$autoCollection[$key].ext,$key,$autoCollection[$key].metadata.cram_index\'\n+ #end if\n+ #end for\n+ --outdir \'$output.files_path\'\n+ --jbrowse2path \\${JBROWSE2_PATH}\n+ --sessName "Autogen JBrowse" &&\n+ #if $jbgen.zipOut == "true":\n+ (cd \'$output.files_path\' && zip -r - . ) > \'$output\'\n+ #else\n+ cp \'$output.files_path/index.html\' \'$output\'\n+ #end if\n+#else:\n+ python \'$__tool_directory__/jbrowse2.py\'\n+ --jbrowse2path \\${JBROWSE2_PATH}\n+ --outdir \'$output.files_path\'\n+ --xml \'$trackxml\' &&\n+ #if $jbgen.zipOut == "true":\n+ (cd \'$output.files_path\' && zip -r - . ) > \'$output\'\n+ #else\n+ cp \'$output.files_path/index.html\' \'$output\'\n+ #end if\n+ ## Ugly testing hack since I cannot get <extra_files> to test the files I want to test. Hmph.\n+ #if str($uglyTestingHack) == "enabled":\n+ && cp \'$trackxml\' \'$output\'\n+ #end if\n #end if\n ]]></command>\n <configfiles>\n <configfile name="trackxml"><![CDATA[<?xml version="1.0"?>\n+#if $jbgen.ucol.formcoll=="form":\n <root>\n <metadata>\n <genomes>\n- #if str($reference_genome.genome_type_select) == "indexed":\n- <genome path="${reference_genome.genome.fields.path}" label="${reference_genome.genome.fields.name}">\n+ #if str($reference_genome.genome_type_select) == "uri":\n+ <genome path="${reference_genome.uri}" label="${reference_genome.refname}" useuri="yes">\n <metadata>\n <dataset\n- dname = "${reference_genome.genome.name}" />\n+ dname = "${reference_genome.refname}" />\n+ </metadata>\n+ </genome>\n+ #else if str($reference_genome.genome_type_select) == "indexed":\n+ <genome pa'..b' <param name="annotation" value="gff3/A.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/A.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n <conditional name="match_part">\n <param name="match_part_select" value="false"/>\n </conditional>\n@@ -571,7 +659,10 @@\n <repeat name="data_tracks">\n <conditional name="data_format">\n <param name="data_format_select" value="gene_calls"/>\n- <param name="annotation" value="gff3/1.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/1.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n <conditional name="match_part">\n <param name="match_part_select" value="false"/>\n </conditional>\n@@ -602,7 +693,10 @@\n <repeat name="data_tracks">\n <conditional name="data_format">\n <param name="data_format_select" value="gene_calls"/>\n- <param name="annotation" value="gff3/interpro.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/interpro.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n <conditional name="match_part">\n <param name="match_part_select" value="false"/>\n </conditional>\n@@ -619,7 +713,10 @@\n <repeat name="data_tracks">\n <conditional name="data_format">\n <param name="data_format_select" value="gene_calls"/>\n- <param name="annotation" value="gff3/2.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/2.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n <conditional name="match_part">\n <param name="match_part_select" value="true"/>\n <param name="name" value="cDNA_match"/>\n@@ -659,7 +756,10 @@\n <repeat name="data_tracks">\n <conditional name="data_format">\n <param name="data_format_select" value="gene_calls"/>\n- <param name="annotation" value="gff3/1.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/1.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n <conditional name="match_part">\n <param name="match_part_select" value="false"/>\n </conditional>\n@@ -691,7 +791,11 @@\n <repeat name="data_tracks">\n <conditional name="data_format">\n <param name="data_format_select" value="gene_calls"/>\n- <param name="annotation" value="gff3/1.gff"/>\n+ <conditional name="useuri">\n+ <param name="annotation" value="gff3/1.gff"/>\n+ <param name="insource" value= "history"/>\n+ </conditional>\n+ <param name="insource" value= "history"/>\n <conditional name="match_part">\n <param name="match_part_select" value="false"/>\n </conditional>\n' |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 klBraLanc5.haps_combined.decontam.20230620.fasta.fa.gz |
| b |
| Binary file klBraLanc5.haps_combined.decontam.20230620.fasta.fa.gz has changed |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 macros.xml --- a/macros.xml Fri Mar 01 05:15:41 2024 +0000 +++ b/macros.xml Mon Mar 04 09:47:19 2024 +0000 |
| [ |
| @@ -140,6 +140,19 @@ <xml name="general_options"> <section name="jbgen" title="General JBrowse Options [Advanced]" expanded="false"> + <conditional name="ucol"> + <param name="formcoll" type="select" label="Convert a collection of track files rather than filling in the tool form" + help="A collection of bam/vcf and other track types will be converted into a JBrowse2 automatically"> + <option value="form" selected="true">Fill in the tool form to specify tracks for the output JBrowse2</option> + <option value="collect">Convert a collection of suitable track files</option> + </param> + <when value="collect"> + <param label="Collection of bed, bam and other track files" name="autoCollection" type="data_collection" /> + </when> + <when value="form"> + </when> + </conditional> + <param label="Create a zip archive for downloading rather than viewing " name="zipOut" help="Default is to make an interactive browser appear when the 'eye' icon is activated" type="boolean" checked="false" truevalue="true" falsevalue="false" /> <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'"/> @@ -505,8 +518,27 @@ </xml> <xml name="input_conditional" token_label="Track Data" token_format="data"> - <param label="@LABEL@" format="@FORMAT@" name="annotation" optional="True" type="data" multiple="True"/> - </xml> + <conditional name="useuri"> + <param name="insource" type="select" label="Define track data as a history file or an internet URI" + help="A public URI implies that all the associated tabix files are also in place. They are created for history files"> + <option value="history" selected="true">Track data from a history file</option> + <option value="uri" selected="true">Tabix data URI - index files must be available at corresponding URI</option> + </param> + <when value="history"> + <param label="@LABEL@" format="@FORMAT@" name="annotation" multiple="True" optional="true" type="data" /> + </when> + <when value="uri"> + <param label="@LABEL@" name="annouri" multiple="false" type="text" /> + <param label="Short name for track display" name="annoname" type="text" > + <sanitizer invalid_char="_"> + <valid initial="string.printable" > + <remove value="'" /> + </valid> + </sanitizer> + </param> + </when> + </conditional> + </xml> <xml name="citations"> <citations> <citation type="doi">10.1186/s13059-016-0924-1</citation> |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 readme.rst --- a/readme.rst Fri Mar 01 05:15:41 2024 +0000 +++ b/readme.rst Mon Mar 04 09:47:19 2024 +0000 |
| b |
| @@ -1,7 +1,19 @@ JBrowse2 in Galaxy ================== -Added Feb 3: cool/mcool -> hic +Added Mar 3: +- optional tracks at last for JB2 + - dotted noodles from optional inputs now ignored without harm +- autogenJB2. + - Takes a collection of bam/vcf etc and turns them into tracks in a normal JB2 history item. + - Uses the JbrowseConnector, but the XML tool drives it from the contents of the collection. + - Collection can be built from any source or with optional noodles in a WF + - Produces a JB2 with all available tracks. + - Argparse command line with repeats for tracks and references + - so works outside Galaxy to process directories or s3 buckets. + + +Added Feb 3: cool/mcool -> hic .. image:: dm4_in_jb2.png |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 test-data/gff3/merlin.gff3 --- a/test-data/gff3/merlin.gff3 Fri Mar 01 05:15:41 2024 +0000 +++ b/test-data/gff3/merlin.gff3 Mon Mar 04 09:47:19 2024 +0000 |
| b |
| b'@@ -1,1230 +1,38 @@\n ##gff-version 3\n ##sequence-region Merlin 1 172788\n-Merlin GeneMark.hmm gene 2 691 -856.563659 + . ID=Merlin_1;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 2 691 . + . ID=Merlin_1_mRNA;Parent=Merlin_1;seqid=Merlin;color=#00ff00\n-Merlin GeneMark.hmm exon 2 691 . + . ID=Merlin_1_exon;Parent=Merlin_1_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 2 691 . + 0 ID=Merlin_1_CDS;Parent=Merlin_1_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 752 1039 -339.046618 + . ID=Merlin_2;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 752 1039 . + . ID=Merlin_2_mRNA;Parent=Merlin_2;seqid=Merlin\n-Merlin GeneMark.hmm exon 752 1039 . + . ID=Merlin_2_exon;Parent=Merlin_2_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 752 1039 . + 0 ID=Merlin_2_CDS;Parent=Merlin_2_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 1067 2011 -1229.683915 - . ID=Merlin_3;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 1067 2011 . - . ID=Merlin_3_mRNA;Parent=Merlin_3;seqid=Merlin\n-Merlin GeneMark.hmm exon 1067 2011 . - . ID=Merlin_3_exon;Parent=Merlin_3_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 1067 2011 . - 0 ID=Merlin_3_CDS;Parent=Merlin_3_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 2011 3066 -1335.034872 - . ID=Merlin_4;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 2011 3066 . - . ID=Merlin_4_mRNA;Parent=Merlin_4;seqid=Merlin\n-Merlin GeneMark.hmm exon 2011 3066 . - . ID=Merlin_4_exon;Parent=Merlin_4_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 2011 3066 . - 0 ID=Merlin_4_CDS;Parent=Merlin_4_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 3066 4796 -2177.374893 - . ID=Merlin_5;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 3066 4796 . - . ID=Merlin_5_mRNA;Parent=Merlin_5;seqid=Merlin\n-Merlin GeneMark.hmm exon 3066 4796 . - . ID=Merlin_5_exon;Parent=Merlin_5_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 3066 4796 . - 0 ID=Merlin_5_CDS;Parent=Merlin_5_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 4793 5317 -682.565030 - . ID=Merlin_6;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 4793 5317 . - . ID=Merlin_6_mRNA;Parent=Merlin_6;seqid=Merlin\n-Merlin GeneMark.hmm exon 4793 5317 . - . ID=Merlin_6_exon;Parent=Merlin_6_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 4793 5317 . - 0 ID=Merlin_6_CDS;Parent=Merlin_6_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 5289 6431 -1457.525863 - . ID=Merlin_7;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 5289 6431 . - . ID=Merlin_7_mRNA;Parent=Merlin_7;seqid=Merlin\n-Merlin GeneMark.hmm exon 5289 6431 . - . ID=Merlin_7_exon;Parent=Merlin_7_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 5289 6431 . - 0 ID=Merlin_7_CDS;Parent=Merlin_7_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 6428 7180 -968.015933 - . ID=Merlin_8;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 6428 7180 . - . ID=Merlin_8_mRNA;Parent=Merlin_8;seqid=Merlin\n-Merlin GeneMark.hmm exon 6428 7180 . - . ID=Merlin_8_exon;Parent=Merlin_8_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 6428 7180 . - 0 ID=Merlin_8_CDS;Parent=Merlin_8_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 7228 7857 -809.330137 + . ID=Merlin_9;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 7228 7857 . + . ID=Merlin_9_mRNA;Parent=Merlin_9;seqid=Merlin\n-Merlin GeneMark.hmm exon 7228 7857 . + . ID=Merlin_9_exon;Parent=Merlin_9_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 7228 7857 . + 0 ID=Merlin_9_CDS;Parent=Merlin_9_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 7857 8252 -515.006678 + . ID=Merlin_10;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 7857 8252 . + . ID=Merlin'..b'20.159549 + . ID=Merlin_305;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 168941 169120 . + . ID=Merlin_305_mRNA;Parent=Merlin_305;seqid=Merlin\n-Merlin GeneMark.hmm exon 168941 169120 . + . ID=Merlin_305_exon;Parent=Merlin_305_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 168941 169120 . + 0 ID=Merlin_305_CDS;Parent=Merlin_305_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 169175 171265 -2617.092758 + . ID=Merlin_306;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 169175 171265 . + . ID=Merlin_306_mRNA;Parent=Merlin_306;seqid=Merlin\n-Merlin GeneMark.hmm exon 169175 171265 . + . ID=Merlin_306_exon;Parent=Merlin_306_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 169175 171265 . + 0 ID=Merlin_306_CDS;Parent=Merlin_306_exon;seqid=Merlin\n-Merlin GeneMark.hmm gene 171301 172788 -1876.322043 + . ID=Merlin_307;seqid=Merlin\n-Merlin GeneMark.hmm mRNA 171301 172788 . + . ID=Merlin_307_mRNA;Parent=Merlin_307;seqid=Merlin\n-Merlin GeneMark.hmm exon 171301 172788 . + . ID=Merlin_307_exon;Parent=Merlin_307_mRNA;seqid=Merlin\n-Merlin GeneMark.hmm CDS 171301 172788 . + 0 ID=Merlin_307_CDS;Parent=Merlin_307_exon;seqid=Merlin\n+Merlin GeneMark.hmm gene 10 30 . + . ID=Merlin_1;seqid=Merlin\n+Merlin GeneMark.hmm mRNA 14 30 . + . ID=Merlin_1_mRNA;Parent=Merlin_1\n+Merlin GeneMark.hmm CDS 14 20 1000 + 0 ID=Merlin_1_CDS ;Parent=Merlin_1_mRNA\n+Merlin GeneMark.hmm CDS 24 30 500 + 0 ID=Merlin_1_CDS ;Parent=Merlin_1_mRNA\n+Merlin GeneMark.hmm gene 14 30 . + . ID=Merlin_2;seqid=Merlin;color=#00ff00\n+Merlin GeneMark.hmm mRNA 14 30 . + . ID=Merlin_2_mRNA;seqid=Merlin;color=#00ff00;Parent=Merlin_2\n+Merlin GeneMark.hmm CDS 14 20 500 + 0 ID=Merlin_2_CDS ;Parent=Merlin_2_mRNA;color=#0000ff\n+Merlin GeneMark.hmm CDS 24 30 750 + 0 ID=Merlin_2_CDS ;Parent=Merlin_2_mRNA;color=#00ff00\n+Merlin GeneMark.hmm gene 10 30 . + . ID=Merlin_3;seqid=Merlin\n+Merlin GeneMark.hmm mRNA 14 30 . + . ID=Merlin_3A_mRNA;Parent=Merlin_3;color=#0000ff\n+Merlin GeneMark.hmm CDS 14 18 1000 + 0 ID=Merlin_3A_CDS ;Parent=Merlin_3A_mRNA;color=#0000ff\n+Merlin GeneMark.hmm CDS 20 30 800 + 0 ID=Merlin_3A_CDS ;Parent=Merlin_3A_mRNA;color=#0000ff\n+Merlin GeneMark.hmm mRNA 14 30 . + . ID=Merlin_3B_mRNA;Parent=Merlin_3;color=#0000ff\n+Merlin GeneMark.hmm CDS 14 22 400 + 0 ID=Merlin_3B_CDS ;Parent=Merlin_3B_mRNA;color=#0000ff\n+Merlin GeneMark.hmm CDS 24 30 1000 + 0 ID=Merlin_3B_CDS ;Parent=Merlin_3B_mRNA;color=#0000ff\n+Merlin exonerate gene 1740 2300 . + . Name=Apple3;Note=Gene with two splicing models;ID=1\n+Merlin exonerate mRNA 1740 2300 . + . Name=Apple3-a;Note=mRNA A with both CDSs and UTRs;ID=1A;Parent=1;\n+Merlin exonerate UTR 1740 1799 . + . Parent=1A\n+Merlin exonerate CDS 1900 2080 . + 0 Parent=1A\n+Merlin exonerate CDS 2100 2120 . + 2 Parent=1A\n+Merlin exonerate UTR 2120 2300 . + . Parent=1A\n+Merlin exonerate mRNA 1740 2300 . + . Name=Apple3-b;Note=mRNA B with both CDSs and UTRs;ID=1B;Parent=1;\n+Merlin exonerate UTR 1740 1799 . + . Parent=1B\n+Merlin exonerate CDS 1800 1880 . + 0 Parent=1B\n+Merlin exonerate CDS 1900 1950 . + 1 Parent=1B\n+Merlin exonerate CDS 2100 2120 . + 2 Parent=1B\n+Merlin exonerate UTR 2120 2300 . + . Parent=1B\n+# {\n+# "baseUrl": "http://localhost:8000/out/data/"\n+# "compress": 0,\n+# "label": "Transcript",\n+# "storeClass": "JBrowse/Store/SeqFeature/NCList",\n+# "trackType": "JBrowse/View/Track/CanvasFeatures",\n+# "type": "JBrowse/View/Track/CanvasFeatures",\n+# "urlTemplate": "tracks/42ff9cb16c0509f0abb4a76ce14077bc_0/{refseq}/trackData.json",\n+# }\n' |
| b |
| diff -r 0ec526d2d8c1 -r 4181e97c70a7 test-data/vcf/merlin.vcf --- a/test-data/vcf/merlin.vcf Fri Mar 01 05:15:41 2024 +0000 +++ b/test-data/vcf/merlin.vcf Mon Mar 04 09:47:19 2024 +0000 |
| b |
| @@ -3,21 +3,21 @@ ##source=myImputationProgramV3.1 ##reference=1000GenomesPilot-NCBI36 ##phasing=partial -##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data"> -##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth"> -##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency"> -##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele"> -##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129"> -##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership"> -##FILTER=<ID=q10,Description="Quality below 10"> -##FILTER=<ID=s50,Description="Less than 50% of samples have data"> +##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth"> +##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency"> +##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele"> +##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129"> +##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership"> +##FILTER=<ID=q10,Description="Quality below 10"> +##FILTER=<ID=s50,Description="Less than 50% of samples have data"> ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> -##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality"> -##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> -##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality"> -#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA00001 NA00002 NA00003 -Merlin 170 rs6054257 G A 29 PASS NS=3;DP=14;AF=0.5;DB;H2 GT:GQ:DP:HQ 0|0:48:1:51,51 1|0:48:8:51,51 1/1:43:5:.,. -Merlin 1020 . T A 3 q10 NS=3;DP=11;AF=0.017 GT:GQ:DP:HQ 0|0:49:3:58,50 0|1:3:5:65,3 0/0:41:3 -Merlin 3445 rs6040355 A G,T 67 PASS NS=2;DP=10;AF=0.333,0.667;AA=T;DB GT:GQ:DP:HQ 1|2:21:6:23,27 2|1:2:0:18,2 2/2:35:4 -Merlin 5050 . T . 47 PASS NS=3;DP=13;AA=T GT:GQ:DP:HQ 0|0:54:7:56,60 0|0:48:4:51,51 0/0:61:2 -Merlin 20000 microsat1 GTCT G,GTACT 50 PASS NS=3;DP=9;AA=G GT:GQ:DP 0/1:35:4 0/2:17:2 1/1:40:3 +##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth"> +##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality"> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA00001 NA00002 NA00003 +Merlin 170 rs6054257 G A 29 PASS NS=3;DP=14;AF=0.5;DB;H2 GT:GQ:DP:HQ 0|0:48:1:51,51 1|0:48:8:51,51 1/1:43:5:.,. +Merlin 1020 . T A 3 q10 NS=3;DP=11;AF=0.017 GT:GQ:DP:HQ 0|0:49:3:58,50 0|1:3:5:65,3 0/0:41:3 +Merlin 3445 rs6040355 A G,T 67 PASS NS=2;DP=10;AF=0.333,0.667;AA=T;DB GT:GQ:DP:HQ 1|2:21:6:23,27 2|1:2:0:18,2 2/2:35:4 +Merlin 5050 . T . 47 PASS NS=3;DP=13;AA=T GT:GQ:DP:HQ 0|0:54:7:56,60 0|0:48:4:51,51 0/0:61:2 +Merlin 20000 microsat1 GTCT G,GTACT 50 PASS NS=3;DP=9;AA=G GT:GQ:DP 0/1:35:4 0/2:17:2 1/1:40:3 |