Mercurial > repos > fubar > jbrowse2

comparison jbrowse2.py @ 56:c0097a584a8a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/usegalaxy-eu/temporary-tools/tree/master/jbrowse2 commit 4b5df41484f6bdf316edaf95b53c92d328ec1674
author fubar
date Tue, 19 Mar 2024 02:33:40 +0000
parents 469c0f6d87d7
children 94264fe60478
comparison
equal deleted inserted replaced
55:469c0f6d87d7 56:c0097a584a8a
17 from collections import defaultdict 17 from collections import defaultdict
18 18
19 logging.basicConfig(level=logging.INFO) 19 logging.basicConfig(level=logging.INFO)
20 log = logging.getLogger("jbrowse") 20 log = logging.getLogger("jbrowse")
21 21
22 JB2VER = "v2.10.2" 22 JB2VER = "v2.10.3"
23 # version pinned for cloning 23 # version pinned for cloning
24 24
25 TODAY = datetime.datetime.now().strftime("%Y-%m-%d") 25 TODAY = datetime.datetime.now().strftime("%Y-%m-%d")
26 GALAXY_INFRASTRUCTURE_URL = None 26 GALAXY_INFRASTRUCTURE_URL = None
27 27
469 genome_name # first one for all tracks - other than paf 469 genome_name # first one for all tracks - other than paf
470 ) 470 )
471 self.genome_sequence_adapter = assem["sequence"]["adapter"] 471 self.genome_sequence_adapter = assem["sequence"]["adapter"]
472 self.genome_firstcontig = None 472 self.genome_firstcontig = None
473 if not useuri: 473 if not useuri:
474 # https://lazarus.name/jbrowse/fish/bigwig_0_coverage_bedgraph_cov_count_count_bw.bigwig
475 # https://lazarus.name/jbrowse/fish/klBraLanc5.haps_combined.decontam.20230620.fasta.fa.gz
476 fl = open(fapath, "r").readline() 474 fl = open(fapath, "r").readline()
477 fls = fl.strip().split(">") 475 fls = fl.strip().split(">")
478 if len(fls) > 1: 476 if len(fls) > 1:
479 fl = fls[1] 477 fl = fls[1]
480 if len(fl.split()) > 1: 478 if len(fl.split()) > 1:
604 useuri = trackData["useuri"].lower() == "yes" 602 useuri = trackData["useuri"].lower() == "yes"
605 if useuri: 603 if useuri:
606 uri = data 604 uri = data
607 else: 605 else:
608 uri = trackData["hic_url"] 606 uri = trackData["hic_url"]
607 categ = trackData['category']
609 trackDict = { 608 trackDict = {
610 "type": "HicTrack", 609 "type": "HicTrack",
611 "trackId": tId, 610 "trackId": tId,
612 "name": uri, 611 "name": uri,
613 "assemblyNames": [self.genome_name], 612 "assemblyNames": [self.genome_name],
613 "category": [categ,],
614 "adapter": { 614 "adapter": {
615 "type": "HicAdapter", 615 "type": "HicAdapter",
616 "hicLocation": uri, 616 "hicLocation": uri,
617 }, 617 },
618 "displays": [ 618 "displays": [
641 "name": "MafViewer", 641 "name": "MafViewer",
642 "url": "https://unpkg.com/jbrowse-plugin-mafviewer/dist/jbrowse-plugin-mafviewer.umd.production.min.js", 642 "url": "https://unpkg.com/jbrowse-plugin-mafviewer/dist/jbrowse-plugin-mafviewer.umd.production.min.js",
643 } 643 }
644 ] 644 ]
645 } 645 }
646 646 categ = trackData['category']
647 fname = "%s.bed" % tId 647 fname = "%s.bed" % tId
648 dest = "%s/%s" % (self.outdir, fname) 648 dest = "%s/%s" % (self.outdir, fname)
649 gname = self.genome_name 649 gname = self.genome_name
650 cmd = [ 650 cmd = [
651 "bash", 651 "bash",
667 samples = [x.split(".")[0] for x in samp] 667 samples = [x.split(".")[0] for x in samp]
668 trackDict = { 668 trackDict = {
669 "type": "MafTrack", 669 "type": "MafTrack",
670 "trackId": tId, 670 "trackId": tId,
671 "name": trackData["name"], 671 "name": trackData["name"],
672 "category": [categ,],
672 "adapter": { 673 "adapter": {
673 "type": "MafTabixAdapter", 674 "type": "MafTabixAdapter",
674 "samples": samples, 675 "samples": samples,
675 "bedGzLocation": { 676 "bedGzLocation": {
676 "uri": fname + ".sorted.bed.gz", 677 "uri": fname + ".sorted.bed.gz",
736 url = "%s.gff3" % trackData["label"] 737 url = "%s.gff3" % trackData["label"]
737 dest = "%s/%s" % (self.outdir, url) 738 dest = "%s/%s" % (self.outdir, url)
738 self._sort_gff(gff3, dest) 739 self._sort_gff(gff3, dest)
739 url = url + ".gz" 740 url = url + ".gz"
740 tId = trackData["label"] 741 tId = trackData["label"]
742 categ = trackData['category']
741 trackDict = { 743 trackDict = {
742 "type": "FeatureTrack", 744 "type": "FeatureTrack",
743 "trackId": tId, 745 "trackId": tId,
744 "name": trackData["name"], 746 "name": trackData["name"],
745 "assemblyNames": [self.genome_name], 747 "assemblyNames": [self.genome_name],
748 "category": [categ,],
746 "adapter": { 749 "adapter": {
747 "type": "Gff3TabixAdapter", 750 "type": "Gff3TabixAdapter",
748 "gffGzLocation": { 751 "gffGzLocation": {
749 "uri": url, 752 "uri": url,
750 }, 753 },
789 dest = os.path.join(self.outdir, url) 792 dest = os.path.join(self.outdir, url)
790 cmd = ["cp", data, dest] 793 cmd = ["cp", data, dest]
791 self.subprocess_check_call(cmd) 794 self.subprocess_check_call(cmd)
792 bwloc = {"uri": url} 795 bwloc = {"uri": url}
793 tId = trackData["label"] 796 tId = trackData["label"]
797 categ = trackData['category']
794 trackDict = { 798 trackDict = {
795 "type": "QuantitativeTrack", 799 "type": "QuantitativeTrack",
796 "trackId": tId, 800 "trackId": tId,
797 "name": trackData["name"], 801 "name": trackData["name"],
802 "category": [categ,],
798 "assemblyNames": [ 803 "assemblyNames": [
799 self.genome_name, 804 self.genome_name,
800 ], 805 ],
801 "adapter": { 806 "adapter": {
802 "type": "BigWigAdapter", 807 "type": "BigWigAdapter",
816 821
817 def add_bam(self, data, trackData, bam_index=None, **kwargs): 822 def add_bam(self, data, trackData, bam_index=None, **kwargs):
818 tId = trackData["label"] 823 tId = trackData["label"]
819 useuri = trackData["useuri"].lower() == "yes" 824 useuri = trackData["useuri"].lower() == "yes"
820 bindex = bam_index 825 bindex = bam_index
826 categ = trackData['category']
821 if useuri: 827 if useuri:
822 url = data 828 url = data
823 else: 829 else:
824 fname = "%s.bam" % trackData["label"] 830 fname = "%s.bam" % trackData["label"]
825 dest = "%s/%s" % (self.outdir, fname) 831 dest = "%s/%s" % (self.outdir, fname)
843 log.warn("Could not find a bam index (.bai file) for %s", data) 849 log.warn("Could not find a bam index (.bai file) for %s", data)
844 trackDict = { 850 trackDict = {
845 "type": "AlignmentsTrack", 851 "type": "AlignmentsTrack",
846 "trackId": tId, 852 "trackId": tId,
847 "name": trackData["name"], 853 "name": trackData["name"],
854 "category": [categ,],
848 "assemblyNames": [self.genome_name], 855 "assemblyNames": [self.genome_name],
849 "adapter": { 856 "adapter": {
850 "type": "BamAdapter", 857 "type": "BamAdapter",
851 "bamLocation": {"uri": url}, 858 "bamLocation": {"uri": url},
852 "index": { 859 "index": {
867 self.tracksToAdd.append(trackDict) 874 self.tracksToAdd.append(trackDict)
868 self.trackIdlist.append(tId) 875 self.trackIdlist.append(tId)
869 876
870 def add_cram(self, data, trackData, cram_index=None, **kwargs): 877 def add_cram(self, data, trackData, cram_index=None, **kwargs):
871 tId = trackData["label"] 878 tId = trackData["label"]
879 categ = trackData['category']
872 useuri = trackData["useuri"].lower() == "yes" 880 useuri = trackData["useuri"].lower() == "yes"
873 if useuri: 881 if useuri:
874 url = data 882 url = data
875 else: 883 else:
876 fname = "%s.cram" % trackData["label"] 884 fname = "%s.cram" % trackData["label"]
890 self.subprocess_check_call(cmd) 898 self.subprocess_check_call(cmd)
891 trackDict = { 899 trackDict = {
892 "type": "AlignmentsTrack", 900 "type": "AlignmentsTrack",
893 "trackId": tId, 901 "trackId": tId,
894 "name": trackData["name"], 902 "name": trackData["name"],
903 "category": [categ,],
895 "assemblyNames": [self.genome_name], 904 "assemblyNames": [self.genome_name],
896 "adapter": { 905 "adapter": {
897 "type": "CramAdapter", 906 "type": "CramAdapter",
898 "cramLocation": {"uri": url}, 907 "cramLocation": {"uri": url},
899 "craiLocation": { 908 "craiLocation": {
917 tId = trackData["label"] 926 tId = trackData["label"]
918 # url = "%s/api/datasets/%s/display" % ( 927 # url = "%s/api/datasets/%s/display" % (
919 # self.giURL, 928 # self.giURL,
920 # trackData["metadata"]["dataset_id"], 929 # trackData["metadata"]["dataset_id"],
921 # ) 930 # )
922 931 categ = trackData['category']
923 useuri = trackData["useuri"].lower() == "yes" 932 useuri = trackData["useuri"].lower() == "yes"
924 if useuri: 933 if useuri:
925 url = data 934 url = data
926 else: 935 else:
927 url = "%s.vcf.gz" % tId 936 url = "%s.vcf.gz" % tId
933 trackDict = { 942 trackDict = {
934 "type": "VariantTrack", 943 "type": "VariantTrack",
935 "trackId": tId, 944 "trackId": tId,
936 "name": trackData["name"], 945 "name": trackData["name"],
937 "assemblyNames": [self.genome_name], 946 "assemblyNames": [self.genome_name],
947 "category": [categ,],
938 "adapter": { 948 "adapter": {
939 "type": "VcfTabixAdapter", 949 "type": "VcfTabixAdapter",
940 "vcfGzLocation": { 950 "vcfGzLocation": {
941 "uri": url 951 "uri": url
942 }, 952 },
991 else: 1001 else:
992 url = "%s.%s.gz" % (trackData["label"], ext) 1002 url = "%s.%s.gz" % (trackData["label"], ext)
993 dest = "%s/%s" % (self.outdir, url) 1003 dest = "%s/%s" % (self.outdir, url)
994 self._sort_gff(data, dest) 1004 self._sort_gff(data, dest)
995 tId = trackData["label"] 1005 tId = trackData["label"]
1006 categ = trackData['category']
996 trackDict = { 1007 trackDict = {
997 "type": "FeatureTrack", 1008 "type": "FeatureTrack",
998 "trackId": tId, 1009 "trackId": tId,
999 "name": trackData["name"], 1010 "name": trackData["name"],
1000 "assemblyNames": [self.genome_name], 1011 "assemblyNames": [self.genome_name],
1012 "category": [categ,],
1001 "adapter": { 1013 "adapter": {
1002 "type": "Gff3TabixAdapter", 1014 "type": "Gff3TabixAdapter",
1003 "gffGzLocation": { 1015 "gffGzLocation": {
1004 "uri": url, 1016 "uri": url,
1005 }, 1017 },
1025 self.tracksToAdd.append(trackDict) 1037 self.tracksToAdd.append(trackDict)
1026 self.trackIdlist.append(tId) 1038 self.trackIdlist.append(tId)
1027 1039
1028 def add_bed(self, data, ext, trackData): 1040 def add_bed(self, data, ext, trackData):
1029 tId = trackData["label"] 1041 tId = trackData["label"]
1042 categ = trackData['category']
1030 useuri = trackData["useuri"].lower() == "yes" 1043 useuri = trackData["useuri"].lower() == "yes"
1031 if useuri: 1044 if useuri:
1032 url = data 1045 url = data
1033 else: 1046 else:
1034 url = "%s.%s.gz" % (trackData["label"], ext) 1047 url = "%s.%s.gz" % (trackData["label"], ext)
1038 "type": "FeatureTrack", 1051 "type": "FeatureTrack",
1039 "trackId": tId, 1052 "trackId": tId,
1040 "name": trackData["name"], 1053 "name": trackData["name"],
1041 "assemblyNames": [self.genome_name], 1054 "assemblyNames": [self.genome_name],
1042 "adapter": { 1055 "adapter": {
1056 "category": [categ,],
1043 "type": "BedTabixAdapter", 1057 "type": "BedTabixAdapter",
1044 "bedGzLocation": { 1058 "bedGzLocation": {
1045 "uri": url, 1059 "uri": url,
1046 }, 1060 },
1047 "index": { 1061 "index": {
1071 self.trackIdlist.append(tId) 1085 self.trackIdlist.append(tId)
1072 1086
1073 def add_paf(self, data, trackData, pafOpts, **kwargs): 1087 def add_paf(self, data, trackData, pafOpts, **kwargs):
1074 tname = trackData["name"] 1088 tname = trackData["name"]
1075 tId = trackData["label"] 1089 tId = trackData["label"]
1090 categ = trackData['category']
1076 pgnames = [x.strip() for x in pafOpts["genome_label"].split(",")] 1091 pgnames = [x.strip() for x in pafOpts["genome_label"].split(",")]
1077 pgpaths = [x.strip() for x in pafOpts["genome"].split(",")] 1092 pgpaths = [x.strip() for x in pafOpts["genome"].split(",")]
1078 passnames = [self.genome_name] # always first 1093 passnames = [self.genome_name] # always first
1079 for i, gname in enumerate(pgnames): 1094 for i, gname in enumerate(pgnames):
1080 if len(gname.split()) > 1: 1095 if len(gname.split()) > 1:
1097 self.symlink_or_copy(os.path.realpath(data), dest) 1112 self.symlink_or_copy(os.path.realpath(data), dest)
1098 trackDict = { 1113 trackDict = {
1099 "type": "SyntenyTrack", 1114 "type": "SyntenyTrack",
1100 "trackId": tId, 1115 "trackId": tId,
1101 "assemblyNames": passnames, 1116 "assemblyNames": passnames,
1117 "category": [categ,],
1102 "name": tname, 1118 "name": tname,
1103 "adapter": { 1119 "adapter": {
1104 "type": "PAFAdapter", 1120 "type": "PAFAdapter",
1105 "pafLocation": {"uri": url}, 1121 "pafLocation": {"uri": url},
1106 "assemblyNames": passnames, 1122 "assemblyNames": passnames,
1107 }, 1123 },
1108 # "displays": [ 1124 "displays": [
1109 # { 1125 {
1110 # "type": "LinearSyntenyDisplay", 1126 "type": "LinearSyntenyDisplay",
1111 # "displayId": "%s-LinearSyntenyDisplay" % tId, 1127 "displayId": "%s-LinearSyntenyDisplay" % tId,
1112 # }, 1128 },
1113 # { 1129 {
1114 # "type": "DotPlotDisplay", 1130 "type": "DotPlotDisplay",
1115 # "displayId": "%s-DotPlotDisplay" % tId, 1131 "displayId": "%s-DotPlotDisplay" % tId,
1116 # }, 1132 },
1117 # ], 1133 ],
1118 } 1134 }
1119 style_json = self._prepare_track_style(trackDict) 1135 style_json = self._prepare_track_style(trackDict)
1120 trackDict["style"] = style_json 1136 trackDict["style"] = style_json
1121 self.tracksToAdd.append(trackDict) 1137 self.tracksToAdd.append(trackDict)
1122 self.trackIdlist.append(tId) 1138 self.trackIdlist.append(tId)
1360 config_json["configuration"].update(config_data) 1376 config_json["configuration"].update(config_data)
1361 self.config_json.update(config_json) 1377 self.config_json.update(config_json)
1362 with open(config_path, "w") as config_file: 1378 with open(config_path, "w") as config_file:
1363 json.dump(self.config_json, config_file, indent=2) 1379 json.dump(self.config_json, config_file, indent=2)
1364 1380
1365 def clone_jbrowse(self): 1381 def clone_jbrowse(self, realclone=True):
1366 """Clone a JBrowse directory into a destination directory. This also works in Biocontainer testing now""" 1382 """Clone a JBrowse directory into a destination directory. This also works in Biocontainer testing now"""
1367 dest = self.outdir 1383 dest = self.outdir
1368 # self.subprocess_check_call(['jbrowse', 'create', dest, '--tag', f"{JB_VER}"]) 1384 if realclone:
1369 shutil.copytree(self.jbrowse2path, dest, dirs_exist_ok=True) 1385 self.subprocess_check_call(['jbrowse', 'create', dest,"-f", '--tag', f"{JB2VER}"])
1386 else:
1387 shutil.copytree(self.jbrowse2path, dest, dirs_exist_ok=True)
1370 for fn in [ 1388 for fn in [
1371 "asset-manifest.json", 1389 "asset-manifest.json",
1372 "favicon.ico", 1390 "favicon.ico",
1373 "robots.txt", 1391 "robots.txt",
1374 "umd_plugin.js", 1392 "umd_plugin.js",