changeset 54:d6b0feb22584 draft

planemo upload for repository https://github.com/usegalaxy-eu/temporary-tools/tree/master/jbrowse2 commit 53aab6394c715dc2d7fdd9188d6c9834e0516b5c
author fubar
date Thu, 14 Mar 2024 00:59:36 +0000
parents bdfa6a7c4543
children 469c0f6d87d7
files __pycache__/jbrowse2.cpython-310.pyc jbrowse2.py jbrowse2.xml readme.rst repeathumfish.txt
diffstat 5 files changed, 119 insertions(+), 5 deletions(-) [+]
line wrap: on
line diff
Binary file __pycache__/jbrowse2.cpython-310.pyc has changed
--- a/jbrowse2.py	Thu Mar 07 09:23:06 2024 +0000
+++ b/jbrowse2.py	Thu Mar 14 00:59:36 2024 +0000
@@ -1085,7 +1085,8 @@
                 # trouble from spacey names in command lines avoidance
                 if gname not in self.genome_names:
                     # ignore if already there - eg for duplicates among pafs.
-                    asstrack = self.make_assembly(pgpaths[i], gname)
+                    useuri = pgpaths[i].startswith('http://') or pgpaths[i].startswith('https://')
+                    asstrack = self.make_assembly(pgpaths[i], gname, useuri)
                     self.genome_names.append(gname)
                     if self.config_json.get("assemblies", None):
                         self.config_json["assemblies"].append(asstrack)
--- a/jbrowse2.xml	Thu Mar 07 09:23:06 2024 +0000
+++ b/jbrowse2.xml	Thu Mar 14 00:59:36 2024 +0000
@@ -1,4 +1,4 @@
- <tool id="jbrowse2" name="jbrowse2" version="@TOOL_VERSION@+@WRAPPER_VERSION@_6" profile="22.05">
+ <tool id="jbrowse2" name="jbrowse2" version="@TOOL_VERSION@+@WRAPPER_VERSION@_7" profile="22.05">
     <description>genome browser</description>
     <macros>
         <import>macros.xml</import>
@@ -81,7 +81,7 @@
               <genome path="${reference_genome.genome.fields.path}" label="${reference_genome.genome.fields.name}" useuri="no">
                   <metadata>
                      <dataset
-                      dname = "${reference_genome.genome.refname}" />
+                      dname = "${reference_genome.genome.fields.name}" />
                   </metadata>
               </genome>
             #else
@@ -320,8 +320,8 @@
                         <option value="bed">BED track</option>
                         <option value="bigwig">BigWig track</option>
                         <option value="blastxml">Blast XML track - converted to GFF</option>
+                        <option value="cool">HiC as cool/mcool/scool format files</option>
                         <option value="cram">CRAM</option>
-                        <option value="cool">HiC as cool/mcool/scool format files</option>
                         <option value="gff">GFF/GFF3 feature track</option>
                         <option value="hic">HiC as juicebox_hic format file. Tabular hic_matrix will NOT work.</option>
                         <option value="maf">Multiple alignment format. Reference name must match the MAF name exactly to work correctly</option>
--- a/readme.rst	Thu Mar 07 09:23:06 2024 +0000
+++ b/readme.rst	Thu Mar 14 00:59:36 2024 +0000
@@ -1,5 +1,12 @@
 JBrowse2 in Galaxy
 ==================
+Added Mar 8:
+ - URI as data source for tracks
+ - Autogenerate from a collection now builtin to advanced options - ignores form
+    - potentially thousands of tracks without filling in any form...
+ - Cram now working
+ - Multigenome pafs from mashmap working properly..
+ - TODO reuse code for references for paf references to allow URI and builtin genomes
 
 Added Mar 3:
  - optional tracks at last for JB2
@@ -24,7 +31,7 @@
 JBrowse2 is a fast, embeddable genome browser built completely with
 JavaScript and HTML5
 
-Thus, it makes an ideal fit with Galaxy, especially for use as a
+Makes an ideal fit with Galaxy, especially for use as a
 workflow summary. E.g. annotate a genome, then visualise all of the
 associated datasets as an interactive HTML page. This tool MUST be whitelisted
 (or ``sanitize_all_html=False`` in galaxy.ini) to function correctly.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/repeathumfish.txt	Thu Mar 14 00:59:36 2024 +0000
@@ -0,0 +1,106 @@
+     Calypte Anna
+
+     ==================================================
+     file name: rm_input.fasta
+     sequences:           159
+     total length: 1059687259 bp  (1043590636 bp excl N/X-runs)
+     GC level:         41.49 %
+     bases masked:   79638300 bp ( 7.63 %)
+     ==================================================
+                    number of      length   percentage
+                    elements*    occupied  of sequence
+     --------------------------------------------------
+     SINEs:            32491      3044030 bp    0.29 %
+           ALUs            0            0 bp    0.00 %
+           MIRs        23309      1792450 bp    0.17 %
+
+     LINEs:           168150     56100653 bp    5.38 %
+           LINE1         446        51456 bp    0.00 %
+           LINE2        3520       419909 bp    0.04 %
+           L3/CR1     161974     55206716 bp    5.29 %
+
+     LTR elements:      3415      1802798 bp    0.17 %
+           ERVL          649       266145 bp    0.03 %
+           ERVL-MaLRs     15          814 bp    0.00 %
+           ERV_classI   1341       795364 bp    0.08 %
+           ERV_classII  1159       705705 bp    0.07 %
+
+     DNA elements:     12073      1651025 bp    0.16 %
+          hAT-Charlie    338        55376 bp    0.01 %
+          TcMar-Tigger   787        83392 bp    0.01 %
+
+     Unclassified:      3325       445147 bp    0.04 %
+
+     Total interspersed repeats: 63043653 bp    6.04 %
+
+
+     Small RNA:         5543       745245 bp    0.07 %
+
+     Satellites:         109         8273 bp    0.00 %
+     Simple repeats:  284418     12956749 bp    1.24 %
+     Low complexity:   61652      3494878 bp    0.33 %
+     ==================================================
+
+     * most repeats fragmented by insertions or deletions
+       have been counted as one element
+       Runs of >=20 X/Ns in query were excluded in % calcs
+
+
+     The query species was assumed to be homo sapiens
+     RepeatMasker version 4.1.5 , default mode
+
+     run with rmblastn version 2.13.0+
+     FamDB: CONS-Dfam_3.7
+
+Amphioxus
+==================================================
+file name: rm_input.fasta
+sequences:            96
+total length:  458494623 bp  (458485423 bp excl N/X-runs)
+GC level:         41.61 %
+bases masked:    9756877 bp ( 2.13 %)
+==================================================
+               number of      length   percentage
+               elements*    occupied  of sequence
+--------------------------------------------------
+SINEs:            10212       946135 bp    0.21 %
+      ALUs            0            0 bp    0.00 %
+      MIRs         5121       527992 bp    0.12 %
+
+LINEs:             4019       622661 bp    0.14 %
+      LINE1         179        11937 bp    0.00 %
+      LINE2         662        63166 bp    0.01 %
+      L3/CR1       2144       286741 bp    0.06 %
+
+LTR elements:       689       138371 bp    0.03 %
+      ERVL           20         1005 bp    0.00 %
+      ERVL-MaLRs      4          322 bp    0.00 %
+      ERV_classI    584       118702 bp    0.03 %
+      ERV_classII    28         1778 bp    0.00 %
+
+DNA elements:       850        57478 bp    0.01 %
+     hAT-Charlie     46         2708 bp    0.00 %
+     TcMar-Tigger    73         5236 bp    0.00 %
+
+Unclassified:       517        41430 bp    0.01 %
+
+Total interspersed repeats:  1806075 bp    0.39 %
+
+
+Small RNA:         5487       857233 bp    0.19 %
+
+Satellites:         629        50630 bp    0.01 %
+Simple repeats:  115914      6556304 bp    1.43 %
+Low complexity:    9124       485904 bp    0.11 %
+==================================================
+
+* most repeats fragmented by insertions or deletions
+  have been counted as one element
+  Runs of >=20 X/Ns in query were excluded in % calcs
+
+
+The query species was assumed to be homo sapiens
+RepeatMasker version 4.1.5 , default mode
+
+run with rmblastn version 2.13.0+
+FamDB: CONS-Dfam_3.7