add refbed format

lidaof · Oct 15, 2018 · 12da7da · 12da7da
1 parent 8dedc2a
commit 12da7da
Show file tree

Hide file tree

Showing 3 changed files with 42 additions and 8 deletions.
diff --git a/docs/conf.py b/docs/conf.py
@@ -20,8 +20,8 @@
 # -- Project information -----------------------------------------------------
 
 project = 'WashU Epigenome Browser'
-copyright = '2018, Daofeng Li, Silas Hsu, Renee Sears and Ting Wang'
-author = 'Daofeng Li, Silas Hsu, Renee Sears and Ting Wang'
+copyright = '2018, Daofeng Li, Silas Hsu, Renee L. Sears and Ting Wang'
+author = 'Daofeng Li, Silas Hsu, Renee L. Sears and Ting Wang'
 
 # The short X.Y version
 version = ''
@@ -134,7 +134,7 @@
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
     (master_doc, 'WashUEpigenomeBrowser.tex', 'WashU Epigenome Browser Documentation',
-     'Daofeng Li, Silas Hsu, Renee Sears and Ting Wang', 'manual'),
+     'Daofeng Li, Silas Hsu, Renee L. Sears and Ting Wang', 'manual'),
 ]
 
 
@@ -155,8 +155,8 @@
 #  dir menu entry, description, category)
 texinfo_documents = [
     (master_doc, 'WashUEpigenomeBrowser', 'WashU Epigenome Browser Documentation',
-     author, 'WashUEpigenomeBrowser', 'One line description of project.',
-     'Miscellaneous'),
+     author, 'WashUEpigenomeBrowser', 'WashU Epigenome Browser Documentation.',
+     'Genomics'),
 ]
 
 

diff --git a/docs/datahub.rst b/docs/datahub.rst
@@ -198,6 +198,17 @@ Example bed track
         "url": "https://epgg-test.wustl.edu/d/mm10/mm10_cpgIslands.bed.gz"
     }
 
+Example refbed track
+--------------------
+
+.. code-block:: json
+
+    {
+        "type": "refbed",
+        "name": "mm10 gencode basic",
+        "url": "https://wangftp.wustl.edu/~rsears/FOR_DAOFENG/gencodeM18_load_basic_Gene.bed.gz"
+    }
+
 Example HiC track
 -----------------
 
@@ -250,6 +261,7 @@ type
 * hic
 * bed
 * bigbed
+* refbed
 * repeatmasker
 * geneAnnotation
 * genomealign

diff --git a/docs/tracks.rst b/docs/tracks.rst
@@ -82,7 +82,7 @@ Here is an example command::
 .. _`coordinate sorting and indexing of bam files`: http://www.htslib.org/doc/samtools.html
 
 Annotation Tracks
-----------------
+-----------------
 
 Annotation tracks represent genomic features or intervals across the genome. 
 Popular examples include SNP files, CpG Island files, and blacklisted regions.
@@ -116,6 +116,28 @@ is reserved for the strand. All other columns are ignored, but can be present in
 
 This format needs to be compressed by bgzip and indexed by tabix for submission as a track. See `Prepare track files`_.
 
+refbed
+~~~~~~
+
+``refbed`` format files allow you to upload custom gene annotation track. It's like
+refGene bed like file downloaded from UCSC but with slightly modifications. Each of
+this format contains (each column is separated by *Tab*):
+
+    chr, transript_start, transript_stop, translation_start,stranslation_stop, strand, gene_name, transcript_id, type, exons(including UTRs) start, exons(including UTRs) stops, additional gene info
+
+Example lines::
+
+    chr1    3073253 3074322 3073253 3074322 +       RP23-271O17.1   ENSMUST00000193812.1    TEC     3073253,        3074322,        
+    chr1    3102016 3102125 3102016 3102125 +       Gm26206 ENSMUST00000082908.1    nonCoding       3102016,        3102125,        
+    chr1    3214482 3671498 3216024 3671349 -       Xkr4    ENSMUST00000070533.4    coding  3670552,3421702,3214482,        3671498,3421901,3216968,        Mus musculus X-linked Kx blood group related 4 (Xkr4), mRNA.
+    chr1    3252757 3253236 3252757 3253236 +       RP23-317L18.1   ENSMUST00000192857.1    pseudo  3252757,        3253236, 
+
+.. note:: Last column is optional, dislayed as gene description when you click a gene on the track.
+          This format can be easily obtain from refGene.bed file downloaded from UCSC, or converted from
+          a GTF or GFF3 format file. Check out our scripts_ for help on converting file to this format.
+
+.. _scripts: https://github.com/lidaof/eg-react/tree/master/backend/scripts
+
 Numerical Tracks
 ----------------
 
@@ -159,8 +181,8 @@ This format needs to be compressed by bgzip and indexed by tabix for submission
 Read Alignment BAM Tracks
 -------------------------
 
-BAM 
-~~~~
+BAM
+~~~
 
 The ``BAM`` format is a compressed SAM format used to store sequence alignment data.
 Please check the `Samtools Documentation`_ page to learn more about this format and how to manipulate these files.