# HG changeset patch
# User jjohnson
# Date 1403645531 14400
# Node ID 926c8f02b3ba5cded4231b9038f8bbdbb990061e

Uploaded

diff -r 000000000000 -r 926c8f02b3ba datatypes_conf.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/datatypes_conf.xml	Tue Jun 24 17:32:11 2014 -0400
@@ -0,0 +1,10 @@
+<?xml version="1.0"?>
+<datatypes>
+    <datatype_files>
+        <datatype_file name="snpeff.py"/>
+    </datatype_files>
+    <registration>
+        <datatype extension="snpeffdb" type="galaxy.datatypes.snpeff:SnpEffDb" display_in_upload="True"/>
+    </registration>
+</datatypes>
+
diff -r 000000000000 -r 926c8f02b3ba lib/galaxy/datatypes/snpeff.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lib/galaxy/datatypes/snpeff.py	Tue Jun 24 17:32:11 2014 -0400
@@ -0,0 +1,48 @@
+"""
+SnpEff datatypes
+"""
+import os,os.path,re,sys,gzip,logging
+import galaxy.datatypes.data
+from galaxy.datatypes.data import Text
+from galaxy.datatypes.metadata import MetadataElement
+
+log = logging.getLogger(__name__)
+
+class SnpEffDb( Text ):
+    """Class describing a SnpEff genome build"""
+    file_ext = "snpeffdb"
+    MetadataElement( name="genome_version", default=None, desc="Genome Version", readonly=True, visible=True, no_value=None )
+    MetadataElement( name="regulation", default=[], desc="Regulation Names", readonly=True, visible=True, no_value=[] )
+    MetadataElement( name="annotation", default=[], desc="Annotation Names", readonly=True, visible=True, no_value=[] )
+
+    def __init__( self, **kwd ):
+        Text.__init__( self, **kwd )
+
+    def set_meta( self, dataset, **kwd ):
+        Text.set_meta(self, dataset, **kwd )
+        data_dir = dataset.extra_files_path
+        ## search data_dir/genome_version for files
+        regulation_pattern = 'regulation_(.+).bin'
+        #  annotation files that are included in snpEff by a flag
+        annotations_dict = {'nextProt.bin' : '-nextprot','motif.bin': '-motif'}
+        regulations = []
+        annotations = []
+        if data_dir and os.path.isdir(data_dir):
+            for root, dirs, files in os.walk(data_dir):
+                for fname in files:
+                    if fname.startswith('snpEffectPredictor'):
+                        # if snpEffectPredictor.bin download succeeded
+                        genome_version = os.path.basename(root)
+                        dataset.metadata.genome_version = genome_version
+                    else:
+                        m = re.match(regulation_pattern,fname)
+                        if m:
+                            name = m.groups()[0]
+                            regulations.append(name)
+                        elif fname in annotations_dict:
+                            value = annotations_dict[fname]
+                            name = value.lstrip('-')
+                            annotations.append(name)
+            dataset.metadata.regulation = regulations
+            dataset.metadata.annotation = annotations
+