Mercurial > repos > devteam > blast_datatypes

changeset 4:f9a7783ed7b6 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.0.14 adding BLAST database support. See also the matching update for the NCBI BLAST+ wrappers which use these new definitions. This update included work by Edward Kirton.
author peterjc
date Fri, 09 Nov 2012 06:50:05 -0500
parents 6ef523b390e0
children b3a3ba0c1d47
files blast.py blast_datatypes.txt datatypes_conf.xml
diffstat 3 files changed, 112 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/blast.py	Thu Sep 20 10:13:16 2012 -0400
+++ b/blast.py	Fri Nov 09 06:50:05 2012 -0500
@@ -3,8 +3,9 @@
 """
 
 from galaxy.datatypes.data import get_file_peek
-from galaxy.datatypes.data import Text
+from galaxy.datatypes.data import Text, Data
 from galaxy.datatypes.xml import GenericXml
+from galaxy.datatypes.metadata import MetadataElement
 
 class BlastXml( GenericXml ):
     """NCBI Blast XML Output data"""
@@ -18,6 +19,7 @@
         else:
             dataset.peek = 'file does not exist'
             dataset.blurb = 'file purged from disk'
+
     def sniff( self, filename ):
         """
         Determines whether the file is blastxml
@@ -55,6 +57,9 @@
         if len(split_files) == 1:
             #For one file only, use base class method (move/copy)
             return Text.merge(split_files, output_file)
+        if not split_files:
+            raise ValueError("Given no BLAST XML files, %r, to merge into %s" \
+                             % (split_files, output_file))
         out = open(output_file, "w")
         h = None
         for f in split_files:
@@ -122,3 +127,98 @@
         out.close()
     merge = staticmethod(merge)
 
+
+class _BlastDb(object):
+    """Base class for BLAST database datatype."""
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text."""
+        if not dataset.dataset.purged:
+            dataset.peek  = "BLAST database (multiple files)"
+            dataset.blurb = "BLAST database (multiple files)"
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def display_peek( self, dataset ):
+        """Create HTML content, used for displaying peek."""
+        try:
+            return dataset.peek
+        except:
+            return "BLAST database (multiple files)"
+
+    def display_data(self, trans, data, preview=False, filename=None,
+                     to_ext=None, size=None, offset=None, **kwd):
+        """Apparently an old display method, but still gets called.
+
+        This allows us to format the data shown in the central pane via the "eye" icon.
+        """
+        return "This is a BLAST database."
+
+    def get_mime(self):
+        """Returns the mime type of the datatype (pretend it is text for peek)"""
+        return 'text/plain'
+
+    def merge(split_files, output_file):
+        """Merge BLAST databases (not implemented for now)."""
+        raise NotImplementedError("Merging BLAST databases is non-trivial (do this via makeblastdb?)")
+
+    def split( cls, input_datasets, subdir_generator_function, split_params):
+        """Split a BLAST database (not implemented for now)."""
+        if split_params is None:
+            return None
+        raise NotImplementedError("Can't split BLAST databases")
+
+
+class BlastNucDb( _BlastDb, Data ):
+    """Class for nucleotide BLAST database files."""
+    file_ext = 'blastdbn'
+    composite_type ='basic'
+    MetadataElement( readonly=True, optional=True, visible=False, no_value=0 )
+
+    def __init__(self,**kwd):
+        Data.__init__(self, **kwd)
+        self.add_composite_file('blastdb.nhr')
+        self.add_composite_file('blastdb.nin')
+        self.add_composite_file('blastdb.nsq')
+        self.add_composite_file('blastdb.nhd', optional=True)
+        self.add_composite_file('blastdb.nsi', optional=True)
+        self.add_composite_file('blastdb.nhi', optional=True)
+        self.add_composite_file('blastdb.nog', optional=True)
+        self.add_composite_file('blastdb.nsd', optional=True)
+
+    def display_data(self, trans, data, preview=False, filename=None,
+                     to_ext=None, size=None, offset=None, **kwd):
+        """Apparently an old display method, but still gets called.
+
+        This allows us to format the data shown in the central pane via the "eye" icon.
+        """
+        return "This is a BLAST nucleotide database."
+
+class BlastProtDb( _BlastDb, Data ):
+    """Class for protein BLAST database files."""
+    file_ext = 'blastdbp'
+    composite_type ='basic'
+    MetadataElement( readonly=True, optional=True, visible=False, no_value=0 )
+
+    def __init__(self,**kwd):
+        Data.__init__(self, **kwd)
+        self.add_composite_file('blastdb.phr')
+        self.add_composite_file('blastdb.pin')
+        self.add_composite_file('blastdb.psq')
+        self.add_composite_file('blastdb.pnd', optional=True)
+        self.add_composite_file('blastdb.pni', optional=True)
+        self.add_composite_file('blastdb.psd', optional=True)
+        self.add_composite_file('blastdb.psi', optional=True)
+        self.add_composite_file('blastdb.psq', optional=True)
+        self.add_composite_file('blastdb.phd', optional=True)
+        self.add_composite_file('blastdb.phi', optional=True)
+        self.add_composite_file('blastdb.pog', optional=True)
+
+    def display_data(self, trans, data, preview=False, filename=None,
+                     to_ext=None, size=None, offset=None, **kwd):
+        """Apparently an old display method, but still gets called.
+
+        This allows us to format the data shown in the central pane via the "eye" icon.
+        """
+        return "This is a BLAST protein database."
--- a/blast_datatypes.txt	Thu Sep 20 10:13:16 2012 -0400
+++ b/blast_datatypes.txt	Fri Nov 09 06:50:05 2012 -0500
@@ -21,6 +21,8 @@
 v0.0.11 - Final revision as part of the Galaxy main repository, and the
           first release via the Tool Shed
 v0.0.13 - Uses blast.py instead of xml.py to define the datatypes
+v0.0.14 - Includes datatypes for protein and nucleotide BLAST databases
+          (based on work by Edward Kirton)
 
 
 Installation
@@ -37,9 +39,15 @@
 datatypes_conf.xml entry to be combined with your local configuration.
 
 However, if you really want to this should work for a manual install. Add
-the following line to the datatypes_conf.xml file in the Galaxy main folder:
+the following lines to the datatypes_conf.xml file in the Galaxy main folder:
 
    <datatype extension="blastxml" type="galaxy.datatypes.blast:BlastXml" mimetype="application/xml" display_in_upload="true"/>
+   <datatype extension="blastdbn" type="galaxy.datatypes.blast:BlastNucDb" mimetype="text/html" display_in_upload="false"/>
+   <datatype extension="blastdbp" type="galaxy.datatypes.blast:BlastProtDb" mimetype="text/html" display_in_upload="false"/>
+
+and later in the sniffer section:
+
+    <sniffer type="galaxy.datatypes.blast:BlastXml"/>
 
 Also create the file lib/galaxy/datatypes/blast.py by moving, copying or linking
 the blast.py file provided in this tar-ball.  Finally add 'import blast' near
--- a/datatypes_conf.xml	Thu Sep 20 10:13:16 2012 -0400
+++ b/datatypes_conf.xml	Fri Nov 09 06:50:05 2012 -0500
@@ -5,6 +5,8 @@
     </datatype_files>
     <registration>
         <datatype extension="blastxml" type="galaxy.datatypes.blast:BlastXml" mimetype="application/xml" display_in_upload="true"/>
+        <datatype extension="blastdbn" type="galaxy.datatypes.blast:BlastNucDb" mimetype="text/html" display_in_upload="false"/>
+        <datatype extension="blastdbp" type="galaxy.datatypes.blast:BlastProtDb" mimetype="text/html" display_in_upload="false"/>
     </registration>
     <sniffers>
         <sniffer type="galaxy.datatypes.blast:BlastXml"/>