Merge pull request #9939 from abretaud/blastdbv5

Add BLASTDBv5 datatype (for blast >=2.8.1)
galaxyproject · Sep 8, 2020 · 511c3e6 · 511c3e6
2 parents 195f333 + 74aa97f
commit 511c3e6
Show file tree

Hide file tree

Showing 2 changed files with 75 additions and 0 deletions.
diff --git a/lib/galaxy/config/sample/datatypes_conf.xml.sample b/lib/galaxy/config/sample/datatypes_conf.xml.sample
@@ -743,6 +743,9 @@
     <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"/>
     <datatype extension="blastdbd" type="galaxy.datatypes.blast:BlastDomainDb" mimetype="text/html" display_in_upload="false"/>
+    <datatype extension="blastdbn5" type="galaxy.datatypes.blast:BlastNucDb5" mimetype="text/html" display_in_upload="false"/>
+    <datatype extension="blastdbp5" type="galaxy.datatypes.blast:BlastProtDb5" mimetype="text/html" display_in_upload="false"/>
+    <datatype extension="blastdbd5" type="galaxy.datatypes.blast:BlastDomainDb5" mimetype="text/html" display_in_upload="false"/>
     <datatype extension="maskinfo-asn1" type="galaxy.datatypes.data:GenericAsn1" mimetype="text/plain" subclass="true" display_in_upload="true"/>
     <datatype extension="maskinfo-asn1-binary" type="galaxy.datatypes.binary:GenericAsn1Binary" mimetype="application/octet-stream" subclass="true" display_in_upload="true"/>
     <datatype extension="pssm-asn1" type="galaxy.datatypes.data:GenericAsn1" mimetype="text/plain" subclass="true" display_in_upload="true"/>

diff --git a/lib/galaxy/datatypes/blast.py b/lib/galaxy/datatypes/blast.py
@@ -306,3 +306,75 @@ def __init__(self, **kwd):
         self.add_composite_file('blastdb.psi', is_binary=True, optional=True)
         self.add_composite_file('blastdb.rps', is_binary=True, optional=True)
         self.add_composite_file('blastdb.aux', is_binary=True, optional=True)
+
+
+class BlastNucDb5(_BlastDb, Data):
+    """Class for nucleotide BLAST database files."""
+    file_ext = 'blastdbn5'
+    allow_datatype_change = False
+    composite_type = 'basic'
+
+    def __init__(self, **kwd):
+        Data.__init__(self, **kwd)
+        self.add_composite_file('blastdb.nhr', is_binary=True)  # sequence headers
+        self.add_composite_file('blastdb.nin', is_binary=True)  # index file
+        self.add_composite_file('blastdb.nsq', is_binary=True)  # nucleotide sequences
+        self.add_composite_file('blastdb.nal', is_binary=False, optional=True)  # alias ( -gi_mask option of makeblastdb)
+        self.add_composite_file('blastdb.nhd', is_binary=True, optional=True)  # sorted sequence hash values ( -hash_index option of makeblastdb)
+        self.add_composite_file('blastdb.nhi', is_binary=True, optional=True)  # index of sequence hash values ( -hash_index option of makeblastdb)
+        self.add_composite_file('blastdb.nnd', is_binary=True, optional=True)  # sorted GI values ( -parse_seqids option of makeblastdb and gi present in the description lines)
+        self.add_composite_file('blastdb.nni', is_binary=True, optional=True)  # index of GI values ( -parse_seqids option of makeblastdb and gi present in the description lines)
+        self.add_composite_file('blastdb.nog', is_binary=True, optional=True)  # OID->GI lookup file ( -hash_index or -parse_seqids option of makeblastdb)
+        self.add_composite_file('blastdb.nsd', is_binary=True, optional=True)  # sorted sequence accession values ( -hash_index or -parse_seqids option of makeblastdb)
+        self.add_composite_file('blastdb.nsi', is_binary=True, optional=True)  # index of sequence accession values ( -hash_index or -parse_seqids option of makeblastdb)
+#        self.add_composite_file('blastdb.00.idx', is_binary=True, optional=True)  # first volume of the MegaBLAST index generated by makembindex
+# The previous line should be repeated for each index volume, with filename extensions like '.01.idx', '.02.idx', etc.
+        self.add_composite_file('blastdb.shd', is_binary=True, optional=True)  # MegaBLAST index superheader (-old_style_index false option of makembindex)
+#        self.add_composite_file('blastdb.naa', is_binary=True, optional=True)  # index of a WriteDB column for e.g. mask data
+#        self.add_composite_file('blastdb.nab', is_binary=True, optional=True)  # data of a WriteDB column
+#        self.add_composite_file('blastdb.nac', is_binary=True, optional=True)  # multiple byte order for a WriteDB column
+# The previous 3 lines should be repeated for each WriteDB column, with filename extensions like ('.nba', '.nbb', '.nbc'), ('.nca', '.ncb', '.ncc'), etc.
+
+
+class BlastProtDb5(_BlastDb, Data):
+    """Class for protein BLAST database files."""
+    file_ext = 'blastdbp5'
+    allow_datatype_change = False
+    composite_type = 'basic'
+
+    def __init__(self, **kwd):
+        Data.__init__(self, **kwd)
+# Component file comments are as in BlastNucDb except where noted
+        self.add_composite_file('blastdb.phr', is_binary=True)
+        self.add_composite_file('blastdb.pin', is_binary=True)
+        self.add_composite_file('blastdb.psq', is_binary=True)  # protein sequences
+        self.add_composite_file('blastdb.phd', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.phi', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.pnd', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.pni', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.pog', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.psd', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.psi', is_binary=True, optional=True)
+#        self.add_composite_file('blastdb.paa', is_binary=True, optional=True)
+#        self.add_composite_file('blastdb.pab', is_binary=True, optional=True)
+#        self.add_composite_file('blastdb.pac', is_binary=True, optional=True)
+# The last 3 lines should be repeated for each WriteDB column, with filename extensions like ('.pba', '.pbb', '.pbc'), ('.pca', '.pcb', '.pcc'), etc.
+
+
+class BlastDomainDb5(_BlastDb, Data):
+    """Class for domain BLAST database files."""
+    file_ext = 'blastdbd5'
+    allow_datatype_change = False
+    composite_type = 'basic'
+
+    def __init__(self, **kwd):
+        Data.__init__(self, **kwd)
+        self.add_composite_file('blastdb.phr', is_binary=True)
+        self.add_composite_file('blastdb.pin', is_binary=True)
+        self.add_composite_file('blastdb.psq', is_binary=True)
+        self.add_composite_file('blastdb.freq', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.loo', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.psd', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.psi', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.rps', is_binary=True, optional=True)
+        self.add_composite_file('blastdb.aux', is_binary=True, optional=True)