Mercurial > repos > iuc > msa_datatypes

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/datatypes_conf.xml	Tue Apr 22 13:55:42 2014 -0400
@@ -0,0 +1,18 @@
+<?xml version="1.0"?>
+  <datatypes>
+   <datatype_files>
+     <datatype_file name="msa.py"/>
+   </datatype_files>
+   <registration>
+        <datatype extension="stockholm" type="galaxy.datatypes.msa:Stockholm_1_0" display_in_upload="True" />
+        <datatype extension="selex" type="galaxy.datatypes.data:Text" subclass="True"/>
+        <datatype extension="clustal" type="galaxy.datatypes.data:Text" subclass="True"/>
+        <datatype extension="msf" type="galaxy.datatypes.data:Text" subclass="True"/>
+        <!-- PHYLIP interleaved alignment format -->
+        <datatype extension="phylip" type="galaxy.datatypes.data:Text" subclass="True"/>
+        <datatype extension="vienna" type="galaxy.datatypes.data:Text" subclass="True"/>
+   </registration>
+   <sniffers>
+        <sniffer type="galaxy.datatypes.infernal:Stockholm_1_0"/>
+   </sniffers>
+</datatypes>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/msa.py	Tue Apr 22 13:55:42 2014 -0400
@@ -0,0 +1,110 @@
+# -*- coding: utf-8 -*-
+
+from galaxy.datatypes.data import Text
+from galaxy.datatypes.sniff import get_headers, get_test_fname
+from galaxy.datatypes.data import get_file_peek
+import subprocess
+import os
+
+from galaxy.datatypes.metadata import MetadataElement
+from galaxy.datatypes import metadata
+
+def count_special_lines( word, filename, invert = False ):
+    """
+        searching for special 'words' using the grep tool
+        grep is used to speed up the searching and counting
+        The number of hits is returned.
+    """
+    try:
+        cmd = ["grep", "-c"]
+        if invert:
+            cmd.append('-v')
+        cmd.extend([word, filename])
+        out = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+        return int(out.communicate()[0].split()[0])
+    except:
+        pass
+    return 0
+
+class Stockholm_1_0( Text ):
+    file_ext = "stockholm"
+
+    MetadataElement( name="number_of_alignments", default=0, desc="Number of multiple alignments", readonly=True, visible=True, optional=True, no_value=0 )
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        if not dataset.dataset.purged:
+            dataset.peek = get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            if (dataset.metadata.number_of_models == 1):
+                dataset.blurb = "1 alignment"
+            else:
+                dataset.blurb = "%s alignments" % dataset.metadata.number_of_models
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disc'
+
+    def sniff( self, filename ):
+        if count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', filename) > 0:
+            return True
+        else:
+            return False
+
+    def set_meta( self, dataset, **kwd ):
+        """
+
+        Set the number of models in dataset.
+        """
+        dataset.metadata.number_of_models = count_special_lines('^#[[:space:]+]STOCKHOLM[[:space:]+]1.0', dataset.file_name)
+
+    def split( cls, input_datasets, subdir_generator_function, split_params):
+        """
+
+        Split the input files by model records.
+        """
+        if split_params is None:
+            return None
+
+        if len(input_datasets) > 1:
+            raise Exception("STOCKHOLM-file splitting does not support multiple files")
+        input_files = [ds.file_name for ds in input_datasets]
+
+        chunk_size = None
+        if split_params['split_mode'] == 'number_of_parts':
+            raise Exception('Split mode "%s" is currently not implemented for STOCKHOLM-files.' % split_params['split_mode'])
+        elif split_params['split_mode'] == 'to_size':
+            chunk_size = int(split_params['split_size'])
+        else:
+            raise Exception('Unsupported split mode %s' % split_params['split_mode'])
+
+        def _read_stockholm_records( filename ):
+            lines = []
+            with open(filename) as handle:
+                for line in handle:
+                    lines.append( line )
+                    if line.strip() == '//':
+                        yield lines
+                        lines = []
+
+        def _write_part_stockholm_file( accumulated_lines ):
+            part_dir = subdir_generator_function()
+            part_path = os.path.join( part_dir, os.path.basename( input_files[0] ) )
+            part_file = open( part_path, 'w' )
+            part_file.writelines( accumulated_lines )
+            part_file.close()
+
+        try:
+
+            stockholm_records = _read_stockholm_records( input_files[0] )
+            stockholm_lines_accumulated = []
+            for counter, stockholm_record in enumerate( stockholm_records, start = 1):
+                stockholm_lines_accumulated.extend( stockholm_record )
+                if counter % chunk_size == 0:
+                    _write_part_stockholm_file( stockholm_lines_accumulated )
+                    stockholm_lines_accumulated = []
+            if stockholm_lines_accumulated:
+                _write_part_stockholm_file( stockholm_lines_accumulated )
+        except Exception,  e:
+            log.error('Unable to split files: %s' % str(e))
+            raise
+    split = classmethod(split)
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/readme.rst	Tue Apr 22 13:55:42 2014 -0400
@@ -0,0 +1,64 @@
+===============================================================
+Collection of Galaxy Datatypes for Multiple Sequence Alignments
+===============================================================
+
+That repository should be a starting point to collect all Multiple Sequence Alignment (MSA)
+file formats.
+Development will happen in https://github.com/bgruening/galaxytools. Feel free to contribute.
+
+Copyright 2013 by:
+
+* Bjoern Gruening
+
+
+============
+Installation
+============
+
+Please install these datatypes with the Galaxy Tool Shed:
+
+==================
+Included Datatypes
+==================
+
+- Stockholm*
+- MSF
+- phylib
+- vienna
+- selex
+- clustal
+
+(*) with split/merge and counting functions
+
+
+=======
+History
+=======
+
+- v1.1.0: Initial public release
+
+
+
+
+===============================
+Wrapper Licence (MIT/BSD style)
+===============================
+
+Permission to use, copy, modify, and distribute this software and its
+documentation with or without modifications and for any purpose and
+without fee is hereby granted, provided that any copyright notices
+appear in all copies and that both those copyright notices and this
+permission notice appear in supporting documentation, and that the
+names of the contributors or copyright holders not be used in
+advertising or publicity pertaining to distribution of the software
+without specific prior permission.
+
+THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL
+WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE
+CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT
+OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
+OR PERFORMANCE OF THIS SOFTWARE.
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/1.stockholm	Tue Apr 22 13:55:42 2014 -0400
@@ -0,0 +1,18 @@
+# STOCKHOLM 1.0
+#=GF ID    UPSK
+#=GF SE    Predicted; Infernal
+#=GF SS    Published; PMID 9223489
+#=GF RN    [1]
+#=GF RM    9223489
+#=GF RT    The role of the pseudoknot at the 3' end of turnip yellow mosaic
+#=GF RT    virus RNA in minus-strand synthesis by the viral RNA-dependent RNA
+#=GF RT    polymerase.
+#=GF RA    Deiman BA, Kortlever RM, Pleij CW;
+#=GF RL    J Virol 1997;71:5990-5996.
+
+AF035635.1/619-641             UGAGUUCUCGAUCUCUAAAAUCG
+M24804.1/82-104                UGAGUUCUCUAUCUCUAAAAUCG
+J04373.1/6212-6234             UAAGUUCUCGAUCUUUAAAAUCG
+M24803.1/1-23                  UAAGUUCUCGAUCUCUAAAAUCG
+#=GC SS_cons                   .AAA....<<<<aaa....>>>>
+//