Changeset 718:ec997c138f9e in orange-bioinformatics

Timestamp:

03/23/09 10:44:10 (4 years ago)

Author:

ales_erjavec <ales.erjavec@…>

Branch:

default

Convert:

6f8f5db40ff0d4754bbcf38aa8ed655ffe881d7a

Message:

 

File:

• obiGene.py (modified) (7 diffs)

obiGene.py

@@ -10 +10 @@
 import obiTaxonomy
 import orngServerFiles
-from obiTaxonomy import TextDB
-from weakref import WeakValueDictionary
 
 default_database_path = orngServerFiles.localpath("NCBI_geneinfo")
 
 class GeneInfo(object):
-    __slots__ = ("tax_id", "gene_id", "symbol", "locus_tag", "synonyms",
-                 "dbXrefs", "chromosome", "map_location", "description", "type",
-                 "symbol_from_nomenclature_authority", "full_name_from_nomenclature_authority",
-                 "nomenclature_status", "other_designations", "modification_date")
+    """ An object representing the NCBI information for a gene.
+    """
+    __slots__ = ncbi_geneinfo_tags
     def __init__(self, line):
+        """ Construct the GeneInfo object from a line in the NCBI gene_info file
+        """
         line = line.split("\t")
-##        line = line[:1] + line[2:]
         for attr, value in zip(self.__slots__, line):
             if value == "-":
@@ -44 +42 @@
 
 class NCBIGeneInfo(dict):
-##    _object_cache = WeakValueDictionary()
     _object_cache = {}
     def __init__(self, *args, **kwargs):
-        """ An object for accessing NCBI gene info
+        """ An dictionary like object for accessing NCBI gene info
+        Arguments::
+                - *organsim*    Organism id
+
+        Example::
+            >>> info = NCBIGeneInfo("Homo sapiens")
         """
         if args and type(args[0]) in [str, unicode]:
@@ -58 +60 @@
             elif len(taxids) > 1:
                 raise obiTaxonomy.MultipleSpeciesException, ", ".join(["%s: %s" % (id, obiTaxonomy.name(id)) for id in taxids])
-##            self.taxid = args[0]
+            
             self.taxid = taxids.pop()
             if not os.path.exists(orngServerFiles.localpath("NCBI_geneinfo", "gene_info.%s.db" % self.taxid)):
@@ -64 +66 @@
             file = open(orngServerFiles.localpath("NCBI_geneinfo", "gene_info.%s.db" % self.taxid), "rb")
             self.update(dict((line.split("\t", 3)[1], line) for line in file.read().split("\n") if line.strip() and not line.startswith("#")))
-##            if self.taxid  not in self._object_cache:
-##                if not os.path.exists(orngServerFiles.localpath("NCBI_geneinfo", "gene_info.%s.db" % self.taxid)):
-##                    orngServerFiles.download("NCBI_geneinfo", "gene_info.%s.db" % self.taxid)
-##                self._object_cache[self.taxid] = self.load(orngServerFiles.localpath("NCBI_geneinfo", "gene_info.%s.db" % self.taxid))
-##                
-##            self.__dict__ = self._object_cache[self.taxid].__dict__
+
         else:
             dict.__init__(self, *args, **kwargs)
@@ -76 +73 @@
     @classmethod    
     def load(cls, file):
+        """ A class method that loads gene info from file
+        """
         if type(file) in [str, unicode]:
             file = open(file, "rb")
-##        self._data = dict([(line.split("\t", 3)[1], line) for line in file.read().split("\n") if line])
-##        self.update(dict([(line.split("\t", 3)[1], line) for line in file.read().split("\n") if line]))
         return cls((line.split("\t", 3)[1], line) for line in file.read().split("\n") if line.strip() and not line.startswith("#"))
         
-    def get_info(self, id):
-##        return GeneInfo(self._data[id])
-        return self[id]
+    def get_info(self, gene_id):
+        """ Search and return the GeneInfo object for gene_id
+        """
+        return self[gene_id]
         
     def __call__(self, name):
+        """ Search and return the GeneInfo object for gene_id
+        """
         translate = lambda a:a
         id = translate(name)
@@ -125 +125 @@
     @staticmethod
     def get_geneinfo_from_ncbi(progressCallback=None):
-##        if type(file) in [unicode, str]:
-##            file = open(file, "wb")
         import urllib2, gzip
         from cStringIO import StringIO
@@ -133 +131 @@
         return info
         
-def prepare_gene_info(file):
-    info = NCBIGeneInfo.load(file)
-    taxids = ["9606"]#obiTaxonomy.common_organisms()
-    genes = dict([(taxid, []) for taxid in taxids])
-    for gi in info.itervalues():
-        if gi.tax_id in taxids:
-            genes[gi.tax_id].append(gi)
-
-    for taxid, genes in genes.items():
-        f = open("gene_info.%s.db" % taxid, "wb")
-        f.write("\n".join([str(gi) for gi in sorted(genes, key=lambda gi:int(gi.gene_id))]))
-        
 
 if __name__ == "__main__":
-##    info = NCBIGeneInfo("9606")
-##    gi = info("1")
-##    print type(gi), type(info.get("1"))
-##    print type(info.values()[0])
-    prepare_gene_info("D:/Download/gene_info/Homo_sapiens.gene_info")
-##    print gi.tax_id, gi.synonyms, gi.dbXrefs, gi.symbol_from_nomenclature_authority, gi.full_name_from_nomenclature_authority
+    info = NCBIGeneInfo("9606")
+    gi = info(list(info)[0])
+    print gi.tax_id, gi.synonyms, gi.dbXrefs, gi.symbol_from_nomenclature_authority, gi.full_name_from_nomenclature_authority