Changeset 30

Timestamp:

Aug 11, 2010, 4:06:01 PM (11 years ago)

Author:

j@…

bzr:base-revision:

j@dannynavarro.net-20100806131029-8dov1nqec1ao917u

bzr:committer:

Danny Navarro <j@dannynavarro.net>

bzr:file-ids:

mzcms/models.py models.py-20100730084238-fjjwldiefr0w07zv-4
mzcms/parsers.py parsers.py-20100806092910-g1sxvv1o5b9umkof-1

bzr:mapping-version:

v4

bzr:repository-uuid:

724254b2-fbe6-419d-9466-c04ef4c9d29d

bzr:revision-id:

j@dannynavarro.net-20100806140012-pvqfaqhcmlz08i2f

bzr:revno:

30

bzr:revprop:branch-nick:

trunk

bzr:root:

trunk

bzr:timestamp:

2010-08-06 16:00:12.605999947 +0200

bzr:user-agent:

bzr2.1.2+bzr-svn1.0.3

svn:original-date:

2010-08-06T14:00:12.606000Z

Message:

Fixed file walker, various renames

Location:

trunk/mzcms

Files:

• models.py (modified) (1 diff)
• parsers.py (modified) (8 diffs)

trunk/mzcms/models.py

@@ -16 +16 @@
 class Proteins(Folder):
     """Proteins folder factory"""
-    def __init__(self, proteins):
+    def __init__(self):
         self.name = 'proteins'
 

trunk/mzcms/parsers.py

@@ -46 +46 @@
         self.contaminant_regex = re.compile(contaminant_str)
 
-    def _parse_spectra_fn(self, datfile):
+    def _parse_spectra_fn(self, dat_file):
         """Parses the spectra file name used for Mascot search
         """
-        for line in datfile:
+        for line in dat_file:
             if line.startswith("FILE="):
                 full_path = line.strip().split('=')[1]
@@ -55 +55 @@
                 return norm_path.split("/")[-1]
 
-    def _parse_frag_mode(self, datfile):
+    def _parse_frag_mode(self, dat_file):
         """Get the fragmentation type by looking at dat parameters
         """
         # TODO: Handle CID and error for other instruments
-        for line in datfile:
+        for line in dat_file:
             if line.startswith("INSTRUMENT="):
                 frag_line = line.strip().split('=')[1]
@@ -69 +69 @@
                     return frag_line
 
-    def _parse_annotations(self, datfile):
+    def _parse_psms(self, dat_file):
         """Parses the peptide section of mascot
         """
-        nativeid_annotations = defaultdict(list)
+        nativeid_psms = defaultdict(list)
         # Seek until Mascot peptide section
         peptide_section = SECTION_TEMPLATE.substitute(section="peptides")
-        for line in datfile:
+        for line in dat_file:
             if line.strip() == peptide_section:
                 break
-        for line in datfile:
+        for line in dat_file:
+            import ipdb; ipdb.set_trace()
             match = re.match(PEP_REGEX, line)
             if match:
@@ -90 +91 @@
                 # the line with flanking Aa
                 # q4_p2_terms=E,K:E,K:E,K:E,K:E,K
-                line = datfile.next().strip()
+                line = dat_file.next().strip()
                 # (('E', 'K'), ('E', 'K'), ('E', 'K'))
                 flanking_pairs = set(tuple(x.split(','))
@@ -98 +99 @@
                             flanking_pair[0], peptide, flanking_pair[1]))
                     annotation = annotation.replace('-', '*')
-                    nativeid_annotations[nativeid].append(dict(
+                    nativeid_psms[nativeid].append(dict(
                             Annotation=annotation, IsDecoy=is_decoy))
             elif line.strip() == SEPARATOR:
-                return nativeid_annotations
+                return nativeid_psms
 
     def _parse_spectra(self, datfile):
@@ -141 +142 @@
         return nativeid_spectra
 
-    def parse(self, datfile):
+    def parse(self, dat_file):
         """Takes a dat file and returns a dictionary of psms.
         """
-        pkl_fn = self._parse_spectra_fn(datfile)
-        frag_mode = self._parse_frag_mode(datfile)
-        nativeid_annotations = self._parse_annotations(datfile)
+        pkl_fn = self._parse_spectra_fn(dat_file)
+        frag_mode = self._parse_frag_mode(dat_file)
+        nativeid_psms = self._parse_psms(dat_file)
         nativeid_spectra = self._parse_spectra(datfile)
         for native_id, annotations in nativeid_annotations.items():
@@ -196 +197 @@
     """Parses all the dat files in dats_dir
     """
-    dat_paths = (f for f in os.walk(dats_dir))
     proteins = proteins_factory()
     peptides = peptides_factory()
@@ -202 +202 @@
     psms = psms_factory()
     dat_parser = DatParser()
-    for dat_path in dat_paths:
-        with open(dat_path) as dat_file:
-            dat_proteins, dat_peptides, \
-            dat_spectra, dat_psms = dat_parser.parse(dat_file)
-            proteins.update(dat_proteins)
-            peptides.update(dat_peptides)
-            spectra.update(dat_spectra)
-            psms.update(dat_psms)
+    for root, dirs, files in os.walk(dats_dir):
+        for dat_fn in files:
+            # TODO: exception for not dat files
+            with open(os.path.join(root, dat_fn)) as dat_file:
+                dat_proteins, dat_peptides, \
+                dat_spectra, dat_psms = dat_parser.parse(dat_file)
+                proteins.update(dat_proteins)
+                peptides.update(dat_peptides)
+                spectra.update(dat_spectra)
+                psms.update(dat_psms)
     return proteins, peptides, spectra, psms