Add config file parsing and subweightsv1

3 files changed, 144 insertions, 38 deletions

diff --git a/bin/pepseq b/bin/pepseq
index 280e471..6ab3922 100755
--- a/bin/pepseq
+++ b/bin/pepseq
@@ -17,6 +17,11 @@ if (os.path.exists(os.path.join(PROJECT_ROOT_DIRECTORY, 'pepseq'))
 import logging
 import optparse
 import pepseq
+import itertools
+
+import ConfigParser
+
+import pepseq.amino_acid
 
 import gettext
 from gettext import gettext as _
@@ -29,39 +34,105 @@ LEVELS = (logging.ERROR,
 
 
 def parse_args():
-    usage = _("pepseq [options]")
+    usage = _("pepseq [options] <inputfile>")
     parser = optparse.OptionParser(version="pepseq %s" % pepseq.__version__,
                                    usage=usage)
     parser.add_option('-d', '--debug', dest='debug_mode', action='store_true',
         help=_('Print the maximum debugging info (implies -vv)'))
     parser.add_option('-v', '--verbose', dest='logging_level', action='count',
         help=_('set error_level output to warning, info, and then debug'))
-    parser.add_option("-f", "--foo", action="store", dest="foo",
-                      help=_("foo should be assigned to bar"))
-    parser.set_defaults(logging_level=0, foo=None)
-    return parser.parse_args()
 
+    parser.set_defaults(logging_level=0)
 
-def main():
-    (options, args) = parse_args()
+    (options, args) = parser.parse_args()
 
     if options.debug_mode:
         loglevel = 3
     else:
         try:
             loglevel = LEVELS[options.logging_level]
-            print 'loglevel: %d, options.logging_level: %d' % (loglevel, options.logging_level)
         except IndexError:
             loglevel = 3
 
-    logging.basicConfig(level=loglevel, format='%(asctime)s %(levelname)s %(message)s')
+    logging.basicConfig(level=loglevel,
+            format='%(asctime)s %(levelname)s %(message)s')
+
+    return parser.parse_args()
+
+
+def main():
+    (options, args) = parse_args()
 
-    if options.foo == 'bar':
-        logging.warning(_('easter egg found'))
-        print(_("Schweet"))
+    config = ConfigParser.ConfigParser()
 
-    print _("I'm launched and my args are: %s") % (" ".join(args))
-    logging.debug(_('end of prog'))
+    try:
+        config.readfp(open(args[0]))
+    except IndexError:
+        try:
+            config.readfp(open("sample-input"))
+        except IOError:
+            config.readfp(open("../sample-input"))
+
+    bucket1 = []
+    for char in config.get('DEFAULT', 'bucket1').split(' '):
+        bucket1.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket2 = []
+    for char in config.get('DEFAULT', 'bucket2').split(' '):
+        bucket2.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket3 = []
+    for char in config.get('DEFAULT', 'bucket3').split(' '):
+        bucket3.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket4 = []
+    for char in config.get('DEFAULT', 'bucket4').split(' '):
+        bucket4.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket5 = []
+    for char in config.get('DEFAULT', 'bucket5').split(' '):
+        bucket5.append(pepseq.amino_acid.AminoAcid(char))
+        bucket5.append(pepseq.amino_acid.AminoAcid('N'))
+
+    bucket6 = []
+    for char in config.get('DEFAULT', 'bucket6').split(' '):
+        bucket6.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket7 = []
+    for char in config.get('DEFAULT', 'bucket7').split(' '):
+        bucket7.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket8 = []
+    for char in config.get('DEFAULT', 'bucket8').split(' '):
+        bucket8.append(pepseq.amino_acid.AminoAcid(char))
+
+    bucket9 = []
+    for char in config.get('DEFAULT', 'bucket9').split(' '):
+        bucket9.append(pepseq.amino_acid.AminoAcid(char))
+
+    possibilities = (bucket1, bucket2, bucket3,
+                     bucket4, bucket5, bucket6,
+                     bucket7, bucket8, bucket9)
+
+    peptides = []
+    sequences = tuple(itertools.product(*possibilities))
+    for sequence in sequences:
+        if sequence[4].letter == 'K':
+            peptide = pepseq.amino_acid.Peptide(sequence)
+            peptide.branch_before(4)
+            peptides.append(peptide)
+
+    peptides.sort()
+
+    output = []
+    for peptide in peptides:
+        if peptide.weight > float(config.get('DEFAULT', 'low')):
+            if peptide.weight < float(config.get('DEFAULT', 'high')):
+                output.append(peptide)
+
+    print 'Number of matches: %d' % len(output)
+    for peptide in output:
+        print ("%.2f  %s   " % (peptide.weight, peptide) + '  '.join(peptide.subweights))
 
 if __name__ == "__main__":
     main()
diff --git a/pepseq/amino_acid.py b/pepseq/amino_acid.py
index 05ecb07..ceced0e 100644
--- a/pepseq/amino_acid.py
+++ b/pepseq/amino_acid.py
@@ -6,27 +6,27 @@ class AminoAcid(object):
     """ Amino acids are molecules containing an amine group, a carboxylic acid
         group and a side chain that varies between different amino acids. """
 
-    aminoAcids = {'G': ('Glycine',                  'Gly', 57.05),
-                  'A': ('Alanine',                  'Ala', 71.09),
-                  'S': ('Serine',                   'Ser', 87.08),
-                  'T': ('Threonine',                'Thr', 101.11),
-                  'C': ('Cysteine',                 'Cys', 103.15),
-                  'V': ('Valine',                   'Val', 99.14),
-                  'L': ('Leucine',                  'Leu', 113.16),
-                  'I': ('Isoleucine',               'Ile', 113.16),
-                  'M': ('Methionine',               'Met', 131.19),
-                  'P': ('Proline',                  'Pro', 97.12),
-                  'F': ('Phenylalanine',            'Phe', 147.18),
-                  'Y': ('Tyrosine',                 'Tyr', 163.18),
-                  'W': ('Tryptophan',               'Trp', 186.21),
-                  'D': ('Aspartic Acid',            'Asp', 115.09),
-                  'E': ('Glutamic Acid',            'Glu', 129.12),
-                  'N': ('Asparagine',               'Asn', 114.11),
-                  'Q': ('Glutamine',                'Gln', 128.14),
-                  'H': ('Histidine',                'His', 137.14),
-                  'K': ('Lysine',                   'Lys', 128.17),
-                  'R': ('Arginine',                 'Arg', 156.19),
-                  'B': ('Borono Phenylalanine',     'Bpa', 309.08),
+    aminoAcids = {'G': ('Glycine',                  'Gly', 57.00),
+                  'A': ('Alanine',                  'Ala', 71.00),
+                  'S': ('Serine',                   'Ser', 87.00),
+                  'T': ('Threonine',                'Thr', 101.00),
+                  'C': ('Cysteine',                 'Cys', 103.00),
+                  'V': ('Valine',                   'Val', 99.10),
+                  'L': ('Leucine',                  'Leu', 113.10),
+                  'I': ('Isoleucine',               'Ile', 113.10),
+                  'M': ('Methionine',               'Met', 131.00),
+                  'P': ('Proline',                  'Pro', 97.10),
+                  'F': ('Phenylalanine',            'Phe', 147.10),
+                  'Y': ('Tyrosine',                 'Tyr', 163.10),
+                  'W': ('Tryptophan',               'Trp', 186.10),
+                  'D': ('Aspartic Acid',            'Asp', 115.00),
+                  'E': ('Glutamic Acid',            'Glu', 129.00),
+                  'N': ('Asparagine',               'Asn', 114.00),
+                  'Q': ('Glutamine',                'Gln', 128.10),
+                  'H': ('Histidine',                'His', 137.10),
+                  'K': ('Lysine',                   'Lys', 128.10),
+                  'R': ('Arginine',                 'Arg', 156.10),
+                  'B': ('Borono Phenylalanine',     'Bpa', 394.10),
     }
 
     def __init__(self, letter):
@@ -45,19 +45,34 @@ class Peptide(object):
     def __init__(self, amino_acids):
         self.amino_acids = amino_acids
         self.weight = 0
+        self.subweights = []
         self.string = ""
         for amino_acid in amino_acids:
             self.weight += amino_acid.weight
             self.string += ('%s' % (amino_acid.letter))
 
     def branch_before(self, index):
-        self.weight = 0
+        self.weight = 18.00
         for (counter, amino_acid) in enumerate(self.amino_acids):
             if counter < index:
                 self.weight += 2 * amino_acid.weight
             else:
                 self.weight += amino_acid.weight
-        self.string = '(' + self.string[0:index] + ')2' + self.string[index:]
+        self.string = ('(' + self.string[0:index] + ')2 ' +
+                       self.string[index + 1:])
+        self._calculate_subweights()
+
+    def _calculate_subweights(self):
+
+        self.subweights.append(str(self.weight - self.amino_acids[0].weight))
+        self.subweights.append(str(float(self.subweights[0]) - self.amino_acids[1].weight))
+        self.subweights.append(str(float(self.subweights[1]) - self.amino_acids[2].weight))
+        self.subweights.append(str(float(self.subweights[2]) - self.amino_acids[3].weight))
+
+        self.subweights.append(str(self.weight - 17.1 - self.amino_acids[-1].weight))
+        self.subweights.append(str(float(self.subweights[-1]) - self.amino_acids[-2].weight))
+        self.subweights.append(str(float(self.subweights[-1]) - self.amino_acids[-3].weight))
+        self.subweights.append(str(float(self.subweights[-1]) - self.amino_acids[-4].weight))
 
     def __cmp__(self, other):
         return cmp(self.weight, other.weight)
@@ -70,7 +85,7 @@ if __name__ == '__main__':
 
     import itertools
 
-    LOW  = 2636.0
+    LOW = 2636.0
     HIGH = 2637.0
 
     possibilities = (
diff --git a/sample-input b/sample-input
new file mode 100644
index 0000000..480624a
--- /dev/null
+++ b/sample-input
@@ -0,0 +1,20 @@
+# This is a sample input file
+#
+# IMPORTANT: There MUST be 9 buckets and bucket 5 MUST be 'K'. There is nearly
+# no input validation, so make sure you get this right. If the output looks
+# wrong, start by verifying what you've recorded here.
+
+[DEFAULT]
+
+low  = 1545.0
+high = 1546.0
+
+bucket1 = B E T Y
+bucket2 = B N A F
+bucket3 = B D S H
+bucket4 = B Q L W
+bucket5 = K
+bucket6 = B N I Y
+bucket7 = B E V W
+bucket8 = B Q P H
+bucket9 = B E S F