debian/changelog

+fastaq (3.17.0-1) unstable; urgency=medium
+
+  * New upstream release.
+  * Use secure format link in d/copyright.
+  * Bump Standards-Version.
+  * Drop unneeded patches.
+  * Use debhelper 11.
+
+ -- Sascha Steinbiss <satta@debian.org>  Thu, 22 Feb 2018 10:22:55 +0100
+
 fastaq (3.16.0-1) unstable; urgency=medium
 
   [ Steffen Moeller ]

debian/compat

-9
+11

debian/control

@@ -5,7 +5,7 @@ Uploaders: Andreas Tille <tille@debian.org>,
            Sascha Steinbiss <satta@debian.org>
 Section: science
 Priority: optional
-Build-Depends: debhelper (>= 9),
+Build-Depends: debhelper (>= 11),
                dh-python,
                python3,
                python3-setuptools,
@@ -14,7 +14,7 @@ Build-Depends: debhelper (>= 9),
                samtools,
                help2man
 X-Python3-Version: >= 3.2
-Standards-Version: 4.1.1
+Standards-Version: 4.1.3
 Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/fastaq.git
 Vcs-Git: https://anonscm.debian.org/git/debian-med/fastaq.git
 Homepage: https://github.com/sanger-pathogens/Fastaq

debian/copyright

-Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: Fastaq
 Source: https://github.com/sanger-pathogens/Fastaq
 

debian/patches/series

-#delay-import-statements-for-manpage-creation.patch

debian/patches/spelling

-Description: spelling 
-Author: Sascha Steinbiss <satta@debian.org>
---- a/pyfastaq/runners/make_random_contigs.py
-+++ b/pyfastaq/runners/make_random_contigs.py
-@@ -9,7 +9,7 @@
-     parser.add_argument('--name_by_letters', action='store_true', help='Name the contigs A,B,C,... will start at A again if you get to Z')
-     parser.add_argument('--prefix', help='Prefix to add to start of every sequence name', default='')
-     parser.add_argument('--seed', type=int, help='Seed for random number generator. Default is to use python\'s default', default=None)
--    parser.add_argument('contigs', type=int, help='Nunber of contigs to make')
-+    parser.add_argument('contigs', type=int, help='Number of contigs to make')
-     parser.add_argument('length', type=int, help='Length of each contig')
-     parser.add_argument('outfile', help='Name of output file')
-     options = parser.parse_args()

pyfastaq/sequences.py

 import copy
 import re
-import string
 import random
 import itertools
-
+from collections import Counter
 from pyfastaq import utils, intervals, genetic_codes
 
 class Error (Exception): pass
@@ -465,6 +464,47 @@ class Fasta:
         '''Returns a Fasta sequence, translated into amino acids. Starts translating from 'frame', where frame expected to be 0,1 or 2'''
         return Fasta(self.id, ''.join([genetic_codes.codes[genetic_code].get(self.seq[x:x+3].upper(), 'X') for x in range(frame, len(self)-1-frame, 3)]))
 
+    def gc_content(self, as_decimal=True):
+        """Returns the GC content for the sequence.
+        Notes:
+            This method ignores N when calculating the length of the sequence.
+            It does not, however ignore other ambiguous bases. It also only
+            includes the ambiguous base S (G or C). In this sense the method is
+            conservative with its calculation.
+
+        Args:
+            as_decimal (bool): Return the result as a decimal. Setting to False
+            will return as a percentage. i.e for the sequence GCAT it will
+            return 0.5 by default and 50.00 if set to False.
+
+        Returns:
+            float: GC content calculated as the number of G, C, and S divided
+            by the number of (non-N) bases (length).
+
+        """
+        gc_total = 0.0
+        num_bases = 0.0
+        n_tuple = tuple('nN')
+        accepted_bases = tuple('cCgGsS')
+
+        # counter sums all unique characters in sequence. Case insensitive.
+        for base, count in Counter(self.seq).items():
+
+            # dont count N in the number of bases
+            if base not in n_tuple:
+                num_bases += count
+
+                if base in accepted_bases:  # S is a G or C
+                    gc_total += count
+
+        gc_content = gc_total / num_bases
+
+        if not as_decimal:  # return as percentage
+            gc_content *= 100
+
+        return gc_content
+
+
 
 class Embl(Fasta):
     '''Exactly the same as Fasta, but reading seqs from a file works differently'''

pyfastaq/tests/sequences_test.py

@@ -520,6 +520,19 @@ class TestFasta(unittest.TestCase):
             fa = sequences.Fasta('name', 'A')
             fa.split_capillary_id()
 
+    def test_gc_content(self):
+        """Test GC content calculation works as expected"""
+        tests = [
+            (sequences.Fasta('ID', 'cgCG'), 1.0),
+            (sequences.Fasta('ID', 'tTaA'), 0.0),
+            (sequences.Fasta('ID', 'GCAT'), 0.5),
+            (sequences.Fasta('ID', 'GCATNN'), 0.5),
+            (sequences.Fasta('ID', 'GCATNNS'), 0.6),
+            (sequences.Fasta('ID', 'GCATNNSK'), 0.5)
+        ]
+        for test, answer in tests:
+            self.assertAlmostEqual(test.gc_content(), answer)
+            self.assertAlmostEqual(test.gc_content(as_decimal=False), answer * 100)
 
 class TestEmbl(unittest.TestCase):
     def test_get_id_from_header_line(self):

setup.py

@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='pyfastaq',
-    version='3.16.0',
+    version='3.17.0',
     description='Script to manipulate FASTA and FASTQ files, plus API for developers',
     packages = find_packages(),
     author='Martin Hunt',