Add python3 support

run_index.py

@@ -1,8 +1,10 @@
+from __future__ import absolute_import
+from __future__ import print_function
 from veppy.utils.fasta import GenbankFastaFile
 from veppy.feature_file import GencodeGtfFile
 from veppy.feature_file import NcbiMapViewFile
 
-print "Indexing FASTA and feature files, this may take 10 minutes or more..."
+print("Indexing FASTA and feature files, this may take 10 minutes or more...")
 
 fasta_file = GenbankFastaFile.for_build("GRCh37")
 feature_file_gencode = GencodeGtfFile.for_build('GRCh37')

veppy/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import os
 import sys
 import logging
@@ -51,7 +52,7 @@
 SUPPORTED_BUILDS = os.environ.get(
     'SUPPORTED_BUILDS', 'GRCh37').split(',')
 
-SUPPORTED_GENE_MODELS = SOURCE_DATA['GRCh37']['feature'].keys()
+SUPPORTED_GENE_MODELS = list(SOURCE_DATA['GRCh37']['feature'].keys())
 
 FEATURE_LIMIT = int(os.getenv('FEATURE_LIMIT', sys.maxint))
 

veppy/consequences.py

@@ -1,4 +1,5 @@
-import functions
+from __future__ import absolute_import
+from . import functions
 
 
 def to_dict(csq):

veppy/feature_file.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import os
 import logging
 from glob import glob
@@ -20,14 +21,13 @@
 from . import errors
 from . import SUPPORTED_BUILDS
 from . import FEATURE_LIMIT
+import six
 
 
 logger = logging.getLogger('veppy')
 
 
-class FeatureFile(object):
-    __metaclass__ = ABCMeta
-
+class FeatureFile(six.with_metaclass(ABCMeta, object)):
     class BoundedCache(object):
         def __init__(self, size=1024):
             self._cache = [None] * size

veppy/features.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import sys
 import re
 import logging
@@ -7,6 +8,8 @@
 from collections import defaultdict, namedtuple
 
 from . import errors
+from six.moves import map
+from six.moves import range
 
 logger = logging.getLogger('veppy')
 
@@ -265,7 +268,7 @@ def build(self, data, force=False):
                     # start counting at 1!
                     feature.number = i + 1
                     feature.total = len(features)
-        except Exception, e:
+        except Exception as e:
             logger.warn('Invalid feature %s' % self)
             logger.warn(e)
             self.errors = True
@@ -629,7 +632,7 @@ def to_genomic_ranges(self, coding_start, coding_stop):
             return genomic_ranges
 
         def __str__(self):
-            return 'coding sequences: %s' % map(str, self._tree)
+            return 'coding sequences: %s' % list(map(str, self._tree))
 
 
 class EnsemblTranscript(Transcript):

veppy/sequence.py

@@ -1,9 +1,13 @@
+from __future__ import absolute_import
 import sys
 from collections import namedtuple
 
 from .features import EffectiveVariant
 from .utils import codons
 from .utils import fasta
+from six.moves import map
+from six.moves import range
+from six.moves import zip
 
 
 Coordinate = \
@@ -207,7 +211,7 @@ def get_amino_acids(coding_coordinates, coding_sequence):
             (ref_seq, ref_genomic_coordinates) = self.build(
                 variant.chromosome, ref_coding_start, ref_coding_stop)
             ref_coding_coordinates = \
-                range(ref_coding_start, ref_coding_stop + 1)
+                list(range(ref_coding_start, ref_coding_stop + 1))
 
         # build symmetric upstream/downstream codon buffer around ref
         # TODO: need to bound upstream_seq and downstream_seq
@@ -224,7 +228,7 @@ def get_amino_acids(coding_coordinates, coding_sequence):
                 variant.chromosome, upstream_coding_start,
                 upstream_coding_stop)
         upstream_coding_coordinates = \
-            range(upstream_coding_start, upstream_coding_stop + 1)
+            list(range(upstream_coding_start, upstream_coding_stop + 1))
 
         # downstream
         (downstream_coding_start, downstream_coding_stop) = (
@@ -236,28 +240,25 @@ def get_amino_acids(coding_coordinates, coding_sequence):
                 variant.chromosome, downstream_coding_start,
                 downstream_coding_stop)
         downstream_coding_coordinates = \
-            range(downstream_coding_start, downstream_coding_stop + 1)
+            list(range(downstream_coding_start, downstream_coding_stop + 1))
 
         # -- Alternate
         # build alt seq...
         # complement if negative strand...
         if self.strand == '-':
-            (ref_seq, alt_allele, upstream_seq, downstream_seq) = map(
+            (ref_seq, alt_allele, upstream_seq, downstream_seq) = list(map(
                 CodingSequenceBuilder.complement_sequence,
                 (ref_seq, alt_allele, upstream_seq, downstream_seq)
-            )
+            ))
             (
                 ref_genomic_coordinates,
                 upstream_genomic_coordinates,
                 downstream_genomic_coordinates
-            ) = map(
-                lambda x: x[::-1],
-                (
-                    ref_genomic_coordinates,
-                    upstream_genomic_coordinates,
-                    downstream_genomic_coordinates
-                )
-            )
+            ) = [x[::-1] for x in (
+                ref_genomic_coordinates,
+                upstream_genomic_coordinates,
+                downstream_genomic_coordinates
+            )]
 
         if variant.is_insertion:
             i0 = coding_start - coding_start_round
@@ -318,7 +319,7 @@ def get_amino_acids(coding_coordinates, coding_sequence):
 
         # NOTE: these are all CODING (!!!) sequences
         return BuilderResult(
-            range(coding_start, coding_stop + 1),
+            list(range(coding_start, coding_stop + 1)),
             CodingSequence(
                 ref_seq,
                 ref_genomic_coordinates,
@@ -376,7 +377,7 @@ def build(self, chromosome, coding_start, coding_stop):
         codon_genomic_coordinates = []
         for gr in genomic_ranges:
             codon_genomic_coordinates.extend(
-                range(gr.start, gr.stop + 1)
+                list(range(gr.start, gr.stop + 1))
             )
 
         return (seq, codon_genomic_coordinates)

veppy/splice_model.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 from collections import namedtuple
 
 FeatureRange = namedtuple('FeatureRange', ['start', 'stop'])

veppy/tests/test_veppy.py

@@ -1,3 +1,5 @@
+from __future__ import absolute_import
+from __future__ import print_function
 import os
 import sys
 import logging
@@ -6,6 +8,7 @@
 
 from veppy.veppy import calculate_consequences
 from veppy.utils.readers import VcfReader
+from six.moves import map
 
 logger = logging.getLogger('test')
 
@@ -78,18 +81,18 @@ def _eff_set(csqs):
                     set(required_effects), set(pruned_results)
                 )
 
-        except AssertionError, e:
-            print '-------------------------------------'
-            print '-------------------------------------'
-            print '   VARIANT: ', str(variant)
-            print '  REQUIRED: ', list(required_effects)
-            print 'DISALLOWED: ', disallowed_effects
-            print '   RESULTS: ', map(
+        except AssertionError as e:
+            print('-------------------------------------')
+            print('-------------------------------------')
+            print('   VARIANT: ', str(variant))
+            print('  REQUIRED: ', list(required_effects))
+            print('DISALLOWED: ', disallowed_effects)
+            print('   RESULTS: ', list(map(
                 str,
                 transcript_results.get(transcript_id, [])
-            )
-            print '-------------------------------------'
-            print '-------------------------------------'
+            )))
+            print('-------------------------------------')
+            print('-------------------------------------')
             raise AssertionError(e)
 
     def _test(self, filepath):

veppy/utils/codons.py

@@ -1,4 +1,6 @@
+from __future__ import absolute_import
 from collections import defaultdict
+from six.moves import range
 
 CODONS_FULL = {
     # Alanine

veppy/utils/data/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import os
 import gzip
 import pickle

veppy/utils/fasta.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import os
 import logging
 
@@ -15,22 +16,21 @@
 from .. import SOURCE_DATA_MD5
 from .. import MD5_CHECK_FAIL
 from .. import errors
+import six
+from six.moves import range
 
 logger = logging.getLogger('veppy')
 
 
-class FastaFile(object):
-    __metaclass__ = ABCMeta
-
-    # -- Util methods
+class FastaFile(six.with_metaclass(ABCMeta, object)):
     @classmethod
     def load_build(klass, build):
         try:
             translated_build = supported_build(build)
             if not klass.BUILD_CACHE.get(translated_build):
                 klass.BUILD_CACHE[translated_build] = \
                     klass(build, klass.filepath_for_build(translated_build))
-        except (FastaNotFound, errors.FastaFileException), e:
+        except (FastaNotFound, errors.FastaFileException) as e:
             logger.fatal(
                 'Error loading FastA file for build %s: %s' % (build, e)
             )
@@ -101,7 +101,7 @@ def __init__(self, build, filepath, index=False):
 
         # TODO: eventually, this should be dynamic and file-specific
         self.chromosomes = \
-            map(lambda x: str(x), range(1, 23)) + ['MT', 'X', 'Y']
+            [str(x) for x in range(1, 23)] + ['MT', 'X', 'Y']
 
     def get(self, chromosome, start, stop):
         fasta_chromosome = self.get_chromosome(chromosome)

veppy/utils/helpers.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import os
 import logging
 
@@ -70,7 +71,7 @@ def set_defaults(transcripts):
     for transcript in transcripts:
         _groups[transcript.gene].append(transcript)
 
-    default_gene = get_default_gene(_groups.keys())
+    default_gene = get_default_gene(list(_groups.keys()))
     if default_gene:
         default_gene.default = True
 

veppy/utils/md5.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import hashlib
 
 

veppy/utils/readers.py

@@ -1,7 +1,9 @@
+from __future__ import absolute_import
 import csv
 import gzip
 import logging
 from cStringIO import StringIO
+from six.moves import map
 
 logger = logging.getLogger('veppy')
 
@@ -90,9 +92,9 @@ def _check_headers(self):
             self._headers = list(self.headercols)
 
     def next(self):
-        parsed_row = self._process_next(super(CsvReader, self).next())
+        parsed_row = self._process_next(next(super(CsvReader, self)))
         while parsed_row is None:
-            parsed_row = self._process_next(super(CsvReader, self).next())
+            parsed_row = self._process_next(next(super(CsvReader, self)))
         return parsed_row
 
     def _process_next(self, line):
@@ -289,12 +291,12 @@ def vcf_to_dict(self, vcf_obj):
             'stop': vcf_obj.POS + len(vcf_obj.REF) - 1,
             'chromosome': vcf_obj.CHROM,
             'reference_allele': vcf_obj.REF,
-            'alternate_alleles': map(self._get_alternate, vcf_obj.ALT),
+            'alternate_alleles': list(map(self._get_alternate, vcf_obj.ALT)),
             'info': vcf_obj.INFO
         }
 
     def __iter__(self):
         return self
 
     def next(self):
-        return self.vcf_to_dict(self.reader.next())
+        return self.vcf_to_dict(next(self.reader))

veppy/veppy.py

@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 import logging
 
 from . import features
@@ -8,6 +9,7 @@
 from .sequence import CodingSequenceBuilder
 from .splice_model import SpliceJunctionModel
 from .utils.codons import split_into_codons
+from six.moves import range
 
 logger = logging.getLogger('veppy')