Merge pull request #15 from counsyl/rename-hgvs-pyhgvs

Rename hgvs module to pyhgvs

CHANGELOG.md

@@ -0,0 +1,10 @@
+# HGVS library change log
+
+## 0.9.2 (2014-12-11)
+  - Rename package to pyhgvs to avoid naming conflict with other libraries.
+
+## 0.9.1 (2014-03-10)
+  - Normalize variants by default when generating names.
+
+## 0.9 (2014-01-16)
+  - Improved testing.

README.md

@@ -93,16 +93,16 @@ and transcripts are read from a RefSeqGenes flat-file using methods
 provided by `hgvs`.
 
 ```python
-import hgvs
-import hgvs.utils
+import pyhgvs as hgvs
+import hgvs.utils as hgvs_utils
 from pygr.seqdb import SequenceFileDB
 
 # Read genome sequence using pygr.
 genome = SequenceFileDB('hg19.fa')
 
 # Read RefSeq transcripts into a python dict.
 with open('hgvs/data/genes.refGene') as infile:
-    transcripts = hgvs.utils.read_transcripts(infile)
+    transcripts = hgvs_utils.read_transcripts(infile)
 
 # Provide a callback for fetching a transcript by its name.
 def get_transcript(name):
@@ -127,7 +127,7 @@ The `hgvs` library can also perform just the parsing step and provide
 a parse tree of the HGVS name.
 
 ```python
-import hgvs
+import pyhgvs as hgvs
 
 hgvs_name = hgvs.HGVSName('NM_000352.3:c.215-10A>G')
 

bin/hgvs

@@ -1,13 +1,13 @@
 #!/usr/bin/env python
 
+import argparse
 import logging
-import optparse
 import sys
 
-import hgvs
-from hgvs.variants import normalize_variant
-from hgvs.utils import read_transcripts
-from hgvs import parse_hgvs_name
+import pyhgvs
+from pyhgvs import parse_hgvs_name
+from pyhgvs.variants import normalize_variant
+from pyhgvs.utils import read_transcripts
 
 import pygr.logger
 from pygr.seqdb import SequenceFileDB
@@ -24,9 +24,10 @@ handler.setFormatter(formatter)
 logger.addHandler(handler)
 
 # Command line options.
-options = optparse.OptionParser()
-options.add_option('-f', '--fasta')
-options.add_option('-t', '--trans')
+options = argparse.ArgumentParser()
+options.add_argument('-f', '--fasta', required=True)
+options.add_argument('-t', '--trans', required=True)
+options.add_argument('hgvs_name', nargs='*')
 
 
 #=============================================================================
@@ -61,7 +62,7 @@ def determine_allele(genome, hgvs_name):
         chrom, start, ref, alt = parse_hgvs_name(
             hgvs_name, genome, get_transcript=get_transcript)
     except (NotImplementedError, AssertionError, KeyError, ValueError,
-            hgvs.InvalidHGVSName) as error:
+            pyhgvs.InvalidHGVSName) as error:
         messages.append(str(error))
         return None, messages
 
@@ -86,23 +87,25 @@ def determine_allele(genome, hgvs_name):
 # Main.
 
 if __name__ == '__main__':
-    conf, args = options.parse_args()
+    args = options.parse_args()
 
     # Read genome and transcripts.
-    genome = SequenceFileDB(conf.fasta)
-    with open(conf.trans) as infile:
+    genome = SequenceFileDB(args.fasta)
+    with open(args.trans) as infile:
         transcripts = read_transcripts(infile)
 
     gene2transcript = {transcript.gene.name: transcript
                        for transcript in transcripts.itervalues()}
 
-    if len(args) == 0:
-        args = (line.rstrip() for line in sys.stdin)
+    if args.hgvs_name:
+        hgvs_names = args.hgvs_name
+    else:
+        hgvs_names = (line.rstrip() for line in sys.stdin)
 
     headers = ['name', 'chrom', 'start', 'ref', 'alt', 'messages']
     print '\t'.join(map(str, headers))
 
-    for allele_name in args:
+    for allele_name in hgvs_names:
         allele, messages = determine_allele(genome, allele_name)
         message = '|'.join(messages)
         if allele:

examples/example1.py

@@ -26,16 +26,16 @@
 
 """
 
-import hgvs
-import hgvs.utils
+import pyhgvs as hgvs
+import hgvs.utils as hgvs_utils
 from pygr.seqdb import SequenceFileDB
 
 # Read genome sequence using pygr.
 genome = SequenceFileDB('hg19.fa')
 
 # Read RefSeq transcripts into a python dict.
 with open('hgvs/data/genes.refGene') as infile:
-    transcripts = hgvs.utils.read_transcripts(infile)
+    transcripts = hgvs_utils.read_transcripts(infile)
 
 
 # Provide a callback for fetching a transcript by its name.

hgvs/tests/test_hgvs_names.py → pyhgvs/tests/test_hgvs_names.py

@@ -97,7 +97,7 @@ def test_name_to_variant():
     """
     genome = MockGenomeTestFile(
         db_filename='hg19.fa',
-        filename='hgvs/tests/data/test_name_to_variant.genome',
+        filename='pyhgvs/tests/data/test_name_to_variant.genome',
         create_data=False)
 
     for hgvs_name, variant, name_canonical, var_canonical in _name_variants:
@@ -115,7 +115,7 @@ def test_variant_to_name():
     """
     genome = MockGenomeTestFile(
         db_filename='hg19.fa',
-        filename='hgvs/tests/data/test_variant_to_name.genome',
+        filename='pyhgvs/tests/data/test_variant_to_name.genome',
         create_data=False)
 
     for (expected_hgvs_name, variant,
@@ -139,7 +139,7 @@ def test_variant_to_name_counsyl():
     """
     genome = MockGenomeTestFile(
         db_filename='hg19.fa',
-        filename='hgvs/tests/data/test_variant_to_name.genome',
+        filename='pyhgvs/tests/data/test_variant_to_name.genome',
         create_data=False)
 
     for (expected_hgvs_name, variant,
@@ -164,7 +164,7 @@ def test_name_to_variant_refseqs():
     if not SequenceFileDB:
         print 'skip test_name_to_variant_refseqs'
         return
-    genome = SequenceFileDB('hgvs/tests/data/test_refseqs.fa')
+    genome = SequenceFileDB('pyhgvs/tests/data/test_refseqs.fa')
 
     for hgvs_name, variant, name_canonical, var_canonical in _name_variants:
         if not var_canonical or 'NM_' not in hgvs_name:

hgvs/tests/test_hgvs_names_long.py → pyhgvs/tests/test_hgvs_names_long.py

@@ -12,11 +12,11 @@ def test_name_to_variant_long():
     """
     genome = MockGenomeTestFile(
         db_filename='hg19.fa',
-        filename='hgvs/tests/data/test_hgvs.genome',
+        filename='pyhgvs/tests/data/test_hgvs.genome',
         create_data=False)
 
     # Read transcripts.
-    with open('hgvs/data/genes.refGene', 'r') as infile:
+    with open('pyhgvs/data/genes.refGene', 'r') as infile:
         transcripts = read_transcripts(infile)
 
     class NoTranscriptError(Exception):
@@ -40,7 +40,7 @@ def get_transcript_long(name):
         return transcript
 
     errors = []
-    with open('hgvs/tests/data/test_hgvs.txt', 'r') as infile:
+    with open('pyhgvs/tests/data/test_hgvs.txt', 'r') as infile:
         for i, line in enumerate(infile):
             row = line.rstrip().split('\t')
             chrom, offset, ref, alt, hgvs_name = row[:5]

setup.py

@@ -19,12 +19,12 @@ def main():
 
     setup(
         name='pyhgvs',
-        version='0.9.1',
+        version='0.9.2',
         description='HGVS name parsing and formatting',
         long_description=description,
         author='Matt Rasmussen',
         author_email='rasmus@counsyl.com',
-        packages=['hgvs', 'hgvs.tests'],
+        packages=['pyhgvs', 'pyhgvs.tests'],
         include_package_data=True,
         package_data={
             '': ['requirements-dev.txt'],