def test_renamed(self):
formats = self.__formats
for i, j in itertools.product(formats[:-1], formats):
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
for k in self.__acc_num_files:
renamer.read_ncbi_acc_num(k, i, j)
# convert sequence IDs
input_file = os.path.join(self.__test_dir, 'ncbi_' + i + '.fa')
with open(self.__output, 'w') as output_fasta:
for line in renamer.renamed(input_file):
output_fasta.write(line)
example_file = os.path.join(self.__test_dir, 'ncbi_' + j + '.fa')
for k in (self.__output + '.fai', example_file + '.fai'):
if os.path.isfile(k):
os.unlink(k)
output_fasta = Fasta(self.__output)
example_fasta = Fasta(example_file)
# compare the obtained file to the example
self.assertEqual(output_fasta.keys(), example_fasta.keys())
# test for an incorrect format
with self.assertRaises(SeqRenameError):
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
renamer.read_ncbi_acc_num(
'unknown', 'chr_refseq',
os.path.join(self.__test_dir, 'ncbi_chr_refseq.fa'))
with self.assertRaises(SeqRenameError):
renamer.read_ncbi_acc_num(
'chr_refseq', 'unknown',
os.path.join(self.__test_dir, 'ncbi_chr_refseq.fa'))
# test for an incorrect NCBI accession number dictionary
with self.assertRaises(IncorrectDictError):
renamer.read_ncbi_acc_num(self.__chr_incorrect, 'refseq_full',
'chr_refseq')
# check if sequence versions are removed
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
for k in self.__acc_num_files:
renamer.read_ncbi_acc_num(k,
'chr',
'genbank',
remove_seq_version=True)
input_file = os.path.join(self.__test_dir, 'ncbi_chr.fa')
example_file = os.path.join(self.__test_dir, 'ncbi_genbank_nover.fa')
with open(self.__output, 'w') as output_fasta:
for line in renamer.renamed(input_file):
output_fasta.write(line)
for k in (self.__output + '.fai', example_file + '.fai'):
if os.path.isfile(k):
os.unlink(k)
output_fasta = Fasta(self.__output)
example_fasta = Fasta(example_file)
self.assertEqual(output_fasta.keys(), example_fasta.keys())
os.unlink(example_file + '.fai')
def test_renamed(self):
formats = (
"refseq_full",
"genbank_full",
"refseq_gi",
"genbank_gi",
"refseq",
"genbank",
"chr_refseq",
"chr_genbank",
"chr",
)
for i, j in itertools.product(formats[:-1], formats):
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
for k in self.__acc_num_files:
renamer.read_ncbi_acc_num(k, i, j)
# convert sequence IDs
input_file = os.path.join(self.__test_dir, "ncbi_" + i + ".fa")
with open(self.__output, "w") as output_fasta:
for line in renamer.renamed(input_file):
output_fasta.write(line)
example_file = os.path.join(self.__test_dir, "ncbi_" + j + ".fa")
for k in (self.__output + ".fai", example_file + ".fai"):
if os.path.isfile(k):
os.unlink(k)
output_fasta = Fasta(self.__output)
example_fasta = Fasta(example_file)
# compare the obtained file to the example
self.assertEqual(output_fasta.keys, example_fasta.keys)
# test for an incorrect format
with self.assertRaises(SeqRenameError):
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
renamer.read_ncbi_acc_num("unknown", "chr_refseq", os.path.join(self.__test_dir, "ncbi_chr_refseq.fa"))
with self.assertRaises(SeqRenameError):
renamer.read_ncbi_acc_num("chr_refseq", "unknown", os.path.join(self.__test_dir, "ncbi_chr_refseq.fa"))
# test for an incorrect NCBI accession number dictionary
with self.assertRaises(IncorrectDictError):
renamer.read_ncbi_acc_num(self.__chr_incorrect, "refseq_full", "chr_refseq")
# check if sequence versions are removed
renamer = bioformats.seqname.NcbiFastaSeqRenamer()
for k in self.__acc_num_files:
renamer.read_ncbi_acc_num(k, "chr", "genbank", remove_seq_version=True)
input_file = os.path.join(self.__test_dir, "ncbi_chr.fa")
example_file = os.path.join(self.__test_dir, "ncbi_genbank_nover.fa")
with open(self.__output, "w") as output_fasta:
for line in renamer.renamed(input_file):
output_fasta.write(line)
for k in (self.__output + ".fai", example_file + ".fai"):
if os.path.isfile(k):
os.unlink(k)
output_fasta = Fasta(self.__output)
example_fasta = Fasta(example_file)
self.assertEqual(output_fasta.keys, example_fasta.keys)
os.unlink(example_file + ".fai")
# remove temporary files and FASTA indices
os.unlink(self.__output)
os.unlink(self.__output + ".fai")
for i in formats:
os.unlink(os.path.join(self.__test_dir, "ncbi_" + i + ".fa.fai"))
