def test_parser_ncbi(self):
header = '>NP_001351877.1 acylglycerol kinase, mitochondrial isoform 2 [H**o sapiens]'
parsed = {
'description': 'acylglycerol kinase, mitochondrial isoform 2',
'id': 'NP_001351877.1',
'taxon': 'H**o sapiens'
}
self.assertEqual(fasta.parse(header), parsed)
def test_parser_spd_mult_ids(self):
header = ('>P02763 Q8TC16|A1AG1_HUMAN| Alpha-1-acid glycoprotein 1 '
'precursor (AGP 1) (Orosomucoid-1) (OMD 1)')
parsed = {
'description': 'Alpha-1-acid glycoprotein 1 precursor (AGP 1)'
' (Orosomucoid-1) (OMD 1)',
'gene': 'A1AG1_HUMAN',
'gene_id': 'A1AG1',
'id': 'P02763 Q8TC16',
'taxon': 'HUMAN'
}
self.assertEqual(fasta.parse(header), parsed)
def test_parser_unimes(self):
header = (
'MES00000000005 Putative uncharacterized protein GOS_3018412 '
'(Fragment) OS=marine metagenome Pep=JCVI_PEP_1096688850003 SV=1')
parsed = {
'OS': 'marine metagenome',
'Pep': 'JCVI_PEP_1096688850003',
'SV': 1,
'id': 'MES00000000005',
'name': 'Putative uncharacterized protein GOS_3018412 (Fragment)'
}
self.assertEqual(fasta.parse(header), parsed)
def test_parser_spd(self):
header = ('>P31947|1433S_HUMAN| 14-3-3 protein sigma (Stratifin) '
'(Epithelial cell marker protein 1).')
parsed = {
'description': '14-3-3 protein sigma (Stratifin) '
'(Epithelial cell marker protein 1).',
'gene': '1433S_HUMAN',
'gene_id': '1433S',
'id': 'P31947',
'taxon': 'HUMAN'
}
self.assertEqual(fasta.parse(header), parsed)
def describe(args):
"""Read database and produce a summary"""
logger.debug('describe called with: %s', args)
try:
dlist = [d for d, seq in fasta.read(args.file)]
except Exception as e:
logger.info('Not a valid FASTA file.')
logger.debug('Exception: %s', e)
else:
logger.info('Found %s FASTA entries.', len(dlist))
n = len(dlist)
if n:
logger.debug('First entry: %s', dlist[0])
if n > 2:
dlist.sort()
prefix_1 = os.path.commonprefix(dlist[:n // 2])
prefix_2 = os.path.commonprefix(dlist[n // 2 + 1:])
if prefix_1 != prefix_2:
logger.info('Common prefixes: %s, %s', prefix_1, prefix_2)
else:
logger.info('Common prefix: %s', prefix_1)
formats = []
for flavor in fasta.std_parsers:
try:
fasta.parse(dlist[0], flavor=flavor)
except Exception as e:
logger.debug('Header: %s; parsing exception: %s', dlist[0],
e)
else:
formats.append(flavor)
k = len(formats)
if not k:
logger.info('Unknown header format.')
elif k == 1:
logger.info('Suggested header format: %s', formats[0])
else:
logger.info('Possible header formats: %s', ', '.join(formats))
def test_parser_uniref(self):
header = ('>UniRef100_A5DI11 Elongation factor 2 n=1 '
'Tax=Pichia guilliermondii RepID=EF2_PICGU')
parsed = {
'RepID': 'EF2_PICGU',
'taxon': 'PICGU',
'gene_id': 'EF2',
'Tax': 'Pichia guilliermondii',
'cluster': 'Elongation factor 2',
'id': 'UniRef100_A5DI11',
'type': 'UniRef100',
'accession': 'A5DI11',
'n': 1
}
self.assertEqual(fasta.parse(header), parsed)
def test_parser_uniptokb_isoform(self):
header = (
'sp|Q4R572-2|1433B_MACFA Isoform Short of 14-3-3 protein beta'
'/alpha OS=Macaca fascicularis GN=YWHAB')
parsed = {
'GN': 'YWHAB',
'OS': 'Macaca fascicularis',
'db': 'sp',
'entry': '1433B_MACFA',
'gene_id': '1433B',
'id': 'Q4R572-2',
'name': 'Isoform Short of 14-3-3 protein beta/alpha',
'taxon': 'MACFA'
}
self.assertEqual(fasta.parse(header), parsed)
def digest(sequences,
name_col,
min_length=6,
missed_cleavage=2,
protease="trypsin"):
"""
Digests a give FASTA sequence collection into peptides. The protease,
and minimum length can be configured via the options.
Parameters:
--------------------------
sequences: pyteomics FileReader,
Filereader object from an FASTA file.
name_col: str,
identifier column that is added to the final dataframe.
min_length: int,
minimal peptide length for sequences to be included in the
final dataframe.
protease: str,
Text identifier for a the desired protease
Returns:
---------------
df: df,
A dataframe with the columns, sequence, proteine and DB
"""
#store peptide (sequence) and proteins (by an integer id)
peptides = []
proteins = []
for description, sequence in sequences:
#get desc and cleavage products
desc = fasta.parse(description)
new_peptides = parser.cleave(sequence,
parser.expasy_rules[protease],
missed_cleavages=missed_cleavage,
min_length=min_length)
#store new data
peptides.extend(new_peptides)
proteins.extend([desc["id"]] * len(new_peptides))
peptide_df = pd.DataFrame([peptides, proteins]).transpose()
peptide_df.columns = ["Peptidesequence", "Protein"]
peptide_df["DB"] = name_col
return (peptide_df)
def test_parser_uniprotkb(self):
header = (
'sp|P27748|ACOX_RALEH Acetoin catabolism protein X OS=Ralstonia'
' eutropha (strain ATCC 17699 / H16 / DSM 428 / Stanier 337)'
' GN=acoX PE=4 SV=2')
parsed = {
'GN': 'acoX',
'OS': 'Ralstonia eutropha '
'(strain ATCC 17699 / H16 / DSM 428 / Stanier 337)',
'PE': 4,
'SV': 2,
'db': 'sp',
'entry': 'ACOX_RALEH',
'id': 'P27748',
'gene_id': 'ACOX',
'name': 'Acetoin catabolism protein X',
'taxon': 'RALEH'
}
self.assertEqual(fasta.parse(header), parsed)
def test_parser_uniparc(self):
header = '>UPI0000000005 status=active'
parsed = {'id': 'UPI0000000005', 'status': 'active'}
self.assertEqual(fasta.parse(header), parsed)
