def predict(self):
self.h2_prediction = self.get_antigen_gene_blast_results(
self.h2_prediction, FLJB_FASTA_PATH)
if not self.h2_prediction.is_missing:
if not self.h2_prediction.is_perfect_match:
top_result = self.h2_prediction.top_result
match_len = top_result['length']
pident = top_result['pident']
# short lower %ID matches are treated as missing or '-' for H2
if match_len <= 600 and pident < 88.0:
self.h2_prediction.h2 = '-'
self.h2_prediction.is_missing = True
return
if match_len <= 600 and not self.h2_prediction.is_trunc:
self.h2_prediction.h2 = '-'
self.h2_prediction.is_missing = True
return
df_blast_results = pd.DataFrame(
self.h2_prediction.blast_results)
df_blast_results = df_blast_results[
(df_blast_results['mismatch'] <= 50)
& (df_blast_results['length'] >= 700)]
if df_blast_results.shape[0] == 0:
self.h2_prediction.is_missing = True
self.h2_prediction.top_result = None
self.h2_prediction.h2 = '-'
return
df_blast_results_over1000 = df_blast_results[
(df_blast_results['mismatch'] <= 5)
& (df_blast_results['length'] >= 1000)]
if df_blast_results_over1000.shape[0] > 0:
df_blast_results = df_blast_results_over1000.sort_values(
by='mismatch')
else:
df_blast_results = df_blast_results.sort_values(
by='bitscore', ascending=False)
result_dict = BlastReader.df_first_row_to_dict(
df_blast_results)
result_trunc = BlastReader.is_blast_result_trunc(
qstart=result_dict['qstart'],
qend=result_dict['qend'],
sstart=result_dict['sstart'],
send=result_dict['send'],
qlen=result_dict['qlen'],
slen=result_dict['slen'])
self.h2_prediction.top_result = result_dict
self.h2_prediction.is_trunc = result_trunc
self.h2_prediction.h2 = get_antigen_name(
self.h2_prediction.top_result['qseqid'])
if self.h2_prediction.is_missing:
self.h2_prediction.h2 = '-'
def test_BlastReader_is_blast_result_trunc():
# not truncated; match found in the middle of the subject sequence
assert not BlastReader.is_blast_result_trunc(qstart=1,
qend=100,
sstart=101,
send=200,
qlen=100,
slen=1000)
# not truncated; shorter match (-10bp) found in the middle of the subject
# sequence
assert not BlastReader.is_blast_result_trunc(qstart=1,
qend=90,
sstart=101,
send=190,
qlen=100,
slen=1000)
# not truncated; shorter match (-20bp) found in the middle of the subject
# sequence
assert not BlastReader.is_blast_result_trunc(qstart=1,
qend=80,
sstart=101,
send=180,
qlen=100,
slen=1000)
# truncated at the start of the subject
assert BlastReader.is_blast_result_trunc(qstart=51,
qend=100,
sstart=1,
send=50,
qlen=100,
slen=1000)
# truncated at the end of the subject
assert BlastReader.is_blast_result_trunc(qstart=51,
qend=100,
sstart=951,
send=1000,
qlen=100,
slen=1000)
def predict(self, filter=['N/A']):
self.h1_prediction = self.get_antigen_gene_blast_results(
self.h1_prediction, FLIC_FASTA_PATH, filter)
if not self.h1_prediction.is_missing and self.h1_prediction.top_result is not None:
if not self.h1_prediction.is_perfect_match:
df_blast_results = pd.DataFrame(
self.h1_prediction.blast_results)
df_blast_results = df_blast_results[
(df_blast_results['mismatch'] <= 25)
& (df_blast_results['length'] >= 700)]
if df_blast_results.shape[0] == 0:
df_blast_results = pd.DataFrame(
self.h1_prediction.blast_results)
df_blast_results = df_blast_results[
(df_blast_results['mismatch'] <= 0)
& (df_blast_results['length'] >= 400)]
if df_blast_results.shape[0] == 0:
self.h1_prediction.is_missing = True
self.h1_prediction.top_result = None
self.h1_prediction.h1 = None
return
df_blast_results_over1000 = df_blast_results[
(df_blast_results['mismatch'] <= 5)
& (df_blast_results['length'] >= 1000)]
if df_blast_results_over1000.shape[0] > 0:
df_blast_results = df_blast_results_over1000.sort_values(
by='mismatch')
else:
df_blast_results = df_blast_results.sort_values(
by='bitscore', ascending=False)
result_dict = BlastReader.df_first_row_to_dict(
df_blast_results)
result_trunc = BlastReader.is_blast_result_trunc(
qstart=result_dict['qstart'],
qend=result_dict['qend'],
sstart=result_dict['sstart'],
send=result_dict['send'],
qlen=result_dict['qlen'],
slen=result_dict['slen'])
self.h1_prediction.top_result = result_dict
self.h1_prediction.is_trunc = result_trunc
self.h1_prediction.h1 = get_antigen_name(
self.h1_prediction.top_result['qseqid'])