def write_in_fastafile(filename, res, min_length=50):
corpus = []
labels = []
for seq, score, pval, _, _ in res:
if len(seq) > min_length and pval < 0.05:
corpus.append(seq)
labels.append(' '.join(
['+' if score > 0 else '-', 'p-val:' + str(pval)]))
FileUtility.create_fasta_file(filename, corpus, labels)
def align_markers(self, p_value_threshold):
final_results = []
for idx, (seq, description) in tqdm.tqdm(self.seq_IDS.items()):
pval = float(description.split(':')[1])
if pval <= p_value_threshold:
FileUtility.create_fasta_file('temp.fasta', [seq], ['temp'])
blastx_cline = NcbiblastnCommandline(
query='temp.fasta',
db=
"/mounts/data/proj/asgari/dissertation/git_repos/16S_datasets/EZ/raw/eztaxon_qiime_full.fasta",
evalue=0.001,
outfmt=5,
out="temp.xml")
blastx_cline()
f = open("temp.xml", 'r')
blast_records = NCBIXML.parse(f)
flag = False
score = -1
alignment_length = -1
results = []
for blast_record in blast_records:
for alignment in blast_record.alignments:
for hsp in alignment.hsps:
if not flag and score == -1:
score = hsp.score
alignment_length = hsp.align_length
flag = True
if hsp.score >= score and hsp.align_length >= alignment_length and 'Eukarya' not in self.ez_taxa_dict[
alignment.hit_id]:
results.append(
(self.ez_taxa_dict[alignment.hit_id],
hsp.expect))
if len(results) > 0:
res = self.lowest_certain_level(results)
if res:
final_results.append(
(seq, self.refine_ez_taxonomy(res) + idx[-1],
pval))
else:
final_results.append((seq, 'ZZZNOVEL' + idx[-1], pval))
else:
final_results.append((seq, 'ZZZNOVEL' + idx[-1], pval))
# sorted markers by the taxonomy information of the last certain level
self.aligned_markers = sorted(final_results,
key=operator.itemgetter(1),
reverse=False)
self.min_p_value = p_value_threshold
self.update_matrix_by_markers()
def _perform_alignment(self, idx__seq_discrpt):
idx, (seq, description) = idx__seq_discrpt
pval = float(description.split(':')[1])
final_results = []
if pval <= self.p_value_threshold:
FileUtility.create_fasta_file('../tmp/temp' + str(idx) + '.fasta',
[seq], ['temp'])
blastx_cline = NcbiblastnCommandline(
query='../tmp/temp' + str(idx) + '.fasta',
db=
"/mounts/data/proj/asgari/dissertation/git_repos/16S_datasets/EZ/raw/eztaxon_qiime_full.fasta",
evalue=0.001,
outfmt=5,
out='../tmp/temp' + str(idx) + '.xml')
blastx_cline()
f = open('../tmp/temp' + str(idx) + '.xml', 'r')
blast_records = NCBIXML.parse(f)
flag = False
score = -1
alignment_length = -1
results = []
for blast_record in blast_records:
for alignment in blast_record.alignments:
for hsp in alignment.hsps:
if not flag and score == -1:
score = hsp.score
alignment_length = hsp.align_length
flag = True
if hsp.score >= score and hsp.align_length >= alignment_length and 'Eukarya' not in self.ez_taxa_dict[
alignment.hit_id]:
results.append(
(self.ez_taxa_dict[alignment.hit_id],
hsp.expect))
if len(results) > 0:
res = self.lowest_certain_level(results)
if res:
final_results = (seq,
self.refine_ez_taxonomy(res) + idx[-1],
pval)
else:
final_results = (seq, 'ZZZNOVEL' + idx[-1], pval)
else:
final_results = (seq, 'ZZZNOVEL' + idx[-1], pval)
return final_results
