def test_prune(self):
folder = "NGS"
blast_data = []
f = open("NGS/blast_data.csv", "r")
tmp = f.readlines()
f.close()
for i in tmp:
blast_data.append(i.strip())
seq_record = SeqIO.parse("NGS/seq_record.fastq", "fastq")
ion_id = "3856"
min_aln_length = "40"
result = NGS.prune(folder, blast_data, seq_record, ion_id,
min_aln_length)
# It should drop on seq_record from the blast_data
self.assertEqual(len(result), 998)
def filter_reads(ion_chunk, blast_chunk, folder):
from Bio import SeqIO;
from pyphylogenomics import NGS
'''
\* *Internal function* \*
Accepting alignment lengths higher than 40 bp
longer than our primer lengths
'''
min_aln_length = 40;
blast_file = open(blast_chunk, "r");
tmp = blast_file.readlines();
blast_file.close();
blast_data = []
for i in tmp:
blast_data.append(i.strip())
# iterate over ion torrent reads
for seq_record in SeqIO.parse(ion_chunk, "fastq"):
if len(blast_data) > 0:
#print "\n\nNew record--------------------"
#print "seq record id @%s" % seq_record.id
# avoid processing seq_records that are not in blast file
# first id in blast_data
#print blast_data
first_id_in_blast_data = blast_data[0].split(",")[0]
#print "fist id in blast_data %s" % first_id_in_blast_data
if int(seq_record.id) >= int(first_id_in_blast_data):
#if str(seq_record.id) == ion_id and aln_length > min_aln_length:
if str(seq_record.id) == first_id_in_blast_data:
#print "prune"
blast_data = NGS.prune(folder, blast_data, seq_record,
first_id_in_blast_data, min_aln_length)
else:
break
