def seq_batch_query():
con = sqlite3.connect('./data/DB')
cur = con.cursor()
list_file = input('list file name:\n')
with open(list_file, 'r') as In:
organism_list = In.read().split(sep='\n')
cur.execute('CREATE TABLE IF NOT EXISTS tasklist (Name TEXT);')
for organism in organism_list:
cur.execute('INSERT INTO tasklist (Name) VALUES (?);', (organism, ))
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism IN (SELECT Name FROM tasklist) ORDER BY Head',
(organism))
result = cur.fetchall()
cur.execute('DROP TABLE tasklist;')
cur.close()
con.close()
query_result = []
for i in result:
title = '|'.join([str(i[0]), i[1], i[2], i[3]])
filename = i[2]
sequence = MutableSeq(i[5])
if i[4] == '-1':
sequence.seq = sequence.reverse_complement()
record = [title, filename, sequence]
query_result.append(record)
for i in query_result:
with open(''.join(['./out/', i[1], '.fasta']), 'a') as Fileout:
Fileout.write('>%s\n%s\n' % (i[0], i[2]))
# rps12 may have larger than 50k fragments, here to filter it
rps12 = SeqIO.parse('./out/rps12.fasta', 'fasta')
rps12short = list()
for item in rps12:
if len(item.seq) < 4000:
rps12short.append(item)
SeqIO.write(rps12short, './out/rps12short.fasta', 'fasta')
print('Done.\n')
def seq_batch_query():
con = sqlite3.connect('./data/DB')
cur = con.cursor()
list_file = input('list file name:\n')
with open(list_file, 'r') as In:
organism_list = In.read().split(sep='\n')
cur.execute('CREATE TABLE IF NOT EXISTS tasklist (Name TEXT);')
for organism in organism_list:
cur.execute('INSERT INTO tasklist (Name) VALUES (?);', (organism,))
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism IN (SELECT Name FROM tasklist) ORDER BY Head',
(organism))
result = cur.fetchall()
cur.execute('DROP TABLE tasklist;')
cur.close()
con.close()
query_result = []
for i in result:
title = '|'.join([str(i[0]), i[1], i[2], i[3]])
filename = i[2]
sequence = MutableSeq(i[5])
if i[4] == '-1':
sequence.seq = sequence.reverse_complement()
record = [title, filename, sequence]
query_result.append(record)
for i in query_result:
with open(''.join(['./out/', i[1], '.fasta']), 'a') as Fileout:
Fileout.write('>%s\n%s\n' % (i[0], i[2]))
# rps12 may have larger than 50k fragments, here to filter it
rps12 = SeqIO.parse('./out/rps12.fasta', 'fasta')
rps12short = list()
for item in rps12:
if len(item.seq) < 4000:
rps12short.append(item)
SeqIO.write(rps12short, './out/rps12short.fasta', 'fasta')
print('Done.\n')
def seq_query():
"""Sequence query function, to be continued.
"""
query_type = input('1.Specific fragment\n'
'2.Specific Organism\n'
'3.Specific gene\n'
'4.All\n'
'5.All cds\n')
organize = input('Organize output?(y/n)\n')
if query_type not in ['1', '2', '3', '4', '5']:
raise ValueError('wrong input!\n')
con = sqlite3.connect('./data/DB')
cur = con.cursor()
if query_type == '1':
organism = input('Organism:\n')
gene = input('Gene:\n')
frag_type = input(
'Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer):\n')
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence FROM main WHERE Name LIKE ? AND Type = ? AND Organism=?',
('%' + gene + '%', frag_type, organism))
result = cur.fetchall()
elif query_type == '2':
organism = input('Organism:\n')
frag_type = input(
'Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer, whole, fragments):\n'
)
if frag_type == 'fragments':
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism = ? ORDER BY Head',
(organism, ))
else:
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism LIKE ? AND Type = ? ORDER BY Head',
('%' + organism + '%', frag_type))
result = cur.fetchall()
elif query_type == '3':
gene = input('Gene:\n')
frag_type = input(
'Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer):\n')
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence FROM main WHERE Name LIKE ? AND Type = ? ORDER BY Taxon',
('%' + gene + '%', frag_type))
result = cur.fetchall()
elif query_type == '4':
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main ORDER BY Taxon'
)
result = cur.fetchall()
elif query_type == '5':
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE type = "cds" ORDER BY Taxon'
)
result = cur.fetchall()
query_result = []
for i in result:
title = '|'.join([str(i[0]), i[1], i[2], i[3]])
sequence = MutableSeq(i[5])
gene = i[2]
if i[4] == '-1':
sequence.seq = sequence.reverse_complement()
record = [title, gene, sequence]
query_result.append(record)
if organize == 'y':
if not exists('output'):
makedirs('output')
for i in query_result:
file_name = ''.join(
['output', '/', i[1].replace('/', ''), '.fasta'])
with open(file_name, 'a') as output_file:
output_file.write('>%s\n%s\n' % (i[0], i[2]))
else:
output = input('Enter output filename:\n')
with open('.'.join([output, 'fasta']), 'w') as output_file:
for i in query_result:
output_file.write('>%s\n%s\n' % (i[0], i[2]))
cur.close()
con.close()
print('Done.\n')
def seq_query():
"""Sequence query function, to be continued.
"""
query_type = input(
'1.Specific fragment\n'
'2.Specific Organism\n'
'3.Specific gene\n'
'4.All\n'
'5.All cds\n'
)
organize = input('Organize output?(y/n)\n')
if query_type not in ['1', '2', '3', '4', '5']:
raise ValueError('wrong input!\n')
con = sqlite3.connect('./data/DB')
cur = con.cursor()
if query_type == '1':
organism = input('Organism:\n')
gene = input('Gene:\n')
frag_type = input('Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer):\n')
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence FROM main WHERE Name LIKE ? AND Type = ? AND Organism=?',
('%' + gene + '%', frag_type, organism))
result = cur.fetchall()
elif query_type == '2':
organism = input('Organism:\n')
frag_type = input('Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer, whole, fragments):\n')
if frag_type == 'fragments':
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism = ? ORDER BY Head',
(organism,))
else:
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE Organism LIKE ? AND Type = ? ORDER BY Head',
('%' + organism + '%', frag_type))
result = cur.fetchall()
elif query_type == '3':
gene = input('Gene:\n')
frag_type = input('Fragment type(gene, cds, rRNA, tRNA, exon, intron, spacer):\n')
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence FROM main WHERE Name LIKE ? AND Type = ? ORDER BY Taxon',
('%' + gene + '%', frag_type))
result = cur.fetchall()
elif query_type == '4':
cur.execute('SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main ORDER BY Taxon')
result = cur.fetchall()
elif query_type == '5':
cur.execute(
'SELECT Taxon, Organism, Name, Type, Strand, Sequence, Head FROM main WHERE type = "cds" ORDER BY Taxon')
result = cur.fetchall()
query_result = []
for i in result:
title = '|'.join([str(i[0]), i[1], i[2], i[3]])
sequence = MutableSeq(i[5])
gene = i[2]
if i[4] == '-1':
sequence.seq = sequence.reverse_complement()
record = [title, gene, sequence]
query_result.append(record)
if organize == 'y':
if not exists('output'):
makedirs('output')
for i in query_result:
file_name = ''.join([
'output',
'/',
i[1].replace('/', ''),
'.fasta'
])
with open(file_name, 'a') as output_file:
output_file.write('>%s\n%s\n' % (i[0], i[2]))
else:
output = input('Enter output filename:\n')
with open('.'.join([output, 'fasta']), 'w') as output_file:
for i in query_result:
output_file.write('>%s\n%s\n' % (i[0], i[2]))
cur.close()
con.close()
print('Done.\n')
