def add_seq_to_reads(read_file, out_file):
with open(read_file) as handle:
with open(out_file, 'w') as ohandle:
new_seqs = []
for name, seq in GeneralSeqTools.fasta_reader(handle):
new_seqs.append((name + ';' + seq, seq))
GeneralSeqTools.fasta_writer(ohandle, new_seqs)
def test_fasta_writer():
items = ['>test1', 'ATCTGCTAGTCGAATCGAGTAGT', '>test2', 'ATCGATGC']
test_seq = '\n'.join(items) + '\n'
handle = StringIO()
GeneralSeqTools.fasta_writer(handle, [('test1', 'ATCTGCTAGTCGAATCGAGTAGT'),
('test2', 'ATCGATGC')])
handle.seek(0)
data = handle.read()
eq_(test_seq, data)
def run_mafft(inseqs):
orig_order = [name for name, _ in inseqs]
with NTF(suffix = '.fasta') as handle:
GeneralSeqTools.fasta_writer(handle, inseqs)
handle.flush()
os.fsync(handle)
cmd = 'mafft --quiet --op 10 --ep 0.123 %s' % handle.name
out = check_output(shlex.split(cmd))
out_dict = dict(GeneralSeqTools.fasta_reader(StringIO(out)))
return [(name, out_dict[name]) for name in orig_order]
1, counts = mot.counts)
make_logo(None,
pwm_name_r,
fix_name,
1, counts = mot.reverse_complement().counts)
if mask.mean() > 0.5:
r5mask, x4mask = (mask, ~mask)
else:
r5mask, x4mask = (~mask, mask)
x4_name = '/home/will/SubCData/TFfasta/X4-%s-%s' % (fix_name, sub)
r5_name = '/home/will/SubCData/TFfasta/R5-%s-%s' % (fix_name, sub)
with open(x4_name+'.fasta', 'w') as handle:
x4_seqs = pred_counts['Seqs'][col][x4mask].dropna().to_dict().items()
x4_scores = pred_counts['Scores'][col][x4mask].astype(float).dropna()
GeneralSeqTools.fasta_writer(handle, x4_seqs)
if len(x4_seqs) == 0:
os.remove(x4_name+'.fasta')
continue
make_logo(x4_name+'.fasta',
x4_name+'.png',
'X4-%s-%s' % (sub, col),
start_pos)
with open(r5_name+'.fasta', 'w') as handle:
r5_seqs = pred_counts['Seqs'][col][r5mask].dropna().to_dict().items()
r5_scores = pred_counts['Scores'][col][r5mask].astype(float).dropna()
GeneralSeqTools.fasta_writer(handle, r5_seqs)
make_logo(r5_name+'.fasta',
r5_name+'.png',
'R5-%s-%s' % (sub, col),
# <codecell>
seq_df = pd.pivot_table(pd.DataFrame(seqs),
rows = 'GI',
cols = 'Prot',
values = 'Seq',
aggfunc = 'first')
# <codecell>
from Bio import Seq
from Bio.Alphabet import generic_dna
res = Seq.Seq('ATG', alphabet=generic_dna).translate()
res.tostring()
# <codecell>
def translate(inseq):
return Seq.Seq(inseq, alphabet=generic_dna).translate().tostring()
benj_seqs = seq_df[['LTR', 'Tat_1', 'Tat_2', 'Vpr', 'V3']].dropna()['Tat_2'].map(translate)
# <codecell>
with open('/home/will/Downloads/tat2_for_benj.fasta', 'w') as handle:
GeneralSeqTools.fasta_writer(handle, benj_seqs.to_dict().items())
# <codecell>
ablocks.append(run_mafft(block))
inseqs = join_blocks(ablocks)
return inseqs
# <codecell>
aligned_seqs = run_mafft(raw_seqs)
# <codecell>
refined = refine_alignment(aligned_seqs)
# <codecell>
with open('/home/will/SubCData/refined.fasta', 'w') as handle:
GeneralSeqTools.fasta_writer(handle, refined)
# <codecell>
refined = join_blocks(aligned_blocks)
# <codecell>
aligned_seqs[0]
# <codecell>
