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_reader():
input_items = ['>test1', 'ATCTGCTAGTCGA', 'ATCGAGTAGT', '>test2', 'ATCGATGC']
input_seq = '\n'.join(input_items)
res = list(GeneralSeqTools.fasta_reader(StringIO(input_seq)))
eq_(len(res), 2)
eq_(res[0][0], 'test1')
eq_(res[0][1], 'ATCTGCTAGTCGAATCGAGTAGT')
eq_(res[1][0], 'test2')
eq_(res[1][1], 'ATCGATGC')
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]
def GetConSeq(region, alphabet=generic_dna, subtype='B', drop_gaps=True):
if (alphabet == generic_dna) or (alphabet.lower() == 'dna'):
path = get_region_file(region, 'dna')
elif (alphabet == generic_protein) or (alphabet.lower() == 'pro'):
path = get_region_file(region, 'pro')
else:
raise(TypeError, 'alphabet must be: "dna", "pro", generic_dna, generic_protein')
seq = None
if path is None:
new_region, start, stop = get_region_span(region, alphabet)
conB_seq = GetConSeq(new_region,
subtype='B',
alphabet=alphabet,
drop_gaps=False)
sub_seq = GetConSeq(new_region,
subtype=subtype,
alphabet=alphabet,
drop_gaps=False)
nstart, nstop = (None, None)
print conB_seq
print sub_seq
conb_pos = 0
for aln_pos, l in enumerate(conB_seq):
if l != '-':
conb_pos += 1
if conb_pos == start:
nstart = aln_pos
if conb_pos == stop:
nstop = aln_pos
break
seq = sub_seq[nstart:nstop]
else:
wanted_key = 'CONSENSUS_'+subtype
with open(path) as handle:
for name, seq in GeneralSeqTools.fasta_reader(handle):
name = name.split('(')[0]
if name == wanted_key:
break
if drop_gaps:
return seq.replace('-', '').replace('$', '')
else:
return seq.replace('$', '')
# <codecell>
pat_data = pd.merge(redcap_data, df,
left_on ='SingleID',
right_on = 'SingleID',
how = 'outer').groupby('SingleID').first()
# <codecell>
import glob
ltr_files = sorted(glob.glob('/home/will/HIVReportGen/Data/PatientFasta/*LTR.fasta'))
ltr_seqs = {}
for f in ltr_files:
with open(f) as handle:
_, seq = GeneralSeqTools.fasta_reader(handle).next()
fname = os.path.basename(f).rsplit('-', 1)[0]
ltr_seqs[fname] = seq
# <codecell>
ltr_df = pd.DataFrame({
'LTR':pd.Series(ltr_seqs)
})
ltr_df.head()
# <codecell>
conb_ltr = ConSeqs.GetConSeq('ltr')
conb_ltr
writer.writerow((gbm, acc))
# <codecell>
files = [('C', sorted(glob.glob('/home/will/WLAHDB_data/SeqDump/C_*'))),
('B', sorted(glob.glob('/home/will/WLAHDB_data/SeqDump/B_*')))]
seqs = []
for sub, sfiles in files:
for f in sfiles:
with open(f) as handle:
base_name = f.rsplit(os.sep,1)[1].rsplit('.',1)[0]
prot = base_name.split('_')[1]
for name, seq in GeneralSeqTools.fasta_reader(handle):
seqs.append({
'Seq':seq,
'ID':gi_to_acc_dict[name],
'Prot':prot,
'Subtype':sub
})
seqdf = pd.DataFrame(seqs)
# <codecell>
pseqdf = pd.pivot_table(seqdf,
rows = ['Subtype', 'ID'],
cols = 'Prot',
values = 'Seq',
except ValueError:
print fname
seqs.append((pid, vn, prot, 1))
df = pd.DataFrame(seqs, columns=["Patient ID", "VisitNum", "Prot", "HasSeq"])
has_seq = pd.pivot_table(df, rows=["Patient ID", "VisitNum"], cols="Prot", values="HasSeq")
# <codecell>
import sys
sys.path.append("/home/will/PySeqUtils/")
import GeneralSeqTools
with open("/home/will/DrugStuff/pat_data.fasta") as handle:
seqs = list(GeneralSeqTools.fasta_reader(handle))
out = GeneralSeqTools.WebPSSM_V3_fasta(seqs)
# <codecell>
tmp = []
for row in out:
parts = row[0].split("-")
if len(parts) == 2:
pat, vnum = parts
else:
pat, vnum, _ = parts
tmp.append({"Patient ID": pat, "VisitNum": vnum, "IsR5": row[2] == "0", "IsX4": row[2] == "1"})
tropism = pd.DataFrame(tmp).groupby(["Patient ID", "VisitNum"]).first()
for num, (gbm, acc) in enumerate(imap(get_gi_acc, gb_files)):
if (num == 100) or (num % 50000 == 0):
print num
gi_to_acc_dict[gbm] = acc
writer.writerow((gbm, acc))
# <codecell>
files = [('B', sorted(glob.glob('/home/will/WLAHDB_data/SeqDump/B_*')))]
seqs = []
for sub, sfiles in files:
for f in sfiles:
with open(f) as handle:
base_name = f.rsplit(os.sep,1)[1].rsplit('.',1)[0]
prot = base_name.split('_')[1]
for name, seq in GeneralSeqTools.fasta_reader(handle):
seqs.append({
'Seq':seq,
'ID':gi_to_acc_dict[name],
'Prot':prot,
})
seqdf = pd.DataFrame(seqs)
# <codecell>
pseqdf = pd.pivot_table(seqdf,
rows = 'ID',
cols = 'Prot',
values = 'Seq',
aggfunc = 'first')
