def get_initial_allele_counts(self, fragment):
'''Get allele counts from the initial time point'''
import os
from hivwholeseq.patients.samples import SamplePat
for i in xrange(len(self.samples)):
sample = SamplePat(self.samples.iloc[i])
if os.path.isfile(sample.get_allele_counts_filename(fragment)):
return sample.get_allele_counts(fragment)
for fragment in fragments:
for samplename, sample in samples.iterrows():
fork_self(samplename,
fragment,
VERBOSE=VERBOSE,
qual_min=qual_min,
PCR=PCR,
maxreads=maxreads,
use_tests=use_tests)
sys.exit()
counts_all = []
for fragment in fragments:
counts = []
for samplename, sample in samples.iterrows():
sample = SamplePat(sample)
pname = sample.patient
if VERBOSE >= 2:
print pname, fragment, samplename
refseq = SeqIO.read(
get_initial_reference_filename(pname, fragment), 'fasta')
fn_out = sample.get_allele_cocounts_filename(fragment,
PCR=PCR,
qual_min=qual_min,
compressed=True)
fn = sample.get_mapped_filtered_filename(
fragment, PCR=PCR, decontaminated=True) #FIXME
if save_to_file:
def itersamples(self):
'''Generator for samples in this patient, each with extended attributes'''
from hivwholeseq.patients.samples import SamplePat
for samplename, sample in self.samples.iterrows():
yield SamplePat(sample)
def initial_sample(self):
'''The initial sample used as a mapping reference'''
from .samples import SamplePat
return SamplePat(self.samples.iloc[0])
fragments = args.fragments
submit = args.submit
VERBOSE = args.verbose
n_pairs = args.maxreads
summary = args.summary
PCR = args.PCR
# Collect all sequenced samples from patients
samples_pat = lssp()
if pnames is not None:
samples_seq = []
for pname in pnames:
patient = load_patient(pname)
patient.discard_nonsequenced_samples()
for samplename_pat, sample_pat in patient.samples.iterrows():
sample_pat = SamplePat(sample_pat)
samples_seq.append(sample_pat.samples_seq)
samples_seq = pd.concat(samples_seq)
elif samplenames is not None:
samples_seq = lss()
ind = samples_pat.index.isin(samplenames)
samplenames_pat = samples_pat.index[ind]
samples_seq = samples_seq.loc[samples_seq['patient sample'].isin(
samplenames_pat)]
else:
samples_seq = lss()
samples_seq = samples_seq.loc[samples_seq['patient sample'].isin(
samples_pat.index)]
VERBOSE = args.verbose
repn = args.repnumber
samplename = args.sample
patient = load_patient(pname)
patient.discard_nonsequenced_samples()
mkdirs(get_initial_reference_foldername(pname))
if not fragments:
fragments = ['F' + str(i) for i in xrange(1, 7)]
if VERBOSE >= 3:
print 'fragments', fragments
if samplename is None:
sample = SamplePat(patient.samples.iloc[samplen])
else:
sample = load_sample_sequenced(samplename)
for fragment in fragments:
sample_seq = SampleSeq(sample.samples_seq.iloc[repn])
seq_run = sample_seq['seq run']
adaID = sample_seq['adapter']
dataset = sample_seq.sequencing_run
data_folder = dataset.folder
if VERBOSE:
print 'Initial sample:', sample_seq.name, sample_seq['seq run'],
print sample_seq.adapter
