def samples_seq(self):
'''Sequencing samples that refer to this patient sample'''
if self._sequenced_samples is None:
#TODO: optimize this call
from hivwholeseq.patients.filenames import get_mapped_to_initial_filename
from hivwholeseq.sequencing.samples import load_samples_sequenced as lss
samples_seq = lss()
samples_seq = samples_seq.loc[samples_seq['patient sample'] ==
self.name]
self._sequenced_samples = samples_seq
return self._sequenced_samples.copy()
def discard_nonsequenced_samples(self):
'''Discard all samples that have not been sequenced yet'''
from hivwholeseq.sequencing.samples import load_samples_sequenced as lss
samples_sequenced = lss()
samples_sequenced_set = set(samples_sequenced.loc[:, 'patient sample']) - set(['nan'])
samples = self.samples.loc[self.samples.index.isin(samples_sequenced_set)]
## Add info on sequencing
## FIXME: why is this here?!
## FIXME: this is buggy is so many ways... pandas is nto great at this
#samples_seq_col = []
#for samplename in samples.index:
# ind = samples_sequenced.loc[:, 'patient sample'] == samplename
# samples_seq_col.append(samples_sequenced.loc[ind])
#samples.loc[:, 'samples seq'] = samples_seq_col
self.samples = samples
def discard_nonsequenced_samples(self):
'''Discard all samples that have not been sequenced yet'''
from hivwholeseq.sequencing.samples import load_samples_sequenced as lss
samples_sequenced = lss()
samples_sequenced_set = set(
samples_sequenced.loc[:, 'patient sample']) - set(['nan'])
samples = self.samples.loc[self.samples.index.isin(
samples_sequenced_set)]
## Add info on sequencing
## FIXME: why is this here?!
## FIXME: this is buggy is so many ways... pandas is nto great at this
#samples_seq_col = []
#for samplename in samples.index:
# ind = samples_sequenced.loc[:, 'patient sample'] == samplename
# samples_seq_col.append(samples_sequenced.loc[ind])
#samples.loc[:, 'samples seq'] = samples_seq_col
self.samples = samples
parser = argparse.ArgumentParser(description="make figure")
parser.add_argument('--redo', action='store_true', help='recalculate data')
params = parser.parse_args()
fragment = 'F1'
VERBOSE = 2
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'first')
fn_data = foldername+'data/'
mkdirs(fn_data)
fn_data = fn_data + 'minor_alleles_example.pickle'
if not os.path.isfile(fn_data) or params.redo:
samplename = 'NL4-3'
sample = lss(samplename)
counts = sample.get_allele_counts(fragment, merge_read_types=True)
data = compress_data(counts, samplename, fragment)
samplename = '27134'
sample = lssp(samplename)
counts = sample.get_allele_counts(fragment, merge_read_types=True)
data = compress_data(counts, samplename, fragment, data=data)
store_data(data, fn_data)
else:
data = load_data(fn_data)
plot_minor_allele_example(data,
VERBOSE=VERBOSE,
import sys
import os
from hivwholeseq.utils.generic import mkdirs
from hivwholeseq.patients.samples import itersample
from hivwholeseq.sequencing.samples import load_samples_sequenced as lss
from hivwholeseq.patients.samples import load_samples_sequenced as lssp
from hivwholeseq.sequencing.filenames import get_sample_foldername
# Script
if __name__ == '__main__':
samples_pat = lssp()
samples_seq = lss()
for samplename, sample in itersample(samples_pat):
root_foldername = sample.get_foldername()+'samples_sequencing/'
mkdirs(root_foldername)
for samplenameseq, sampleseq in samples_seq.iterrows():
if sampleseq['patient sample'] == samplename:
src_folder = get_sample_foldername(samplenameseq)
dst_folder = root_foldername+samplenameseq
if not os.path.islink(dst_folder):
os.symlink(src_folder, dst_folder)
print 'Symlink:', src_folder, dst_folder
else:
print 'Esists:', dst_folder
help='Execute the script in parallel on the cluster')
args = parser.parse_args()
seq_runs = args.runs
adaIDs = args.adaIDs
use_pats = args.use_pats
use_interactive = args.interactive
detail = args.detail
submit = args.submit
if submit:
fork_self(seq_runs, adaIDs=adaIDs, pats=use_pats, detail=detail)
sys.exit()
samples_pat = lssp(include_wrong=True)
samples = lss()
samples = samples.loc[samples['seq run'].isin(seq_runs)]
if adaIDs is not None:
samples = samples.loc[samples.adapter.isin(adaIDs)]
if len(seq_runs) >= 2:
samples.sort(columns=['patient sample', 'seq run'], inplace=True)
for isa, (samplename, sample) in enumerate(samples.iterrows()):
sample = SampleSeq(sample)
print sample.name, 'seq:', sample['seq run'], sample.adapter,
if sample['patient sample'] == 'nan':
print 'not a patient sample',
if use_pats:
print '(skip)'
help='Number of reads analyzed')
parser.add_argument('--verbose', type=int, default=0,
help='Verbosity level [0-3]')
parser.add_argument('--minor-allele', action='store_true', dest='minor_allele',
help='Plot also minor allele')
args = parser.parse_args()
samplenames = args.samples
seq_runs = args.runs
adaIDs = args.adaIDs
fragments = args.fragments
maxreads = args.maxreads
VERBOSE = args.verbose
use_minor_allele = args.minor_allele
samples = lss()
if samplenames is not None:
samples = samples.loc[samples.index.isin(samplenames)]
else:
ind = np.zeros(len(samples), bool)
for seq_run in seq_runs:
dataset = load_sequencing_run(seq_run)
data_folder = dataset.folder
samples_run = dataset.samples
# If the script is called with no adaID, iterate over all
if adaIDs is not None:
samples_run = samples_run.loc[samples_run.adapter.isin(adaIDs)]
ind |= samples.index.isin(samples_run.index)
parser = argparse.ArgumentParser(description="make figure")
parser.add_argument('--redo', action='store_true', help='recalculate data')
params = parser.parse_args()
fragment = 'F1'
VERBOSE = 2
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'first')
fn_data = foldername + 'data/'
mkdirs(fn_data)
fn_data = fn_data + 'minor_alleles_example.pickle'
if not os.path.isfile(fn_data) or params.redo:
samplename = 'NL4-3'
sample = lss(samplename)
counts = sample.get_allele_counts(fragment, merge_read_types=True)
data = compress_data(counts, samplename, fragment)
samplename = '27134'
sample = lssp(samplename)
counts = sample.get_allele_counts(fragment, merge_read_types=True)
data = compress_data(counts, samplename, fragment, data=data)
store_data(data, fn_data)
else:
data = load_data(fn_data)
plot_minor_allele_example(
data,
VERBOSE=VERBOSE,
