patients = load_patients()
if pnames is not None:
patients = patients.loc[pnames]
data = []
for pname, patient in patients.iterrows():
if VERBOSE >= 1:
print patient.code, start, end
if submit:
fork_self(patient.code, width, gap, start, end, VERBOSE=VERBOSE,
freqmin=freqmin, countmin=countmin)
continue
patient = Patient(patient)
ref = patient.get_reference('genomewide')
L = len(ref)
win_start = start
while win_start + width - gap < min(L, end):
win_end = min(win_start + width, end, L)
if VERBOSE >= 1:
print patient.code, win_start, win_end
if VERBOSE >= 2:
print 'Get region haplotypes'
try:
datum = patient.get_local_haplotype_count_trajectories(\
'genomewide',
start=win_start,
patients = load_patients()
if pnames is not None:
patients = patients.loc[pnames]
if VERBOSE >= 3:
print 'patients', patients.index
if not len(patients):
raise ValueError('No patients found!')
maps_coord = defaultdict(dict)
for pname, patient in patients.iterrows():
patient = Patient(patient)
# Make maps for all annotations if not explicit
if regions is None:
patseqann = patient.get_reference('genomewide', format='gb')
regionspat = map(attrgetter('id'),
patseqann.features) + ['genomewide']
else:
regionspat = regions
for region in regionspat:
if VERBOSE >= 1:
print pname, region
refseq = load_custom_reference(refname, format='gb', region=region)
patseq = patient.get_reference(region)
mapco = build_coordinate_map(refseq, patseq, VERBOSE=VERBOSE)
mapco = np.array(mapco, int)
shift_mapco(mapco, refname, region)
regions = args.regions
VERBOSE = args.verbose
save_to_file = args.save
patients = load_patients()
if pnames is not None:
patients = patients.loc[pnames]
if VERBOSE >= 3:
print 'patients', patients.index
if not len(patients):
raise ValueError('No patients found!')
maps_coord = defaultdict(dict)
for pname, patient in patients.iterrows():
patient = Patient(patient)
# Make maps for all annotations if not explicit
if regions is None:
patseqann = patient.get_reference('genomewide', format='gb')
regionspat = map(attrgetter('id'), patseqann.features) + ['genomewide']
else:
regionspat = regions
for region in regionspat:
if VERBOSE >= 1:
print pname, region
coomap = patient.get_map_coordinates_reference(region,
refname=refname)
if VERBOSE >= 1:
print patient.code, start, end
if submit:
fork_self(patient.code,
width,
gap,
start,
end,
VERBOSE=VERBOSE,
freqmin=freqmin,
countmin=countmin)
continue
patient = Patient(patient)
ref = patient.get_reference('genomewide')
L = len(ref)
win_start = start
while win_start + width - gap < min(L, end):
win_end = min(win_start + width, end, L)
if VERBOSE >= 1:
print patient.code, win_start, win_end
if VERBOSE >= 2:
print 'Get region haplotypes'
try:
datum = patient.get_local_haplotype_count_trajectories(\
'genomewide',
start=win_start,
help='Verbosity level [0-4]')
args = parser.parse_args()
pnames = args.patients
regions = args.regions
VERBOSE = args.verbose
patients = load_patients()
if pnames:
patients = patients.loc[pnames]
alis = {}
for pname, patient in patients.iterrows():
patient = Patient(patient)
patient.discard_nonsequenced_samples()
# Guess regions if not specified
if regions is None:
refseq_gw = patient.get_reference('genomewide', 'gb')
regionspat = map(attrgetter('id'), refseq_gw.features) + ['genomewide']
else:
regionspat = regions
for region in regionspat:
if VERBOSE >= 1:
print pname, region
ali = patient.get_consensi_alignment(region)
alis[(region, pname)] = ali
# Prepare output structures
n_binsx = 5
binsy = [
0., 0.002, 0.01, 0.025, 0.12, 0.33, 0.67, 0.88, 0.975, 0.99, 0.998, 1.
]
props = {(gene, synkey): Propagator(n_binsx,
binsy=binsy,
use_logit=use_logit)
for gene in genes for synkey in ('syn', 'nonsyn')}
for pname, patient in patients.iterrows():
patient = Patient(patient)
samplenames = patient.samples.index
refseq = patient.get_reference('genomewide', format='gb')
for gene in genes:
if VERBOSE >= 1:
print pname, gene,
# Get the right fragment(s)
# FIXME: do better than this ;-)
frags = {'pol': ['F2', 'F3'], 'gag': ['F1'], 'env': ['F5', 'F6']}
fragments = frags[gene]
if VERBOSE >= 1:
print fragments
for fragment in fragments:
if VERBOSE >= 1:
for feature in refseq.features:
if feature.id[0] == 'F':
continue
print feature.id,
from hivwholeseq.utils.genome_info import genes
if feature.type in ('gene', 'protein'):
print feature.extract(refseq).seq.translate()
else:
print feature.extract(refseq).seq
print ''
try:
refseq_old = patient.get_reference('genomewide', format='gb')
except IOError:
if VERBOSE >= 1:
print "Old annotated reference not found (that's ok)"
refseq_old = None
if refseq_old is not None:
try:
compare_annotations(refseq, refseq_old, VERBOSE=VERBOSE)
except ValueError:
if use_force:
print 'Annotations differ from old sequence'
else:
raise
if use_save:
if 'genomewide' in fragments:
do_genomewide = True
del fragments[fragments.index('genomewide')]
else:
do_genomewide = False
for pname, patient in patients.iterrows():
print pname
patient = Patient(patient)
patient.discard_nonsequenced_samples()
for fragment in fragments:
if VERBOSE >= 1:
print fragment
ref = patient.get_reference(fragment)
refm = np.array(ref, 'S1')
af0 = patient.get_initial_allele_frequencies(fragment)
consm = alpha[af0.argmax(axis=0)]
seqm = consm.copy()
# Gaps in a reference are not wished for
if '-' in seqm:
seqm[seqm == '-'] = refm[seqm == '-']
seq = SeqRecord(Seq(''.join(seqm), ambiguous_dna),
id=ref.id,
name=ref.name,
description=ref.description)
if VERBOSE >= 2:
args = parser.parse_args()
VERBOSE = args.verbose
fragments = args.fragments
patients = load_patients()
for fragment in fragments:
if VERBOSE >= 1:
print fragment
refs = []
for pname, patient in patients.iterrows():
if VERBOSE >= 2:
print pname
patient = Patient(patient)
refs.append(patient.get_reference(fragment))
ali = align_muscle(*refs, sort=True)
# Check whether all references are complete (using the longest primers)
if VERBOSE >= 2:
print 'Check alignment'
alim = np.array(ali)
if (alim[:, :4] == '-').any():
raise ValueError('Gaps at the beginning of fragment found')
elif (alim[:, -4:] == '-').any():
raise ValueError('Gaps at the end of fragment found')
if VERBOSE >= 2:
print 'Save to file'
fn = get_reference_alignment_filename(fragment)
args = parser.parse_args()
VERBOSE = args.verbose
fragments = args.fragments
patients = load_patients()
for fragment in fragments:
if VERBOSE >= 1:
print fragment
refs = []
for pname, patient in patients.iterrows():
if VERBOSE >= 2:
print pname
patient = Patient(patient)
refs.append(patient.get_reference(fragment))
ali = align_muscle(*refs, sort=True)
# Check whether all references are complete (using the longest primers)
if VERBOSE >= 2:
print 'Check alignment'
alim = np.array(ali)
if (alim[:, :4] == '-').any():
raise ValueError('Gaps at the beginning of fragment found')
elif (alim[:, -4:] == '-').any():
raise ValueError('Gaps at the end of fragment found')
if VERBOSE >= 2:
print 'Save to file'
fn = get_reference_alignment_filename(fragment)
patients = patients.loc[patients.code != "p7"]
# Prepare output structures
n_binsx = 5
binsy = [0.0, 0.002, 0.01, 0.025, 0.12, 0.33, 0.67, 0.88, 0.975, 0.99, 0.998, 1.0]
props = {
(gene, synkey): Propagator(n_binsx, binsy=binsy, use_logit=use_logit)
for gene in genes
for synkey in ("syn", "nonsyn")
}
for pname, patient in patients.iterrows():
patient = Patient(patient)
samplenames = patient.samples.index
refseq = patient.get_reference("genomewide", format="gb")
for gene in genes:
if VERBOSE >= 1:
print pname, gene,
# Get the right fragment(s)
# FIXME: do better than this ;-)
frags = {"pol": ["F2", "F3"], "gag": ["F1"], "env": ["F5", "F6"]}
fragments = frags[gene]
if VERBOSE >= 1:
print fragments
for fragment in fragments:
if VERBOSE >= 1:
for feature in refseq.features:
if feature.id[0] == 'F':
continue
print feature.id,
from hivwholeseq.utils.genome_info import genes
if feature.type in ('gene', 'protein'):
print feature.extract(refseq).seq.translate()
else:
print feature.extract(refseq).seq
print ''
try:
refseq_old = patient.get_reference('genomewide', format='gb')
except IOError:
if VERBOSE >= 1:
print "Old annotated reference not found (that's ok)"
refseq_old = None
if refseq_old is not None:
try:
compare_annotations(refseq, refseq_old, VERBOSE=VERBOSE)
except ValueError:
if use_force:
print 'Annotations differ from old sequence'
else:
raise
if use_save:
