def build_coordinate_map(refseq, patseq, VERBOSE=0, score_gapopen=-20, **kwargs):
'''Build the coordinate map
Parameters
**kwargs: passed to alignment function (e.g. alignment penalties)
'''
from seqanpy import align_global
(score, ali1, ali2) = align_global(refseq, patseq, score_gapopen=score_gapopen,
**kwargs)
patseq_start = len(ali2) - len(ali2.lstrip('-'))
patseq_end = len(ali2.rstrip('-'))
if VERBOSE >= 3:
from hivwholeseq.utils.sequence import pretty_print_pairwise_ali
pretty_print_pairwise_ali([ali1[patseq_start: patseq_end],
ali2[patseq_start: patseq_end]],
name1=refseq.name, name2=patseq.name)
# Bijective map
mapbi = []
pos_ref = patseq_start
pos_ini = 0
for col in xrange(patseq_start, patseq_end):
nuc_ref = ali1[col]
nuc_ini = ali2[col]
if (nuc_ref != '-') and (nuc_ini != '-'):
mapbi.append((pos_ref, pos_ini))
pos_ref += 1
pos_ini += 1
elif (nuc_ref != '-'):
pos_ref += 1
elif (nuc_ini != '-'):
pos_ini += 1
return mapbi
def check_similarity_initial_sample(refseq,
sample_seq,
fragment,
VERBOSE=0,
maxdiff=10):
'''Check whether the reference looks similar to the initial sample'''
from seqanpy import align_global
(score, ali1, ali2) = align_global(str(refseq.seq),
str(sample_seq.seq),
band=50)
alim = np.zeros((2, len(ali1)), 'S1')
alim[0] = np.fromstring(ali1, 'S1')
alim[1] = np.fromstring(ali2, 'S1')
n_diff = (alim[0] != alim[1]).sum()
if VERBOSE >= 2:
print fragment + ': difference between ref and initial consensus:', n_diff
if n_diff > maxdiff:
print 'ERROR: '+fragment+', reference is not similar to initial consensus ('+\
str(sample_init_seq.name)+', '+\
str(n_diff)+' differences)'
return False
elif VERBOSE >= 3:
print 'OK: reference is similar to initial consensus ('+\
str(sample_init_seq.name)+', '+\
str(n_diff)+' differences)'
return True
def on_click(event):
'''Print sequence on click'''
mouseevent = event.mouseevent
artist = event.artist
i_clicked = int(artist.get_label())
(score, ali1, ali2) = align_global(seq0, seqs[i_clicked], score_gapopen=-20)
pretty_print_pairwise_ali((ali1, ali2), name1='cons0', name2='clicked', width=120)
def __init__(self, ref1='HXB2', ref2='NL4-3'):
super(ReferenceTranslator, self).__init__()
self.ref1 = ref1
self.ref2 = ref2
self.refseq1 = SeqIO.read(get_custom_reference_filename(self.ref1, format='gb'), format='genbank').seq
self.refseq2 = SeqIO.read(get_custom_reference_filename(self.ref2, format='gb'), format='genbank').seq
from seqanpy import align_global
(score, ali1, ali2) = align_global(str(self.refseq1), str(self.refseq2), band=200)
self.count1 = np.cumsum(np.fromstring(ali1,'S1')!='-')-1
self.count2 = np.cumsum(np.fromstring(ali2,'S1')!='-')-1
def __init__(self, ref1='HXB2', ref2='NL4-3'):
super(ReferenceTranslator, self).__init__()
self.ref1 = ref1
self.ref2 = ref2
self.refseq1 = SeqIO.read(get_custom_reference_filename(self.ref1,
format='gb'),
format='genbank').seq
self.refseq2 = SeqIO.read(get_custom_reference_filename(self.ref2,
format='gb'),
format='genbank').seq
from seqanpy import align_global
(score, ali1, ali2) = align_global(str(self.refseq1),
str(self.refseq2),
band=200)
self.count1 = np.cumsum(np.fromstring(ali1, 'S1') != '-') - 1
self.count2 = np.cumsum(np.fromstring(ali2, 'S1') != '-') - 1
def build_coordinate_map(refseq,
patseq,
VERBOSE=0,
score_gapopen=-20,
**kwargs):
'''Build the coordinate map
Parameters
**kwargs: passed to alignment function (e.g. alignment penalties)
'''
from seqanpy import align_global
(score, ali1, ali2) = align_global(refseq,
patseq,
score_gapopen=score_gapopen,
**kwargs)
patseq_start = len(ali2) - len(ali2.lstrip('-'))
patseq_end = len(ali2.rstrip('-'))
if VERBOSE >= 3:
from hivwholeseq.utils.sequence import pretty_print_pairwise_ali
pretty_print_pairwise_ali(
[ali1[patseq_start:patseq_end], ali2[patseq_start:patseq_end]],
name1=refseq.name,
name2=patseq.name)
# Bijective map
mapbi = []
pos_ref = patseq_start
pos_ini = 0
for col in xrange(patseq_start, patseq_end):
nuc_ref = ali1[col]
nuc_ini = ali2[col]
if (nuc_ref != '-') and (nuc_ini != '-'):
mapbi.append((pos_ref, pos_ini))
pos_ref += 1
pos_ini += 1
elif (nuc_ref != '-'):
pos_ref += 1
elif (nuc_ini != '-'):
pos_ini += 1
return mapbi
def check_protein(fea, seqgw, VERBOSE=0, delta_pos=2.5):
'''Check a protein annotation'''
seq = fea.extract(seqgw).seq
if len(seq) % 3:
raise ValueError('The length of ' + fea.id + ' is not a multiple of 3')
if 'N' in seq:
raise ValueError('N nucleotides found in ' + fea.id)
if '-' in seq:
raise ValueError('Gaps found in ' + fea.id)
prot = seq.translate()
if ('*' in prot) and (prot.find('*') != len(prot) - 1):
raise ValueError('Premature stops found in ' + fea.id)
if 'X' in prot:
raise ValueError('X amino acids found in ' + fea.id)
# Compare to HXB2
from hivwholeseq.reference import load_custom_reference
ref = load_custom_reference('HXB2', region=fea.id)
from seqanpy import align_global
(score, alis, alir) = align_global(seq, ref, score_gapopen=-20)
if VERBOSE >= 3:
from hivwholeseq.utils.sequence import pretty_print_pairwise_ali
pretty_print_pairwise_ali((alir, alis),
name1='HXB2',
name2='seq',
width=100)
scoremax = 3 * len(alis)
delta = scoremax - score
if delta > delta_pos * len(alis):
raise ValueError('The sequence of ' + fea.id +
' looks different from HXB2')
def align_codon_pairwise(seqstr, refstr, **kwargs):
'''Pairwise alignment via codons
Parameters:
**kwargs: passed down to SeqAn alignment function
'''
from Bio.Seq import translate
from seqanpy import align_global
from itertools import izip
if len(seqstr) % 3:
raise ValueError('The length of the first sequence is not a multiple of 3')
elif len(refstr) % 3:
raise ValueError('The length of the second sequence is not a multiple of 3')
seqpr = translate(seqstr)
refpr = translate(refstr)
(score, alis, alir) = align_global(seqpr, refpr, **kwargs)
aliseq = []
aliref = []
poss = 0
posr = 0
for aas, aar in izip(alis, alir):
if aas == '-':
aliseq.append('---')
else:
aliseq.append(seqstr[poss: poss+3])
poss += 3
if aar == '-':
aliref.append('---')
else:
aliref.append(refstr[posr: posr+3])
posr += 3
aliseq = ''.join(aliseq)
aliref = ''.join(aliref)
return (aliseq, aliref)
def check_similarity_initial_sample(refseq, sample_seq, fragment, VERBOSE=0, maxdiff=10):
'''Check whether the reference looks similar to the initial sample'''
from seqanpy import align_global
(score, ali1, ali2) = align_global(str(refseq.seq), str(sample_seq.seq), band=50)
alim = np.zeros((2, len(ali1)), 'S1')
alim[0] = np.fromstring(ali1, 'S1')
alim[1] = np.fromstring(ali2, 'S1')
n_diff = (alim[0] != alim[1]).sum()
if VERBOSE >= 2:
print fragment+': difference between ref and initial consensus:', n_diff
if n_diff > maxdiff:
print 'ERROR: '+fragment+', reference is not similar to initial consensus ('+\
str(sample_init_seq.name)+', '+\
str(n_diff)+' differences)'
return False
elif VERBOSE >=3:
print 'OK: reference is similar to initial consensus ('+\
str(sample_init_seq.name)+', '+\
str(n_diff)+' differences)'
return True
def check_protein(fea, seqgw, VERBOSE=0, delta_pos=2.5):
'''Check a protein annotation'''
seq = fea.extract(seqgw).seq
if len(seq) % 3:
raise ValueError('The length of '+fea.id+' is not a multiple of 3')
if 'N' in seq:
raise ValueError('N nucleotides found in '+fea.id)
if '-' in seq:
raise ValueError('Gaps found in '+fea.id)
prot = seq.translate()
if ('*' in prot) and (prot.find('*') != len(prot) - 1):
raise ValueError('Premature stops found in '+fea.id)
if 'X' in prot:
raise ValueError('X amino acids found in '+fea.id)
# Compare to HXB2
from hivwholeseq.reference import load_custom_reference
ref = load_custom_reference('HXB2', region=fea.id)
from seqanpy import align_global
(score, alis, alir) = align_global(seq, ref, score_gapopen=-20)
if VERBOSE >= 3:
from hivwholeseq.utils.sequence import pretty_print_pairwise_ali
pretty_print_pairwise_ali((alir, alis), name1='HXB2', name2='seq',
width=100)
scoremax = 3 * len(alis)
delta = scoremax - score
if delta > delta_pos * len(alis):
raise ValueError('The sequence of '+fea.id+' looks different from HXB2')
indrandom = np.arange(len(ds))
np.random.shuffle(indrandom)
ds = ds[indrandom]
edges = np.array(edges)[indrandom]
seqs = [seqs[i] for i in indrandom]
for irp, (dpair, edgepair, seqpair) in enumerate(izip(ds, edges, seqs)):
# NOTE: Take only the most distant read of a pair
print irp, dpair
i = dpair.argmax()
d = dpair[i]
edge = edgepair[i]
seq = seqpair[i]
(score, ali1, ali2) = align_global(seq, consrec[edge[0]: edge[1]])
scoremax = 3 * len(ali1)
delta = scoremax - score
ali = [ali2, ali1]
print 'Alignment to its own consensus (delta = '+str(delta)+')'
pretty_print_pairwise_ali(ali,
'cons',
'read'+str(i+1)+' '+str(edge),
len_name=25, width=90)
print ''
# Compare to all consensi and find the closest
alifr = alis[fragment]
alifrpw = []
for cons in alifr:
date: 30/01/14
content: Test of the seqanpy module from Python.
'''
# Modules
# Script
if __name__ == '__main__':
# Try import
import seqanpy as sap
# Global pairwise alignment
seq1 = 'AAAGGTCTA'
seq2 = 'AAATCGA'
output = sap.align_global(seq1, seq2, band=5)
print output
# Overlap pairwise alignment
seq1 = 'AAAGGTCTA'
seq2 = 'ATCT'
output = sap.align_overlap(seq1, seq2)
print output
# Overlap pairwise alignment cutting flanks
seq1 = 'AAAGGTCTA'
seq2 = 'ATCT'
output = sap.align_overlap(seq1, seq2, cut_flanks=True)
print output
# Ladder pairwise alignment
if do_genomewide:
seqs = [patient.get_reference('F'+str(i)) for i in xrange(1, 7)]
seq = merge_sequences_fragments(seqs, VERBOSE=VERBOSE)
seq = SeqRecord(Seq(seq, ambiguous_dna),
id=pname+'_genomewide',
name=pname+'_genomewide',
description='Genomewide reference for patient '+pname)
ref = patient.get_reference('genomewide')
if VERBOSE >= 2:
from seqanpy import align_global
from hivwholeseq.utils.sequence import pretty_print_pairwise_ali
(score, ali1, ali2) = align_global(ref, seq, score_gapopen=-20)
pretty_print_pairwise_ali((ali1, ali2),
name1='Old ref', name2='New ref',
width=100)
# TODO: resplit sequences to make sure we cover the whole F5a, F3c,
# etc. THIS CHANGES THE COORDINATES!
if use_save:
fn = patient.get_reference_filename('genomewide', 'fasta')
fn_old = fn.replace('.fasta', '_old.fasta')
save_protect(fn, fn_old, VERBOSE=VERBOSE)
def global_test():
print('Test align_global')
import seqanpy
(score, ali1, ali2) = seqanpy.align_global('ACCGT', 'AGT')
assert ali1 == 'ACCGT'
assert ali2 == 'A--GT'
