def check_F2(refseq, spec, VERBOSE=0):
'''Check fragment F2: gag, pol'''
check = check_length_fragment(refseq,
'F2' + spec,
VERBOSE=VERBOSE,
tolerance=80)
if not check:
return False
# Check gag (there should be end)
genename = 'gag'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of ' + genename + ' not found in F2!'
return False
elif VERBOSE >= 3:
print 'OK: end of ' + genename + ' found'
geneseq = refseq[:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, 'gag', VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, 'gag', VERBOSE=VERBOSE)
if not check:
return False
# Check pol (there should be the start)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of ' + genename + ' not found in F2!'
return False
elif VERBOSE >= 3:
print 'OK: start of ' + genename + ' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F2(refseq, spec, VERBOSE=0):
'''Check fragment F2: gag, pol'''
check = check_length_fragment(refseq, 'F2'+spec, VERBOSE=VERBOSE, tolerance=80)
if not check:
return False
# Check gag (there should be end)
genename = 'gag'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of '+genename+' not found in F2!'
return False
elif VERBOSE >= 3:
print 'OK: end of '+genename+' found'
geneseq = refseq[:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, 'gag', VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, 'gag', VERBOSE=VERBOSE)
if not check:
return False
# Check pol (there should be the start)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of '+genename+' not found in F2!'
return False
elif VERBOSE >= 3:
print 'OK: start of '+genename+' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F3(refseq, spec, VERBOSE=0):
'''Check fragment F3: end of pol'''
check = check_length_fragment(refseq,
'F3' + spec,
VERBOSE=VERBOSE,
tolerance=50)
if not check:
return False
# Check pol: this depends on the spec: for F3bo there should be the end,
# anything else has only the middle (it's all pol!)
genename = 'pol'
if spec == 'bo':
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of ' + genename + ' not found in F3!'
return False
elif VERBOSE >= 3:
print 'OK: end of ' + genename + ' found'
geneseq = refseq[:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
else:
# Try all 3 reading frames
for offset in xrange(3):
geneseq = refseq[offset:]
geneseq = geneseq[:len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_premature_stops_noend(prot, genename, VERBOSE=0)
if check:
if VERBOSE >= 3:
print 'OK: ' + genename + ' has no premature stop codons'
break
else:
if VERBOSE >= 1:
print 'ERROR: ' + genename + ' has premature stop codons in all reading frames!'
return False
return True
def check_F3(refseq, spec, VERBOSE=0):
'''Check fragment F3: end of pol'''
check = check_length_fragment(refseq, 'F3'+spec, VERBOSE=VERBOSE, tolerance=50)
if not check:
return False
# Check pol: this depends on the spec: for F3bo there should be the end,
# anything else has only the middle (it's all pol!)
genename = 'pol'
if spec == 'bo':
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of '+genename+' not found in F3!'
return False
elif VERBOSE >= 3:
print 'OK: end of '+genename+' found'
geneseq = refseq[:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
else:
# Try all 3 reading frames
for offset in xrange(3):
geneseq = refseq[offset:]
geneseq = geneseq[: len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_premature_stops_noend(prot, genename, VERBOSE=0)
if check:
if VERBOSE >= 3:
print 'OK: '+genename+' has no premature stop codons'
break
else:
if VERBOSE >= 1:
print 'ERROR: '+genename+' has premature stop codons in all reading frames!'
return False
return True
def check_genomewide(refseq, VERBOSE=0):
'''Check the integrity of all genes in the genomewide consensus'''
# Check single-exon genes
length_tolerance = {'gag': 30, 'pol': 30, 'env': 70, 'vpr': 15, 'vpu': 15}
for genename, tol in length_tolerance.iteritems():
(start, end,
start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=tol)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
# sometimes the gene ends a few nucleotides upstream, and there is a
# frameshift mutation that screws up
gene_new = refseq.seq[start:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = start + (3 * end_new + 3) - end
if -90 < end_diff < 0:
print genename.upper()+' ENDS '+str((end - start) // 3 - end_new - 1)+' AMINO ACIDS UPSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
else:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if (not check):
if genename != 'vpu':
return False
else:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
# sometimes a gene is a bit longer
gene_new = refseq.seq[start:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = start + (3 * end_new + 3) - end
if -90 < end_diff < 0:
print genename.upper()+' ENDS '+str((end - start) // 3 - end_new - 1)+' AMINO ACIDS UPSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
prot = gene.translate()
elif 0 < end_diff < 90:
print genename.upper()+' ENDS '+str(end_new + 1 - (end - start) // 3)+' AMINO ACIDS DOWNSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
prot = gene.translate()
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Vif is special because it can be longer than in HXB2
genename = 'vif'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename,
VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=0)
if not check:
# Vif tends to be a bit longer than in HXB2
for nc in xrange(1, 4):
gene_ext = refseq[start: end + 3 * nc].seq
prot_ext = gene_ext.translate()
check = check_has_end(prot_ext, genename, VERBOSE=0)
if check:
gene = gene_ext
prot = prot_ext
if VERBOSE:
print 'WARNING: '+genename+' actually ends '+str(nc)+' codons downstream'
break
else:
print 'ERROR: '+genename+' does not end, not even slightly downstream'
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check 2-exon genes
for genename_whole in ('tat', 'rev'):
genename = genename_whole+'1'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
start_exon1 = start
end_exon1 = end
genename = genename_whole+'2'
(start, end, start_found, end_found) = locate_gene(refseq[end_exon1 + 2000:], genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
start += end_exon1 + 2000
end += end_exon1 + 2000
# NOTE: rev2 overlaps with env gp41 and can have insertions or deletions
if genename == 'rev2':
tol = 45
else:
tol = 15
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=tol)
if not check:
return False
geneseq = refseq[start: end]
frame = get_frame(geneseq, gene_HXB2, genename, VERBOSE=VERBOSE)
geneseq = geneseq[frame:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
if genename != 'rev2':
return False
else:
# rev2 can end a bit early
end_new = prot.rfind('*')
if end_new != -1:
if len(prot) - 1 - end_new < 20:
print 'REV2 ENDS '+str(len(prot) - end_new - 1)+' AMINO ACIDS UPSTREAM!'
prot = prot[:end_new + 1]
end = start + frame + 3 * (end_new + 1)
else:
return False
else:
# rev2 can also end quite a bit late
gene_new = refseq.seq[start:]
gene_new = gene_new[(end - start) % 3:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
if (start + 3 * end_new) - end < 200:
print 'REV2 ENDS '+str(end_new - len(prot) + 1)+' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
end = start + ((end - start) % 3) + 3 * (end_new + 1)
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
start_exon2 = start
end_exon2 = end
genename = genename_whole
gene_HXB2 = get_gene_HXB2(genename)
from Bio.SeqFeature import FeatureLocation
gene_loc = FeatureLocation(start_exon1, end_exon1, strand=+1) + \
FeatureLocation(start_exon2, end_exon2, strand=+1)
geneseq = gene_loc.extract(refseq)
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F6(refseq, spec, VERBOSE=0):
'''Check fragment F6: end of env, tat2, rev2'''
check = check_length_fragment(refseq, 'F6'+spec, VERBOSE=VERBOSE, tolerance=50)
if not check:
return False
# Check env (there should be end)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of '+genename+' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: end of '+genename+' found'
geneseq = refseq[:end]
gene_HXB2 = get_gene_HXB2(genename)
frame = get_frame(geneseq, gene_HXB2, genename)
geneseq = geneseq[frame:]
geneseq = geneseq[:len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
# env can end a bit early or late
if not check:
gene_new = refseq.seq[frame:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = (frame + 3 * end_new) - end
if 0 < end_diff < 200:
print 'ENV ENDS '+str(end_new - len(prot) + 1)+' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
elif -200 < end_diff < 0:
print 'ENV ENDS '+str(len(prot) - 1 - end_new)+' AMINO ACIDS UPSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print prot
return False
# Check tat2 (second exon of tat, should be complete)
genename = 'tat2'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN TAT2 PREMATURE STOPS, CONTINUING!'
# Check rev2 (second exon of rev, should be complete)
genename = 'rev2'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
# NOTE: rev2 overlaps with env gp41 and can have insertions or deletions
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename,
VERBOSE=VERBOSE, maxdiff=45)
if not check:
return False
geneseq = refseq[start: end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
# rev2 can end a bit early
end_new = prot.rfind('*')
if end_new != -1:
if len(prot) - 1 - end_new < 20:
print 'REV2 ENDS '+str(len(prot) - end_new - 1)+' AMINO ACIDS UPSTREAM!'
prot = prot[:end_new + 1]
else:
return False
else:
# rev2 can also end quite a bit late
gene_new = refseq.seq[start:]
gene_new = gene_new[(end - start) % 3:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
if (start + 3 * end_new) - end < 200:
print 'REV2 ENDS '+str(end_new - len(prot) + 1)+' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F5(refseq, spec, VERBOSE=0):
'''Check fragment F5: env'''
if spec == 'a+bo':
spec_inner = 'bo'
else:
spec_inner = spec
check = check_length_fragment(refseq, 'F5'+spec_inner, VERBOSE=VERBOSE, tolerance=70)
if not check:
return False
# Check env (there should be the start)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of '+genename+' not found in F5!'
return False
elif VERBOSE >= 3:
print 'OK: start of '+genename+' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpu (should be complete in F5ao)
if spec_inner == 'ao':
genename = 'vpu'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
#return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F4(refseq, spec, VERBOSE=0):
'''Check fragment F4: pol, vif, vpr, vpu, tat1, rev1, env'''
check = check_length_fragment(refseq, 'F4'+spec, VERBOSE=VERBOSE, tolerance=50)
if not check:
return False
# Check pol (there should be end)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: end of '+genename+' found'
geneseq = refseq[:end]
gene_HXB2 = get_gene_HXB2(genename)
frame = get_frame(geneseq, gene_HXB2, genename)
geneseq = geneseq[frame:]
geneseq = geneseq[:len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
# it can end a bit early or late
if not check:
gene_new = refseq.seq[frame:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = (frame + 3 * end_new) - end
if 0 < end_diff < 200:
print genename.upper()+' ENDS '+str(end_new - len(prot) + 1)+' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
elif -200 < end_diff < 0:
print genename.upper()+' ENDS '+str(len(prot) - 1 - end_new)+' AMINO ACIDS UPSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print prot
return False
# Check env (there should be the start)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start of '+genename+' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vif (should be complete)
genename = 'vif'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=0)
if check:
if VERBOSE >= 3:
print 'OK: '+genename+' ends with a *'
else:
# Vif tends to be a bit longer than in HXB2
for nc in xrange(1, 4):
gene_ext = refseq[start: end + 3 * nc].seq
prot_ext = gene_ext.translate()
check = check_has_end(prot_ext, genename, VERBOSE=0)
if check:
gene = gene_ext
prot = prot_ext
if VERBOSE:
print 'WARNING: '+genename+' actually ends '+str(nc)+' codons downstream'
break
else:
print 'ERROR: '+genename+' does not end, not even slightly downstream'
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpu (should be complete)
genename = 'vpu'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
#return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpr (should be complete)
genename = 'vpr'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check tat1 (first exon of tat, should be complete)
genename = 'tat1'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=35)
if not check:
return False
geneseq = refseq[start: end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check rev1 (first exon of rev, should be complete)
genename = 'rev1'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=15)
if not check:
return False
geneseq = refseq[start: end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F1(refseq, spec, VERBOSE=0):
'''Check fragment F1: gag, pol'''
check = check_length_fragment(refseq, 'F1'+spec, VERBOSE=VERBOSE, tolerance=50)
if not check:
return False
# Check gag (should be complete)
genename = 'gag'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: '+genename+' not found in F1!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of '+genename+' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start, len(gene_HXB2), genename, VERBOSE=VERBOSE, maxdiff=30)
if not check:
return False
geneseq = refseq[start: end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check pol (there should be the start)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq, genename, VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of '+genename+' not found in F1!'
return False
elif VERBOSE >= 3:
print 'OK: start of '+genename+' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def annotate_sequence(seqrecord, additional_edges={}, additional_features=['chunk'], VERBOSE=0):
'''Annotate a consensus with the genes and stuff (in place)'''
# TODO: what do we do with genes that do not start/end where they are
# supposed to? Do we follow biology and track their new locations?
from Bio.SeqFeature import SeqFeature, FeatureLocation, CompoundLocation
from hivwholeseq.utils.genome_info import gene_edges, RNA_structure_edges, \
other_edges, find_region_edges, find_region_edges_multiple, \
locate_gene
edge_dict = {'gene': gene_edges,
'RNA structure': RNA_structure_edges,
'other': other_edges}
edge_dict.update(additional_edges)
additional_features = ['protein'] + additional_features
features = edge_dict.keys() + additional_features
if VERBOSE:
print 'Features:', ', '.join(features)
smat = np.array(seqrecord)
for feature_type in edge_dict:
edges_all = edge_dict[feature_type]
print feature_type, edge_dict[feature_type].keys()
for name, edges in edges_all.iteritems():
if VERBOSE >= 2:
print name,
# Skip a feature if it's present already
if name in map(lambda x: x.id, seqrecord.features):
if VERBOSE >= 2:
print 'already present.'
continue
# Behave differently for unsplit regions and split ones
if len(edges) == 2:
# LTR problems with F6
if 'F6' in name:
pos_edge = find_region_edges(smat[6000::], [edges[0], None])
pos_edge[0] += 6000
elif feature_type == 'genes':
pos_edge = locate_gene(smat, name, output_compact=True)
else:
pos_edge = find_region_edges(smat, edges)
# Cut the primers for some features
if (None not in pos_edge) and name in ['V1', 'V3', 'V4', 'V5']:
pos_edge[0] += len(edges[0])
pos_edge[1] -= len(edges[1])
# Cut only the right primer for V2
if (None not in pos_edge) and name in ['V2']:
pos_edge[1] -= len(edges[1])
if pos_edge[0] is None:
if name not in ['F1', "LTR5'"]:
print 'WARNING: start not found'
pos_edge[0] = 0
if pos_edge[1] is None:
if name not in ['F6', "LTR3'"]:
print 'WARNING: end not found'
pos_edge[1] = len(smat)
location = FeatureLocation(*pos_edge)
else:
if feature_type == 'genes':
pos_edges = [locate_gene(smat, name+suff, output_compact=True)
for suff in ('1', '2')]
else:
pos_edges = find_region_edges_multiple(smat, edges, min_distance=1)
locations = [FeatureLocation(*pos_edge) for pos_edge in pos_edges]
location = CompoundLocation(locations)
if VERBOSE >= 2:
print 'found:', location
feature = SeqFeature(location, type=feature_type, id=name, strand=1)
seqrecord.features.append(feature)
# Add proteins and other features from HXB2
from operator import attrgetter
from seqanpy import align_overlap
from hivwholeseq.utils.genome_info import proteins, chunks
from hivwholeseq.reference import load_custom_reference
additional_features_dict = {}
if 'protein' in additional_features:
additional_features_dict['protein'] = proteins
if 'chunk' in additional_features:
additional_features_dict['chunk'] = chunks
ref_ann = load_custom_reference('HXB2', 'gb')
for feagroup, additional_features_grp in additional_features_dict.iteritems():
for feaname in additional_features_grp:
if VERBOSE >= 2:
print feaname,
fea = ref_ann.features[map(attrgetter('id'), ref_ann.features).index(feaname)]
seq = fea.extract(ref_ann)
(score, ali1, ali2) = align_overlap(seqrecord, seq, score_gapopen=-20)
start = len(ali2) - len(ali2.lstrip('-'))
end = len(ali2.rstrip('-'))
end -= ali1[start: end].count('-')
location = FeatureLocation(start, end)
if VERBOSE >= 2:
print 'found:', location
feature = SeqFeature(location, type=feagroup, id=feaname, strand=1)
seqrecord.features.append(feature)
def check_genomewide(refseq, VERBOSE=0):
'''Check the integrity of all genes in the genomewide consensus'''
# Check single-exon genes
length_tolerance = {'gag': 30, 'pol': 30, 'env': 70, 'vpr': 15, 'vpu': 15}
for genename, tol in length_tolerance.iteritems():
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=tol)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
# sometimes the gene ends a few nucleotides upstream, and there is a
# frameshift mutation that screws up
gene_new = refseq.seq[start:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = start + (3 * end_new + 3) - end
if -90 < end_diff < 0:
print genename.upper() + ' ENDS ' + str(
(end - start) // 3 - end_new -
1) + ' AMINO ACIDS UPSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
else:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if (not check):
if genename != 'vpu':
return False
else:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
# sometimes a gene is a bit longer
gene_new = refseq.seq[start:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = start + (3 * end_new + 3) - end
if -90 < end_diff < 0:
print genename.upper() + ' ENDS ' + str(
(end - start) // 3 - end_new -
1) + ' AMINO ACIDS UPSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
prot = gene.translate()
elif 0 < end_diff < 90:
print genename.upper() + ' ENDS ' + str(
end_new + 1 -
(end - start) // 3) + ' AMINO ACIDS DOWNSTREAM!'
gene = gene_new[:3 * (end_new + 1)]
prot = gene.translate()
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Vif is special because it can be longer than in HXB2
genename = 'vif'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=0)
if not check:
# Vif tends to be a bit longer than in HXB2
for nc in xrange(1, 4):
gene_ext = refseq[start:end + 3 * nc].seq
prot_ext = gene_ext.translate()
check = check_has_end(prot_ext, genename, VERBOSE=0)
if check:
gene = gene_ext
prot = prot_ext
if VERBOSE:
print 'WARNING: ' + genename + ' actually ends ' + str(
nc) + ' codons downstream'
break
else:
print 'ERROR: ' + genename + ' does not end, not even slightly downstream'
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check 2-exon genes
for genename_whole in ('tat', 'rev'):
genename = genename_whole + '1'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
start_exon1 = start
end_exon1 = end
genename = genename_whole + '2'
(start, end, start_found,
end_found) = locate_gene(refseq[end_exon1 + 2000:],
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in genomewide!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
start += end_exon1 + 2000
end += end_exon1 + 2000
# NOTE: rev2 overlaps with env gp41 and can have insertions or deletions
if genename == 'rev2':
tol = 45
else:
tol = 15
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=tol)
if not check:
return False
geneseq = refseq[start:end]
frame = get_frame(geneseq, gene_HXB2, genename, VERBOSE=VERBOSE)
geneseq = geneseq[frame:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
if genename != 'rev2':
return False
else:
# rev2 can end a bit early
end_new = prot.rfind('*')
if end_new != -1:
if len(prot) - 1 - end_new < 20:
print 'REV2 ENDS ' + str(len(prot) - end_new -
1) + ' AMINO ACIDS UPSTREAM!'
prot = prot[:end_new + 1]
end = start + frame + 3 * (end_new + 1)
else:
return False
else:
# rev2 can also end quite a bit late
gene_new = refseq.seq[start:]
gene_new = gene_new[(end - start) % 3:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
if (start + 3 * end_new) - end < 200:
print 'REV2 ENDS ' + str(end_new - len(prot) + 1
) + ' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
end = start + ((end - start) % 3) + 3 * (end_new + 1)
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
start_exon2 = start
end_exon2 = end
genename = genename_whole
gene_HXB2 = get_gene_HXB2(genename)
from Bio.SeqFeature import FeatureLocation
gene_loc = FeatureLocation(start_exon1, end_exon1, strand=+1) + \
FeatureLocation(start_exon2, end_exon2, strand=+1)
geneseq = gene_loc.extract(refseq)
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F6(refseq, spec, VERBOSE=0):
'''Check fragment F6: end of env, tat2, rev2'''
check = check_length_fragment(refseq,
'F6' + spec,
VERBOSE=VERBOSE,
tolerance=50)
if not check:
return False
# Check env (there should be end)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of ' + genename + ' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: end of ' + genename + ' found'
geneseq = refseq[:end]
gene_HXB2 = get_gene_HXB2(genename)
frame = get_frame(geneseq, gene_HXB2, genename)
geneseq = geneseq[frame:]
geneseq = geneseq[:len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
# env can end a bit early or late
if not check:
gene_new = refseq.seq[frame:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = (frame + 3 * end_new) - end
if 0 < end_diff < 200:
print 'ENV ENDS ' + str(end_new - len(prot) +
1) + ' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
elif -200 < end_diff < 0:
print 'ENV ENDS ' + str(len(prot) - 1 -
end_new) + ' AMINO ACIDS UPSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print prot
return False
# Check tat2 (second exon of tat, should be complete)
genename = 'tat2'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN TAT2 PREMATURE STOPS, CONTINUING!'
# Check rev2 (second exon of rev, should be complete)
genename = 'rev2'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F6!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
# NOTE: rev2 overlaps with env gp41 and can have insertions or deletions
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=45)
if not check:
return False
geneseq = refseq[start:end]
geneseq = geneseq[len(geneseq) % 3:]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
# rev2 can end a bit early
end_new = prot.rfind('*')
if end_new != -1:
if len(prot) - 1 - end_new < 20:
print 'REV2 ENDS ' + str(len(prot) - end_new -
1) + ' AMINO ACIDS UPSTREAM!'
prot = prot[:end_new + 1]
else:
return False
else:
# rev2 can also end quite a bit late
gene_new = refseq.seq[start:]
gene_new = gene_new[(end - start) % 3:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
if (start + 3 * end_new) - end < 200:
print 'REV2 ENDS ' + str(end_new - len(prot) +
1) + ' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F5(refseq, spec, VERBOSE=0):
'''Check fragment F5: env'''
if spec == 'a+bo':
spec_inner = 'bo'
else:
spec_inner = spec
check = check_length_fragment(refseq,
'F5' + spec_inner,
VERBOSE=VERBOSE,
tolerance=70)
if not check:
return False
# Check env (there should be the start)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of ' + genename + ' not found in F5!'
return False
elif VERBOSE >= 3:
print 'OK: start of ' + genename + ' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpu (should be complete in F5ao)
if spec_inner == 'ao':
genename = 'vpu'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
#return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F4(refseq, spec, VERBOSE=0):
'''Check fragment F4: pol, vif, vpr, vpu, tat1, rev1, env'''
check = check_length_fragment(refseq,
'F4' + spec,
VERBOSE=VERBOSE,
tolerance=50)
if not check:
return False
# Check pol (there should be end)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not end_found):
print 'ERROR: end of ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: end of ' + genename + ' found'
geneseq = refseq[:end]
gene_HXB2 = get_gene_HXB2(genename)
frame = get_frame(geneseq, gene_HXB2, genename)
geneseq = geneseq[frame:]
geneseq = geneseq[:len(geneseq) - (len(geneseq) % 3)]
gene = geneseq.seq
prot = gene.translate()
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
# it can end a bit early or late
if not check:
gene_new = refseq.seq[frame:]
gene_new = gene_new[:len(gene_new) - (len(gene_new) % 3)]
prot_new = gene_new.translate()
end_new = prot_new.find('*')
end_diff = (frame + 3 * end_new) - end
if 0 < end_diff < 200:
print genename.upper() + ' ENDS ' + str(
end_new - len(prot) + 1) + ' AMINO ACIDS DOWNSTREAM!'
prot = prot_new[:end_new + 1]
elif -200 < end_diff < 0:
print genename.upper() + ' ENDS ' + str(
len(prot) - 1 - end_new) + ' AMINO ACIDS UPSTREAM!'
prot = prot_new[:end_new + 1]
else:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
print prot
return False
# Check env (there should be the start)
genename = 'env'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start of ' + genename + ' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vif (should be complete)
genename = 'vif'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=0)
if check:
if VERBOSE >= 3:
print 'OK: ' + genename + ' ends with a *'
else:
# Vif tends to be a bit longer than in HXB2
for nc in xrange(1, 4):
gene_ext = refseq[start:end + 3 * nc].seq
prot_ext = gene_ext.translate()
check = check_has_end(prot_ext, genename, VERBOSE=0)
if check:
gene = gene_ext
prot = prot_ext
if VERBOSE:
print 'WARNING: ' + genename + ' actually ends ' + str(
nc) + ' codons downstream'
break
else:
print 'ERROR: ' + genename + ' does not end, not even slightly downstream'
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpu (should be complete)
genename = 'vpu'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
print 'ERROR IN VPU STARTING CODON, CONTINUING!'
#return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check vpr (should be complete)
genename = 'vpr'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check tat1 (first exon of tat, should be complete)
genename = 'tat1'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=35)
if not check:
return False
geneseq = refseq[start:end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check rev1 (first exon of rev, should be complete)
genename = 'rev1'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F4!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=15)
if not check:
return False
geneseq = refseq[start:end]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def check_F1(refseq, spec, VERBOSE=0):
'''Check fragment F1: gag, pol'''
check = check_length_fragment(refseq,
'F1' + spec,
VERBOSE=VERBOSE,
tolerance=50)
if not check:
return False
# Check gag (should be complete)
genename = 'gag'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found) or (not end_found):
print 'ERROR: ' + genename + ' not found in F1!'
return False
elif VERBOSE >= 3:
print 'OK: start and end of ' + genename + ' found'
gene_HXB2 = get_gene_HXB2(genename)
check = check_has_similar_length(end - start,
len(gene_HXB2),
genename,
VERBOSE=VERBOSE,
maxdiff=30)
if not check:
return False
geneseq = refseq[start:end]
gene = geneseq.seq
check = check_has_complete_codons(gene, genename, VERBOSE=VERBOSE)
if not check:
return False
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_end(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
# Check pol (there should be the start)
genename = 'pol'
(start, end, start_found, end_found) = locate_gene(refseq,
genename,
VERBOSE=VERBOSE)
if (not start_found):
print 'ERROR: start of ' + genename + ' not found in F1!'
return False
elif VERBOSE >= 3:
print 'OK: start of ' + genename + ' found'
geneseq = refseq[start:]
geneseq = geneseq[:len(geneseq) - len(geneseq) % 3]
gene = geneseq.seq
prot = gene.translate()
check = check_start_aminoacid(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
check = check_has_premature_stops_noend(prot, genename, VERBOSE=VERBOSE)
if not check:
return False
return True
def annotate_sequence(seqrecord,
additional_edges={},
additional_features=['chunk'],
VERBOSE=0):
'''Annotate a consensus with the genes and stuff (in place)'''
# TODO: what do we do with genes that do not start/end where they are
# supposed to? Do we follow biology and track their new locations?
from Bio.SeqFeature import SeqFeature, FeatureLocation, CompoundLocation
from hivwholeseq.utils.genome_info import gene_edges, RNA_structure_edges, \
other_edges, find_region_edges, find_region_edges_multiple, \
locate_gene
edge_dict = {
'gene': gene_edges,
'RNA structure': RNA_structure_edges,
'other': other_edges
}
edge_dict.update(additional_edges)
additional_features = ['protein'] + additional_features
features = edge_dict.keys() + additional_features
if VERBOSE:
print 'Features:', ', '.join(features)
smat = np.array(seqrecord)
for feature_type in edge_dict:
edges_all = edge_dict[feature_type]
print feature_type, edge_dict[feature_type].keys()
for name, edges in edges_all.iteritems():
if VERBOSE >= 2:
print name,
# Skip a feature if it's present already
if name in map(lambda x: x.id, seqrecord.features):
if VERBOSE >= 2:
print 'already present.'
continue
# Behave differently for unsplit regions and split ones
if len(edges) == 2:
# LTR problems with F6
if 'F6' in name:
pos_edge = find_region_edges(smat[6000::],
[edges[0], None])
pos_edge[0] += 6000
elif feature_type == 'genes':
pos_edge = locate_gene(smat, name, output_compact=True)
else:
pos_edge = find_region_edges(smat, edges)
# Cut the primers for some features
if (None not in pos_edge) and name in ['V1', 'V3', 'V4', 'V5']:
pos_edge[0] += len(edges[0])
pos_edge[1] -= len(edges[1])
# Cut only the right primer for V2
if (None not in pos_edge) and name in ['V2']:
pos_edge[1] -= len(edges[1])
if pos_edge[0] is None:
if name not in ['F1', "LTR5'"]:
print 'WARNING: start not found'
pos_edge[0] = 0
if pos_edge[1] is None:
if name not in ['F6', "LTR3'"]:
print 'WARNING: end not found'
pos_edge[1] = len(smat)
location = FeatureLocation(*pos_edge)
else:
if feature_type == 'genes':
pos_edges = [
locate_gene(smat, name + suff, output_compact=True)
for suff in ('1', '2')
]
else:
pos_edges = find_region_edges_multiple(smat,
edges,
min_distance=1)
locations = [
FeatureLocation(*pos_edge) for pos_edge in pos_edges
]
location = CompoundLocation(locations)
if VERBOSE >= 2:
print 'found:', location
feature = SeqFeature(location,
type=feature_type,
id=name,
strand=1)
seqrecord.features.append(feature)
# Add proteins and other features from HXB2
from operator import attrgetter
from seqanpy import align_overlap
from hivwholeseq.utils.genome_info import proteins, chunks
from hivwholeseq.reference import load_custom_reference
additional_features_dict = {}
if 'protein' in additional_features:
additional_features_dict['protein'] = proteins
if 'chunk' in additional_features:
additional_features_dict['chunk'] = chunks
ref_ann = load_custom_reference('HXB2', 'gb')
for feagroup, additional_features_grp in additional_features_dict.iteritems(
):
for feaname in additional_features_grp:
if VERBOSE >= 2:
print feaname,
fea = ref_ann.features[map(attrgetter('id'),
ref_ann.features).index(feaname)]
seq = fea.extract(ref_ann)
(score, ali1, ali2) = align_overlap(seqrecord,
seq,
score_gapopen=-20)
start = len(ali2) - len(ali2.lstrip('-'))
end = len(ali2.rstrip('-'))
end -= ali1[start:end].count('-')
location = FeatureLocation(start, end)
if VERBOSE >= 2:
print 'found:', location
feature = SeqFeature(location, type=feagroup, id=feaname, strand=1)
seqrecord.features.append(feature)
