def get_align_seq(seq_list, options, product):
'''Alignment seq'''
filter_product = []
for i in xrange(len(product)):
amp = product[i]
pseq = amp['pseq']
mseq = amp['mseq']
pts = seq_list[2*i] # Forward primer target sequence
mts = seq_list[2*i+1] # Reverse primer target sequence
# ts for target sequence
#p_aseq = Watson_Click_alignment(pseq, pts, 'forward')
p_aseq = Thermodynamics_alignment(pseq, pts, 'forward')
p_aseq_len = len(p_aseq)
p_qseq = pseq[-p_aseq_len:].upper()
p_sseq = pts[-p_aseq_len:].upper()
p_tail = pseq[:-p_aseq_len]
p_thermo = TmDeltaG.Cal(p_qseq, Seq.complement(p_sseq), mono_conc=options.mono_conc, diva_conc=options.diva_conc, dntp_conc=options.dntp_conc)
p_DeltaG = p_thermo.DeltaG
p_Tm = p_thermo.Tm
if p_Tm < float(options.tm_start) or p_Tm > float(options.tm_stop):
continue
#m_aseq = Watson_Click_alignment(mseq, mts, 'reverse')
m_aseq = Thermodynamics_alignment(mseq, mts, 'reverse')
m_aseq_len = len(m_aseq)
m_qseq = mseq[:m_aseq_len].upper()
m_sseq = mts[:m_aseq_len].upper()
r_len = amp['mlen']
if m_aseq_len == r_len:
m_tail = ''
else:
m_tail = mseq[m_aseq_len:]
m_thermo = TmDeltaG.Cal(m_qseq, Seq.complement(m_sseq), mono_conc=options.mono_conc, diva_conc=options.diva_conc, dntp_conc=options.dntp_conc)
m_DeltaG = m_thermo.DeltaG
m_Tm = m_thermo.Tm
if m_Tm < float(options.tm_start) or m_Tm > float(options.tm_stop):
continue
amp['p_qseq'] = p_qseq
amp['p_aseq'] = p_aseq
amp['p_sseq'] = p_sseq
amp['p_tail'] = p_tail
amp['m_qseq'] = m_qseq
amp['m_aseq'] = m_aseq
amp['m_sseq'] = m_sseq
amp['m_tail'] = m_tail
amp['p_Tm'] = p_Tm
amp['p_DeltaG'] = p_DeltaG
amp['m_Tm'] = m_Tm
amp['m_DeltaG'] = m_DeltaG
filter_product.append(amp)
return filter_product
def format_oligos(oligos, options):
'''for output'''
oligo_list = []
for oligo in oligos:
id = oligo['id']
seq = oligo['seq'].upper()
size = oligo['size']
GC = chilli.cal_GC_content(seq, size)
Tm = TmDeltaG.calTm(seq, Seq.complement(seq), mono_conc=options.mono_conc, diva_conc=options.diva_conc, dntp_conc=options.dntp_conc, oligo_conc=options.oligo_conc)
GC = '%.1f' % GC
Tm = '%.1f' % Tm
oligo_list.append((id, seq, size, GC, Tm))
return oligo_list
def main():
qseq = 'TATACTTT'
sseq = Seq.complement(qseq)
qseq = 'GGACTGACG'
sseq = 'CCTGGCTGC'
mono = 50
diva = 1.5
oligo = 50
dntp = 0.25
seq = Cal(qseq,
sseq,
mono_conc=50,
diva_conc=1.5,
oligo_conc=50,
dntp_conc=0.25)
print('Tm: ', seq.Tm)
print('DeltaG: ', seq.DeltaG)
def primer_process(options, session_dir, fcdict, db, oligos):
'''Primer Process'''
#options.processor = int(options.processor)
oligo_pos = []
oligo_id_list = []
#t1 = time.time()
for oligo in oligos:
primer_seq = oligo['seq']
oligo_id_list.append(oligo['id'])
#mer = primer_seq[-options.k:]
mer = primer_seq[-options.k_value:]
mer_id = chilli.DNA2int(mer)
# p for plus strand, m for minus strand
p_pos_list, m_pos_list = get_position(options, mer_id, db)
oligo_pos.append({
'p_list' : p_pos_list,
'm_list' : m_pos_list,
})
#t2 = time.time()
#cost = t2 - t1
#print cost
product = []
binding_range = []
binding_primer = []
for i in xrange(len(oligos)):
p_list = oligo_pos[i]['p_list']
p_oligo_length = oligos[i]['size']
for k in xrange(len(oligos)):
m_list = oligo_pos[k]['m_list']
m_oligo_length = oligos[k]['size']
for j in p_list.iterkeys():
hid = str(j) # Because the database has been re-formated
try:
p_pos = p_list[j]
m_pos = m_list[j]
except:
continue
for p in p_pos:
left = get_pos_range(p, m_pos)
for pos_index in xrange(left, len(m_pos)):
f3_pos = p+1
r3_pos = m_pos[pos_index]
# The amplicon size <= p.len + m.len
if f3_pos >= r3_pos:
continue
product_size = p_oligo_length + m_pos[pos_index] - p + m_oligo_length - 1
if product_size < options.size_start:
continue
if product_size > options.size_stop:
break
p_start = p - p_oligo_length + 1
if p_start < 0:
p_start = 0
m_stop = r3_pos + m_oligo_length
if m_stop > fcdict[hid]['size']:
m_stop = fcdict[hid]['size']
binding_range.append('%s:%s-%s' % (hid, p_start, p + 1))
# Reverse: Correction for reverse
binding_range.append('%s:%s-%s' % (hid, r3_pos, m_stop))
amp = {
'hid' : hid,
'pid' : oligos[i]['id'],
'mid' : oligos[k]['id'],
'plen' : p_oligo_length,
'mlen' : m_oligo_length,
'pseq' : oligos[i]['seq'],
'mseq' : Seq.rev_com(oligos[k]['seq']),
'size' : product_size,
'f3_pos' : f3_pos,
'r3_pos' : r3_pos,
}
product.append(amp)
return product, binding_range
def primer_analysis(product, options, oligos, session_dir, fcdict, db):
'''Analysis the candidate forward and reverse primer and check whether they can amplify an amplicon'''
mid_seq_id_list = []
tmp_list = []
amp_list = []
filter_product = []
# Forward primer
for i in xrange(len(product)):
# Reverse primer
#print i
amp = product[i]
hid = amp['hid']
pid = amp['pid']
mid = amp['mid']
f_len = amp['plen']
r_len = amp['mlen']
pseq = amp['pseq']
mseq = amp['mseq']
size = amp['size']
f_3_pos = amp['f3_pos']
r_3_pos = amp['r3_pos']
p_qseq = amp['p_qseq']
p_aseq = amp['p_aseq']
p_sseq = amp['p_sseq']
p_tail = amp['p_tail']
m_qseq = amp['m_qseq']
m_aseq = amp['m_aseq']
m_sseq = amp['m_sseq']
m_tail = amp['m_tail']
p_Tm = amp['p_Tm']
p_DeltaG = amp['p_DeltaG']
m_Tm = amp['m_Tm']
m_DeltaG = amp['m_DeltaG']
#print 2*i, 2*i + 1
p_3_DeltaG = TmDeltaG.calDeltaG(p_qseq[-5:], Seq.complement(p_sseq[-5:]), mono_conc=options.mono_conc, diva_conc=options.diva_conc, dntp_conc=options.dntp_conc)
m_3_DeltaG = TmDeltaG.calDeltaG(m_qseq[:5], Seq.complement(m_sseq[:5]), mono_conc=options.mono_conc, diva_conc=options.diva_conc, dntp_conc=options.dntp_conc)
# Filter DeltaG
if p_3_DeltaG < float(options.dg_start) or p_3_DeltaG > float(options.dg_stop):
continue
if m_3_DeltaG < float(options.dg_start) or m_3_DeltaG > float(options.dg_stop):
continue
ppc = cal_PPC(len(p_qseq), f_len, len(m_qseq), r_len)
# Filter by PPC
if ppc < options.ppc:
continue
mid_seq_id = '%s:%s-%s' % (hid, f_3_pos, r_3_pos)
mid_seq_id_list.append(mid_seq_id)
ave_Tm = (p_Tm + m_Tm) / 2 # For sort
to_be_added = (ave_Tm, ppc, p_3_DeltaG, m_3_DeltaG)
tmp_list.append(to_be_added)
filter_product.append(amp)
mid_seq_list = get_mid_seq(mid_seq_id_list, options, session_dir, db)
for i in xrange(len(mid_seq_list)):
mid_seq = mid_seq_list[i]
(ave_Tm, ppc, p_3_DeltaG, m_3_DeltaG) = tmp_list[i]
amp = filter_product[i]
pid = amp['pid']
mid = amp['mid']
hid = int(amp['hid'])
real_hid = fcdict[str(hid)]['id']
hdesc = fcdict[str(hid)]['desc']
amp_graphic = draw_graphical_alignment_primer(amp, oligos, options, mid_seq)
size = amp['size']
amp['p_3_DeltaG'] = p_3_DeltaG
amp['m_3_DeltaG'] = m_3_DeltaG
amp['real_hid'] = real_hid
amp['hdesc'] = hdesc
amp['mid_seq'] = mid_seq
amp['amp_graphic'] = amp_graphic
amp_list.append([ave_Tm, ppc, size, amp])
return amp_list
def get_align_seq(seq_list, options, product):
'''Alignment seq'''
filter_product = []
for i in xrange(len(product)):
amp = product[i]
pseq = amp['pseq']
mseq = amp['mseq']
pts = seq_list[2 * i] # Forward primer target sequence
mts = seq_list[2 * i + 1] # Reverse primer target sequence
# ts for target sequence
#p_aseq = Watson_Click_alignment(pseq, pts, 'forward')
p_aseq = Thermodynamics_alignment(pseq, pts, 'forward')
p_aseq_len = len(p_aseq)
p_qseq = pseq[-p_aseq_len:].upper()
p_sseq = pts[-p_aseq_len:].upper()
p_tail = pseq[:-p_aseq_len]
p_thermo = TmDeltaG.Cal(p_qseq,
Seq.complement(p_sseq),
mono_conc=options.mono_conc,
diva_conc=options.diva_conc,
dntp_conc=options.dntp_conc)
p_DeltaG = p_thermo.DeltaG
p_Tm = p_thermo.Tm
if p_Tm < float(options.tm_start) or p_Tm > float(options.tm_stop):
continue
#m_aseq = Watson_Click_alignment(mseq, mts, 'reverse')
m_aseq = Thermodynamics_alignment(mseq, mts, 'reverse')
m_aseq_len = len(m_aseq)
m_qseq = mseq[:m_aseq_len].upper()
m_sseq = mts[:m_aseq_len].upper()
r_len = amp['mlen']
if m_aseq_len == r_len:
m_tail = ''
else:
m_tail = mseq[m_aseq_len:]
m_thermo = TmDeltaG.Cal(m_qseq,
Seq.complement(m_sseq),
mono_conc=options.mono_conc,
diva_conc=options.diva_conc,
dntp_conc=options.dntp_conc)
m_DeltaG = m_thermo.DeltaG
m_Tm = m_thermo.Tm
if m_Tm < float(options.tm_start) or m_Tm > float(options.tm_stop):
continue
amp['p_qseq'] = p_qseq
amp['p_aseq'] = p_aseq
amp['p_sseq'] = p_sseq
amp['p_tail'] = p_tail
amp['m_qseq'] = m_qseq
amp['m_aseq'] = m_aseq
amp['m_sseq'] = m_sseq
amp['m_tail'] = m_tail
amp['p_Tm'] = p_Tm
amp['p_DeltaG'] = p_DeltaG
amp['m_Tm'] = m_Tm
amp['m_DeltaG'] = m_DeltaG
filter_product.append(amp)
return filter_product
def primer_process(options, session_dir, fcdict, db, oligos):
'''Primer Process'''
#options.processor = int(options.processor)
oligo_pos = []
oligo_id_list = []
#t1 = time.time()
for oligo in oligos:
primer_seq = oligo['seq']
oligo_id_list.append(oligo['id'])
#mer = primer_seq[-options.k:]
mer = primer_seq[-options.k_value:]
mer_id = chilli.DNA2int(mer)
# p for plus strand, m for minus strand
p_pos_list, m_pos_list = get_position(options, mer_id, db)
oligo_pos.append({
'p_list': p_pos_list,
'm_list': m_pos_list,
})
#t2 = time.time()
#cost = t2 - t1
#print cost
product = []
binding_range = []
binding_primer = []
for i in xrange(len(oligos)):
p_list = oligo_pos[i]['p_list']
p_oligo_length = oligos[i]['size']
for k in xrange(len(oligos)):
m_list = oligo_pos[k]['m_list']
m_oligo_length = oligos[k]['size']
for j in p_list.iterkeys():
hid = str(j) # Because the database has been re-formated
try:
p_pos = p_list[j]
m_pos = m_list[j]
except:
continue
for p in p_pos:
left = get_pos_range(p, m_pos)
for pos_index in xrange(left, len(m_pos)):
f3_pos = p + 1
r3_pos = m_pos[pos_index]
# The amplicon size <= p.len + m.len
if f3_pos >= r3_pos:
continue
product_size = p_oligo_length + m_pos[
pos_index] - p + m_oligo_length - 1
if product_size < options.size_start:
continue
if product_size > options.size_stop:
break
p_start = p - p_oligo_length + 1
if p_start < 0:
p_start = 0
m_stop = r3_pos + m_oligo_length
if m_stop > fcdict[hid]['size']:
m_stop = fcdict[hid]['size']
binding_range.append('%s:%s-%s' %
(hid, p_start, p + 1))
# Reverse: Correction for reverse
binding_range.append('%s:%s-%s' %
(hid, r3_pos, m_stop))
amp = {
'hid': hid,
'pid': oligos[i]['id'],
'mid': oligos[k]['id'],
'plen': p_oligo_length,
'mlen': m_oligo_length,
'pseq': oligos[i]['seq'],
'mseq': Seq.rev_com(oligos[k]['seq']),
'size': product_size,
'f3_pos': f3_pos,
'r3_pos': r3_pos,
}
product.append(amp)
return product, binding_range
def primer_analysis(product, options, oligos, session_dir, fcdict, db):
'''Analysis the candidate forward and reverse primer and check whether they can amplify an amplicon'''
mid_seq_id_list = []
tmp_list = []
amp_list = []
filter_product = []
# Forward primer
for i in xrange(len(product)):
# Reverse primer
#print i
amp = product[i]
hid = amp['hid']
pid = amp['pid']
mid = amp['mid']
f_len = amp['plen']
r_len = amp['mlen']
pseq = amp['pseq']
mseq = amp['mseq']
size = amp['size']
f_3_pos = amp['f3_pos']
r_3_pos = amp['r3_pos']
p_qseq = amp['p_qseq']
p_aseq = amp['p_aseq']
p_sseq = amp['p_sseq']
p_tail = amp['p_tail']
m_qseq = amp['m_qseq']
m_aseq = amp['m_aseq']
m_sseq = amp['m_sseq']
m_tail = amp['m_tail']
p_Tm = amp['p_Tm']
p_DeltaG = amp['p_DeltaG']
m_Tm = amp['m_Tm']
m_DeltaG = amp['m_DeltaG']
#print 2*i, 2*i + 1
p_3_DeltaG = TmDeltaG.calDeltaG(p_qseq[-5:],
Seq.complement(p_sseq[-5:]),
mono_conc=options.mono_conc,
diva_conc=options.diva_conc,
dntp_conc=options.dntp_conc)
m_3_DeltaG = TmDeltaG.calDeltaG(m_qseq[:5],
Seq.complement(m_sseq[:5]),
mono_conc=options.mono_conc,
diva_conc=options.diva_conc,
dntp_conc=options.dntp_conc)
# Filter DeltaG
if p_3_DeltaG < float(options.dg_start) or p_3_DeltaG > float(
options.dg_stop):
continue
if m_3_DeltaG < float(options.dg_start) or m_3_DeltaG > float(
options.dg_stop):
continue
ppc = cal_PPC(len(p_qseq), f_len, len(m_qseq), r_len)
# Filter by PPC
if ppc < options.ppc:
continue
mid_seq_id = '%s:%s-%s' % (hid, f_3_pos, r_3_pos)
mid_seq_id_list.append(mid_seq_id)
ave_Tm = (p_Tm + m_Tm) / 2 # For sort
to_be_added = (ave_Tm, ppc, p_3_DeltaG, m_3_DeltaG)
tmp_list.append(to_be_added)
filter_product.append(amp)
mid_seq_list = get_mid_seq(mid_seq_id_list, options, session_dir, db)
for i in xrange(len(mid_seq_list)):
mid_seq = mid_seq_list[i]
(ave_Tm, ppc, p_3_DeltaG, m_3_DeltaG) = tmp_list[i]
amp = filter_product[i]
pid = amp['pid']
mid = amp['mid']
hid = int(amp['hid'])
real_hid = fcdict[str(hid)]['id']
hdesc = fcdict[str(hid)]['desc']
amp_graphic = draw_graphical_alignment_primer(amp, oligos, options,
mid_seq)
size = amp['size']
amp['p_3_DeltaG'] = p_3_DeltaG
amp['m_3_DeltaG'] = m_3_DeltaG
amp['real_hid'] = real_hid
amp['hdesc'] = hdesc
amp['mid_seq'] = mid_seq
amp['amp_graphic'] = amp_graphic
amp_list.append([ave_Tm, ppc, size, amp])
return amp_list