def variant_mask(chr_no, start_pos, stop_pos, variant_path, refDB_path,
write_path, time_stamp, variant_mask_condition):
indel_count = 0
snp_count = 0
filename = "chr" + str(chr_no)
output_poly_masked = open(
write_path + str(time_stamp) + "_" + str(chr_no) + "_" +
str(start_pos) + "_" + str((stop_pos - start_pos) + 1) +
"_VariantMasked.fasta", "w")
output_poly_masked.write(
str(">" + "TA_" + str(chr_no) + "_" + str(start_pos) + "_" +
str((stop_pos - start_pos) + 1) + "_" + "VariantMasked" + '\n'))
Locus = get_Locus(start_pos, stop_pos, chr_no, refDB_path)
gap_count = Locus.count('N' * 100)
locus_gc = gc_content(Locus)
if variant_mask_condition == 1:
df = pd.read_csv(variant_path + filename, sep='\t', header=0)
df = df[(df.coordinate >= int(start_pos))
& (df.coordinate <= int(stop_pos))]
for index, row in df.iterrows():
if '<INS>' in row['alternate_allele'] or '<DEL>' in row[
'alternate_allele']:
poly_coord = int(row['coordinate']) - (start_pos - 1)
Locus = Locus[:(poly_coord - 1)] + "n" + Locus[
poly_coord:] # Indels annotated as "n"
indel_count += 1
else:
poly_coord = int(row['coordinate']) - (start_pos - 1)
Locus = Locus[:(poly_coord - 1)] + "N" + Locus[
poly_coord:] # Polymorphisms other than indels annotated as "N"
snp_count += 1
output_poly_masked.write(str(Locus))
output_poly_masked.close()
return [indel_count, snp_count, gap_count, locus_gc]
def primer_filter (primer, minTm, maxTm, GC_range_min,GC_range_max, self_Tmdiff ,filter_AT_3prime, primer_dict, i, strand, filter_di_si_repeats, filter_GC_clamp):
if check_compostion(primer):
primer_GC = gc_content(primer)
if primer_GC >= GC_range_min and primer_GC <= GC_range_max:
primer_end_filter = check_ATends(primer, filter_AT_3prime)
if primer_end_filter =="noATend_filter":
primer_GC_clamp_filter = check_GC_clamp(primer, filter_GC_clamp )
if primer_GC_clamp_filter =="noGC_clamp_filter":
primer_di_single_repeat_filter = di_single_nucleo_repeat_filter(primer, filter_di_si_repeats = filter_di_si_repeats, di_si_repeats_threshold = di_si_repeats_threshold)
if primer_di_single_repeat_filter ==0:
primer_Tm = float(NN_Tm(seq=primer, compl_seq=complement(primer), primer_conc=primer_conc, Na=Na, K=K, Tris=Tris, Mg=Mg, dNTPs=dNTPs, ion_corr=True))
if primer_Tm >=minTm and primer_Tm <=maxTm:
Tm_hairpin = float(hairpin_Tm(primer, monovalent_cation_eq, primer_conc))
Tm_homodimer = float(homodimer_Tm(primer, monovalent_cation_eq, primer_conc))
if (primer_Tm - Tm_hairpin ) >= float(self_Tmdiff) and (primer_Tm - Tm_homodimer ) >= float(self_Tmdiff) :
if primer not in primer_dict:
primer_dict[primer] = [i, (primer_size), 1, primer_Tm, strand]
else:
primer_dict[primer][2] +=1
def primer_filter(primer, minTm, maxTm, GC_range_min, GC_range_max,
self_Tmdiff, filter_AT_3prime, primer_dict, i, strand,
filter_di_si_repeats, filter_GC_clamp):
if check_compostion(primer):
primer_GC = gc_content(primer)
if primer_GC >= GC_range_min and primer_GC <= GC_range_max:
primer_end_filter = check_ATends(primer, filter_AT_3prime)
if primer_end_filter == "noATend_filter":
primer_GC_clamp_filter = check_GC_clamp(
primer, filter_GC_clamp)
if primer_GC_clamp_filter == "noGC_clamp_filter":
primer_di_single_repeat_filter = di_single_nucleo_repeat_filter(
primer,
filter_di_si_repeats=filter_di_si_repeats,
di_si_repeats_threshold=di_si_repeats_threshold)
if primer_di_single_repeat_filter == 0:
primer_Tm = float(
NN_Tm(seq=primer,
compl_seq=complement(primer),
primer_conc=primer_conc,
Na=Na,
K=K,
Tris=Tris,
Mg=Mg,
dNTPs=dNTPs,
ion_corr=True))
if primer_Tm >= minTm and primer_Tm <= maxTm:
Tm_hairpin = float(
hairpin_Tm(primer, monovalent_cation_eq,
primer_conc))
Tm_homodimer = float(
homodimer_Tm(primer, monovalent_cation_eq,
primer_conc))
if (primer_Tm -
Tm_hairpin) >= float(self_Tmdiff) and (
primer_Tm -
Tm_homodimer) >= float(self_Tmdiff):
if primer not in primer_dict:
primer_dict[primer] = [
i, (primer_size), 1, primer_Tm, strand
]
else:
primer_dict[primer][2] += 1
def variant_mask(chr_no, start_pos, stop_pos, variant_path, refDB_path, write_path, time_stamp, variant_mask_condition):
indel_count = 0
snp_count = 0
filename = "chr" + str(chr_no)
output_poly_masked = open(write_path + str(time_stamp)+"_"+ str(chr_no) + "_"+ str(start_pos) + "_"+ str((stop_pos-start_pos)+1) + "_VariantMasked.fasta", "w")
output_poly_masked.write(str(">"+"TA_"+ str(chr_no) + "_"+ str(start_pos) + "_"+ str((stop_pos-start_pos)+1) + "_"+"VariantMasked"+'\n'))
Locus = get_Locus(start_pos, stop_pos, chr_no, refDB_path)
gap_count = Locus.count('N'*100)
locus_gc = gc_content(Locus)
if variant_mask_condition == 1:
df = pd.read_csv(variant_path+filename, sep='\t', header=0)
df = df[(df.coordinate >= int(start_pos)) & (df.coordinate <= int(stop_pos))]
for index, row in df.iterrows():
if '<INS>' in row['alternate_allele'] or '<DEL>' in row['alternate_allele']:
poly_coord = int(row['coordinate'])-(start_pos-1)
Locus = Locus[:(poly_coord-1)] + "n" + Locus[poly_coord:] # Indels annotated as "n"
indel_count += 1
else :
poly_coord = int(row['coordinate'])-(start_pos-1)
Locus = Locus[:(poly_coord-1)] + "N" + Locus[poly_coord:] # Polymorphisms other than indels annotated as "N"
snp_count += 1
output_poly_masked.write(str(Locus))
output_poly_masked.close()
return [indel_count, snp_count, gap_count, locus_gc]
f0 = open(os.devnull, 'w')
sp.call(["makeblastdb","-in","%s" %locus, "-dbtype","nucl","-parse_seqids","-out","%sloci_db" %query_path], stdout=f0,stderr=f0)
### Exact match to loci to get coords
p5 = sp.Popen(["blastn","-db","%sloci_db" %query_path,"-query","%s" %fasta_input_file_FR,"-evalue","0.1","-word_size","%s" %word_size,"-gapopen","0","-gapextend","2","-reward","1","-penalty","-3","-dust","no","-perc_identity","100","-max_target_seqs", "13","-outfmt","10 qseqid length sstart send", "-num_threads","%s" %mp_num_threads],stdout=sp.PIPE,stderr=f0)
exact_match_output_pooled_primers, error = p5.communicate()
### final pooled oligo coordinate output file
f5 = open(query_path + path + Time_stamp + "_" + 'PSE_out3_1.csv','w')
f5.write("Primer"+','+"Loci_start"+','+"Loci_stop"+','+"Genome_start"+','+"Genome_stop"+','+"Strand"+','+"Primer_Tm"+','+"Max_misprime_Tm"+','+"Tm_difference"+','+'Misprime_Tm_'+str(misprime_Tm_percentile_value)+'th_percentile'+','+"Primer_GC"+','+"Continuous_GC"+','+"3'_region_mismatches"+','+"Hairpin_Tm"+','+"Homodimer_Tm"+'\n') ### changed header name to Max_misprime_Tm
for exact_match_pooled_output_line in exact_match_output_pooled_primers.split('\n')[:-1]:
exact_match_pooled_output_line = exact_match_pooled_output_line.strip(' ').split(',')
Primer_pooled = exact_match_pooled_output_line[0]
primer_gc = gc_content(Primer_pooled)
primer_continuous_gc= continuous_gc(Primer_pooled)
query_len_pooled = len(Primer_pooled)
match_len_pooled = int(exact_match_pooled_output_line[1])
sstart = int(exact_match_pooled_output_line[2])
sstart = (actual_locus_start_pos + sstart) - 1
send = int(exact_match_pooled_output_line[3])
send = (actual_locus_start_pos + send) - 1
if query_len_pooled == match_len_pooled:
Primer_Tm_p = pooled_primer_f_r_dict[Primer_pooled][0]
Max_misprime_Tm_p = pooled_primer_f_r_dict[Primer_pooled][1]
Tm_difference_p = pooled_primer_f_r_dict[Primer_pooled][2]
three_prime_region_mismatches = pooled_primer_f_r_dict[Primer_pooled][3]
misprime_Tm_percentile = pooled_primer_f_r_dict[Primer_pooled][4]
Hairpin_Tm = pooled_primer_f_r_dict[Primer_pooled][5]
Homodimer_Tm = pooled_primer_f_r_dict[Primer_pooled][6]
def pick_primer_pairs(input_file):
G=nx.Graph()
primer_list = []
d_coords_plus = {}
d_coords_minus = {}
counter = 0
f = open(input_file)
csv_f = csv.DictReader(f, delimiter=',')
for row in csv_f:
primer, p_start_pos, p_stop_pos, strand, Tm, max_misprimeTm, GC = row['Primer'], int(row['Genome_start']), int(row['Genome_stop']), row['Strand'], \
float(row['Primer_Tm']), (row['Max_misprime_Tm']), float(row['Primer_GC'])
if max_misprimeTm == "3prime_mismatch":
max_misprimeTm=0
else:
max_misprimeTm=float(max_misprimeTm)
if Tm - max_misprimeTm >= pair_misprimeTm_diff:
primer_list.append(primer)
G.add_node(primer, p_start_pos=p_start_pos, p_stop_pos=p_stop_pos, strand=strand, Tm=Tm, max_misprimeTm=max_misprimeTm, GC=GC)
unique_primers = {}
primer_pair_coords = []
amplicon_len_list = []
amplicon_coords_list = []
mplex_ampl_coords_list = []
### pick primer pairs that meet the user defined conditions
### write bed files (for picked oligos)
f8 = open(path + Time_stamp + "_" +'bed_separate_tracks_selected_oligos.bed', 'w')
f8.write('browser position chr '+str(chr_no)+':'+ str(start_pos)+'-'+str(stop_pos)+'\n')
f8.write('track name="Primers" description="Primers on separate tracks" visibility=2 colorByStrand="255,0,0 0,0,255"' + '\n')
Gfor_subsetting=nx.Graph()
primer_pair_counter = 0
for (nodeId, data_f) in G.nodes(data=True):
if data_f['strand'] == "+":
forward_start = data_f['p_start_pos']
forward_Tm = int(data_f['Tm'])
forward_GC = int(data_f['GC'])
forward_MaxMispTm = int(data_f['max_misprimeTm'])
query_nodeId = nodeId
for (nodeId, data_r) in G.nodes(data=True):
if data_r['strand'] == "-":
amplicon_len = (data_r['p_stop_pos']- forward_start)+1
reverse_Tm = int(data_r['Tm'])
reverse_GC = int(data_r['GC'])
reverse_MaxMispTm = int(data_r['max_misprimeTm'])
### check if primer pair meets user defined amplicon length conditon
if amplicon_len >= amplicon_size_min and amplicon_len <= amplicon_size_max:
### check if primer pair meets user defined pair_misprimeTm_diff condition
if min(forward_Tm, reverse_Tm) - max(forward_MaxMispTm, reverse_MaxMispTm) >= pair_misprimeTm_diff:
### check if primer pair meets user defined pair_Tm_diff and pair_GC_diff conditions
if abs(forward_Tm-reverse_Tm) <= pair_Tm_diff:
### check if primer pair meets user defined between primer interaction_dg conditions
interaction_dg = heterodimer_dg(query_nodeId, nodeId, mv_cation=monovalent_cation_eq,primer_conc=primer_conc)
if interaction_dg >= min_misprime_dg:
amplicon_len_list.append(amplicon_len)
### get the expected amplicon sequence
amplicon_seq = spf.seq_extraction_loci(locus, start_pos, data_f['p_start_pos'], data_r['p_stop_pos'])
### eliminate amplicons with gaps
if amplicon_gap_filter == 1:
if 'N'*100 in amplicon_seq:
break
amplicon_gc = spf.gc_content(amplicon_seq.upper())
### check if amplicons have gaps and indels
if 'N'*100 in amplicon_seq:
gaps = 'Yes'
else:
gaps = 'No'
if 'n' in amplicon_seq:
indel = 'Yes'
else:
indel = 'No'
f_primer_length = len(query_nodeId)
r_primer_length = len(nodeId)
primer_name_f = "TA_" + str(chr_no) + "_" + str(data_f['p_start_pos']) + "_" + str(f_primer_length) + "_F"
primer_name_r = "TA_" + str(chr_no) + "_" + str(data_r['p_stop_pos']) + "_" + str(r_primer_length) + "_R" ### now naming of r primers uses 5' end coords
primer_pair_coords.append((data_f['p_start_pos'], data_r['p_stop_pos']))
if query_nodeId not in unique_primers:
f8.write('chr'+ str(chr_no)+'\t'+ str(data_f['p_start_pos'])+'\t'+ str(data_f['p_stop_pos'])+'\t'+ str(primer_name_f)+'\t'+ str(0) +'\t'+ "+"+'\n')
elif nodeId not in unique_primers:
f8.write('chr'+ str(chr_no)+'\t'+ str(data_r['p_start_pos'])+'\t'+ str(data_r['p_stop_pos'])+'\t'+ str(primer_name_r)+'\t'+ str(0) +'\t'+ "-"+'\n')
unique_primers[query_nodeId] = [str(chr_no), str(data_f['p_start_pos']), str(data_f['p_stop_pos']), str(data_f['Tm']), \
str(data_f['max_misprimeTm']), str(data_f['GC']), str(data_f['strand'])]
unique_primers[nodeId] = [str(chr_no), str(data_r['p_start_pos']), str(data_r['p_stop_pos']), str(data_r['Tm']), \
str(data_r['max_misprimeTm']), str(data_r['GC']), str(data_r['strand'])]
amplicon_coords = (data_f['p_start_pos'], data_r['p_stop_pos']) # nodes for creation of new network for subsetting connected components
amplicon_coords_list.append(amplicon_coords)
### info for multiplex primer picking
### select primers within the given Tm range if select multiplex primer select option is given in the parameters file
if multiplex_primers == 1 and data_f['Tm'] >= multiplex_Tm_min and data_r['Tm'] >= multiplex_Tm_min and data_f['Tm'] <= multiplex_Tm_max and data_r['Tm'] <= multiplex_Tm_max:
f_primer_info = {'primer_name':primer_name_f, 'primer_sequence':query_nodeId, 'strand':data_f['strand'], 'p_start_pos':data_f['p_start_pos'], 'p_stop_pos':data_f['p_stop_pos'], 'Tm':data_f['Tm'], 'max_misprimeTm':data_f['max_misprimeTm'], 'GC':data_f['GC']}
r_primer_info = {'primer_name':primer_name_r, 'primer_sequence':nodeId, 'strand':data_r['strand'], 'p_start_pos':data_r['p_start_pos'], 'p_stop_pos':data_r['p_stop_pos'], 'Tm':data_r['Tm'], 'max_misprimeTm':data_r['max_misprimeTm'], 'GC':data_r['GC']}
amplicon_info = {'interaction_dg':interaction_dg, 'amplicon_len':amplicon_len, 'amplicon_gc':amplicon_gc,'gaps':gaps, 'indel':indel, 'amplicon_seq':amplicon_seq}
Gfor_subsetting.add_node(amplicon_coords, f_primer_info = f_primer_info, r_primer_info = r_primer_info, amplicon_info = amplicon_info)
mplex_ampl_coords = (data_f['p_start_pos'], data_r['p_stop_pos'])
mplex_ampl_coords_list.append(mplex_ampl_coords)
primer_pair_counter += 1
output_primer_pairs.write(str(primer_pair_counter) + '\t' + str(primer_name_f)+'\t'+str(query_nodeId) +'\t'+ str(data_f['strand']) +'\t'+ str(data_f['p_start_pos']) +'\t'+ str(data_f['p_stop_pos']) +'\t'+ str(data_f['Tm'])+'\t'+ str(data_f['max_misprimeTm'])+'\t'+ str(data_f['GC']) +'\t'+ str(interaction_dg)+'\t'+ str(amplicon_len) +'\t'+ str(amplicon_gc)+'\t'+ str(gaps)+'\t'+ str(indel)+'\t'+ str(amplicon_seq)+'\n')
output_primer_pairs.write(str(primer_pair_counter) + '\t' + str(primer_name_r )+'\t'+str(nodeId)+'\t'+ str(data_r['strand'])+'\t'+ str(data_r['p_stop_pos']) +'\t'+ str(data_r['p_start_pos']) +'\t'+ str(data_r['Tm'])+'\t'+ str(data_r['max_misprimeTm'])+'\t'+ str(data_r['GC']) +'\t'+ '-'+'\t'+ '-' +'\t'+ '-' +'\t'+ '-' +'\t'+ '-' +'\t'+ '-'+'\n')
order_primer_pairs.write(str(primer_name_f )+'\t'+ str(query_nodeId) +'\t'+ str(data_f['Tm'])+'\n')
order_primer_pairs.write(str(primer_name_r)+'\t'+ str(nodeId) +'\t'+ str(data_r['Tm']) +'\n')
f8.close()
output_primer_pairs.close()
order_primer_pairs.close()
no_unique_primers_picked = len(unique_primers)
return {'mplex_ampl_coords_list': mplex_ampl_coords_list, 'Gfor_subsetting': Gfor_subsetting, 'amplicon_len_list': amplicon_len_list, 'amplicon_coords_list':amplicon_coords_list, 'primer_pair_coords': primer_pair_coords,\
'no_unique_primers_picked': no_unique_primers_picked}
def pick_primer_pairs(input_file):
G = nx.Graph()
primer_list = []
d_coords_plus = {}
d_coords_minus = {}
counter = 0
f = open(input_file)
csv_f = csv.DictReader(f, delimiter=',')
for row in csv_f:
primer, p_start_pos, p_stop_pos, strand, Tm, max_misprimeTm, GC = row['Primer'], int(row['Genome_start']), int(row['Genome_stop']), row['Strand'], \
float(row['Primer_Tm']), (row['Max_misprime_Tm']), float(row['Primer_GC'])
if max_misprimeTm == "3prime_mismatch":
max_misprimeTm = 0
else:
max_misprimeTm = float(max_misprimeTm)
if Tm - max_misprimeTm >= pair_misprimeTm_diff:
primer_list.append(primer)
G.add_node(primer,
p_start_pos=p_start_pos,
p_stop_pos=p_stop_pos,
strand=strand,
Tm=Tm,
max_misprimeTm=max_misprimeTm,
GC=GC)
unique_primers = {}
primer_pair_coords = []
amplicon_len_list = []
amplicon_coords_list = []
mplex_ampl_coords_list = []
### pick primer pairs that meet the user defined conditions
### write bed files (for picked oligos)
f8 = open(
path + Time_stamp + "_" + 'bed_separate_tracks_selected_oligos.bed',
'w')
f8.write('browser position chr ' + str(chr_no) + ':' + str(start_pos) +
'-' + str(stop_pos) + '\n')
f8.write(
'track name="Primers" description="Primers on separate tracks" visibility=2 colorByStrand="255,0,0 0,0,255"'
+ '\n')
Gfor_subsetting = nx.Graph()
primer_pair_counter = 0
for (nodeId, data_f) in G.nodes(data=True):
if data_f['strand'] == "+":
forward_start = data_f['p_start_pos']
forward_Tm = int(data_f['Tm'])
forward_GC = int(data_f['GC'])
forward_MaxMispTm = int(data_f['max_misprimeTm'])
query_nodeId = nodeId
for (nodeId, data_r) in G.nodes(data=True):
if data_r['strand'] == "-":
amplicon_len = (data_r['p_stop_pos'] - forward_start) + 1
reverse_Tm = int(data_r['Tm'])
reverse_GC = int(data_r['GC'])
reverse_MaxMispTm = int(data_r['max_misprimeTm'])
### check if primer pair meets user defined amplicon length conditon
if amplicon_len >= amplicon_size_min and amplicon_len <= amplicon_size_max:
### check if primer pair meets user defined pair_misprimeTm_diff condition
if min(forward_Tm, reverse_Tm) - max(
forward_MaxMispTm,
reverse_MaxMispTm) >= pair_misprimeTm_diff:
### check if primer pair meets user defined pair_Tm_diff and pair_GC_diff conditions
if abs(forward_Tm - reverse_Tm) <= pair_Tm_diff:
### check if primer pair meets user defined between primer interaction_dg conditions
interaction_dg = heterodimer_dg(
query_nodeId,
nodeId,
mv_cation=monovalent_cation_eq,
primer_conc=primer_conc)
if interaction_dg >= min_misprime_dg:
amplicon_len_list.append(amplicon_len)
### get the expected amplicon sequence
amplicon_seq = spf.seq_extraction_loci(
locus, start_pos,
data_f['p_start_pos'],
data_r['p_stop_pos'])
### eliminate amplicons with gaps
if amplicon_gap_filter == 1:
if 'N' * 100 in amplicon_seq:
break
amplicon_gc = spf.gc_content(
amplicon_seq.upper())
### check if amplicons have gaps and indels
if 'N' * 100 in amplicon_seq:
gaps = 'Yes'
else:
gaps = 'No'
if 'n' in amplicon_seq:
indel = 'Yes'
else:
indel = 'No'
f_primer_length = len(query_nodeId)
r_primer_length = len(nodeId)
primer_name_f = "TA_" + str(
chr_no) + "_" + str(
data_f['p_start_pos']) + "_" + str(
f_primer_length) + "_F"
primer_name_r = "TA_" + str(
chr_no
) + "_" + str(
data_r['p_stop_pos']
) + "_" + str(
r_primer_length
) + "_R" ### now naming of r primers uses 5' end coords
primer_pair_coords.append(
(data_f['p_start_pos'],
data_r['p_stop_pos']))
if query_nodeId not in unique_primers:
f8.write('chr' + str(chr_no) + '\t' +
str(data_f['p_start_pos']) +
'\t' +
str(data_f['p_stop_pos']) +
'\t' + str(primer_name_f) +
'\t' + str(0) + '\t' + "+" +
'\n')
elif nodeId not in unique_primers:
f8.write('chr' + str(chr_no) + '\t' +
str(data_r['p_start_pos']) +
'\t' +
str(data_r['p_stop_pos']) +
'\t' + str(primer_name_r) +
'\t' + str(0) + '\t' + "-" +
'\n')
unique_primers[query_nodeId] = [str(chr_no), str(data_f['p_start_pos']), str(data_f['p_stop_pos']), str(data_f['Tm']), \
str(data_f['max_misprimeTm']), str(data_f['GC']), str(data_f['strand'])]
unique_primers[nodeId] = [str(chr_no), str(data_r['p_start_pos']), str(data_r['p_stop_pos']), str(data_r['Tm']), \
str(data_r['max_misprimeTm']), str(data_r['GC']), str(data_r['strand'])]
amplicon_coords = (
data_f['p_start_pos'],
data_r['p_stop_pos']
) # nodes for creation of new network for subsetting connected components
amplicon_coords_list.append(
amplicon_coords)
### info for multiplex primer picking
### select primers within the given Tm range if select multiplex primer select option is given in the parameters file
if multiplex_primers == 1 and data_f[
'Tm'] >= multiplex_Tm_min and data_r[
'Tm'] >= multiplex_Tm_min and data_f[
'Tm'] <= multiplex_Tm_max and data_r[
'Tm'] <= multiplex_Tm_max:
f_primer_info = {
'primer_name':
primer_name_f,
'primer_sequence':
query_nodeId,
'strand':
data_f['strand'],
'p_start_pos':
data_f['p_start_pos'],
'p_stop_pos':
data_f['p_stop_pos'],
'Tm':
data_f['Tm'],
'max_misprimeTm':
data_f['max_misprimeTm'],
'GC':
data_f['GC']
}
r_primer_info = {
'primer_name':
primer_name_r,
'primer_sequence':
nodeId,
'strand':
data_r['strand'],
'p_start_pos':
data_r['p_start_pos'],
'p_stop_pos':
data_r['p_stop_pos'],
'Tm':
data_r['Tm'],
'max_misprimeTm':
data_r['max_misprimeTm'],
'GC':
data_r['GC']
}
amplicon_info = {
'interaction_dg': interaction_dg,
'amplicon_len': amplicon_len,
'amplicon_gc': amplicon_gc,
'gaps': gaps,
'indel': indel,
'amplicon_seq': amplicon_seq
}
Gfor_subsetting.add_node(
amplicon_coords,
f_primer_info=f_primer_info,
r_primer_info=r_primer_info,
amplicon_info=amplicon_info)
mplex_ampl_coords = (
data_f['p_start_pos'],
data_r['p_stop_pos'])
mplex_ampl_coords_list.append(
mplex_ampl_coords)
primer_pair_counter += 1
output_primer_pairs.write(
str(primer_pair_counter) + '\t' +
str(primer_name_f) + '\t' +
str(query_nodeId) + '\t' +
str(data_f['strand']) + '\t' +
str(data_f['p_start_pos']) + '\t' +
str(data_f['p_stop_pos']) + '\t' +
str(data_f['Tm']) + '\t' +
str(data_f['max_misprimeTm']) + '\t' +
str(data_f['GC']) + '\t' +
str(interaction_dg) + '\t' +
str(amplicon_len) + '\t' +
str(amplicon_gc) + '\t' + str(gaps) +
'\t' + str(indel) + '\t' +
str(amplicon_seq) + '\n')
output_primer_pairs.write(
str(primer_pair_counter) + '\t' +
str(primer_name_r) + '\t' +
str(nodeId) + '\t' +
str(data_r['strand']) + '\t' +
str(data_r['p_stop_pos']) + '\t' +
str(data_r['p_start_pos']) + '\t' +
str(data_r['Tm']) + '\t' +
str(data_r['max_misprimeTm']) + '\t' +
str(data_r['GC']) + '\t' + '-' + '\t' +
'-' + '\t' + '-' + '\t' + '-' + '\t' +
'-' + '\t' + '-' + '\n')
order_primer_pairs.write(
str(primer_name_f) + '\t' +
str(query_nodeId) + '\t' +
str(data_f['Tm']) + '\n')
order_primer_pairs.write(
str(primer_name_r) + '\t' +
str(nodeId) + '\t' +
str(data_r['Tm']) + '\n')
f8.close()
output_primer_pairs.close()
order_primer_pairs.close()
no_unique_primers_picked = len(unique_primers)
return {'mplex_ampl_coords_list': mplex_ampl_coords_list, 'Gfor_subsetting': Gfor_subsetting, 'amplicon_len_list': amplicon_len_list, 'amplicon_coords_list':amplicon_coords_list, 'primer_pair_coords': primer_pair_coords,\
'no_unique_primers_picked': no_unique_primers_picked}
def PickPrimerPair(inputfile):
G = nx.Graph()
primerList = []
d_coords_plus = {}
d_coords_minus = {}
primer_pair_counter = 0
f = open(inputfile)
locus = outdir + "sequence.txt"
output_primer_pairs = open(outdir + "PPS_primer_pairs_info.txt", "w")
output_primer_pairs.write('Primer_pair#'+'\t'+'Primer_name'+'\t'+'Primer_seq'+'\t'+ 'Strand'+'\t'+ '5prime_pos' +'\t'+ '3prime_pos' +'\t'+ 'Tm' +'\t'+ \
'Max_misprimeTm'+'\t'+ 'GC' +'\t'+ 'Primer_dimer_dG' +'\t'+ 'Amplicon_size' +'\t'+ 'Amplicon_GC' +'\t'+ 'Gaps'+'\t'+ 'Polymorphisms'+'\t'+ 'Amplicon_seq'+'\n')
order_primer_pairs = open(outdir + "_" + "primer_pairs_order.txt", "w")
order_primer_pairs.write('Primer_name' + '\t' + 'Primer_seq' + '\t' +
'Tm' + '\n')
csv_f = csv.DictReader(f, delimiter=',')
for row in csv_f:
id_p, primer, start, end, strand, Tm, max_misprimeTm, GC , Continuous_GC = row['id'], row['Primer'], int(row['start']), \
int(row['stop']), row['Strand'], float(row['Primer_Tm']), row['Max_misprime_Tm'], float(row['Primer_GC']), int(row['Continuous_GC'])
if max_misprimeTm == "3prime_mismatch":
max_misprimeTm = 0
else:
max_misprimeTm = float(max_misprimeTm)
if Tm - max_misprimeTm >= pair_misprimeTm_diff:
primerList.append(id_p)
G.add_node(id_p, p_chrom=id_p.split('_')[2], p_start_pos=int(id_p.split('_')[3]), p_stop_pos=int(id_p.split('_')[3])+int(id_p.split('_')[4]), \
strand=strand, Tm=Tm, max_misprimeTm=max_misprimeTm, GC=GC, Continuous_GC=Continuous_GC)
unique_primers = {}
primer_pair_coords = []
amplicon_len_list = []
amplicon_coords_list = []
mplex_ampl_coords_list = []
f8 = open(outdir + 'bed_separate_tracks_selected_oligos.bed', 'w')
#f8.write('browser position chr '+str(chr_no)+':'+ str(start_pos)+'-'+str(stop_pos)+'\n')
f8.write(
'track name="Primers" description="Primers on separate tracks" visibility=2 colorByStrand="255,0,0 0,0,255"'
+ '\n')
Gfor_subsetting = nx.Graph()
for (nodeId, data) in G.nodes(data=True):
'''data ------ {'p_chrom': 'chr17', 'p_start_pos': 7565168, 'Tm': 65.84, 'GC': 52.17, 'p_stop_pos': 7565191, 'max_misprimeTm': 54.02, 'strand': '+'}
nodeId ------'TA_1_chr17_7565168_23_65.84_+_TCCCTGGTTAAGAGATCCTCCTG'
'''
if data['strand'] == "+":
forward_chrom = data['p_chrom']
forward_start = data['p_start_pos']
forward_stop = data['p_stop_pos']
amplicon_start = int(forward_stop)
amplicon_end = int(forward_start) + 120
forward_Tm = int(data['Tm'])
forward_GC = int(data['GC'])
forward_MaxMispTm = int(data['max_misprimeTm'])
#query_nodeId = nodeId
id_f = nodeId.split('_')[1]
f_primer_length = len(nodeId.split('_')[-1])
primer_name_f = "TA_" + str(
id_f) + "_" + forward_chrom + "_" + str(
data['p_start_pos']) + "_" + str(f_primer_length) + "_F"
if forward_Tm - forward_MaxMispTm >= pair_misprimeTm_diff:
amplicon_seq = seq_extraction_loci(locus, id_f, amplicon_start,
amplicon_end)
if amplicon_seq == '':
continue
if amplicon_gap_filter == 1:
if 'N' * 100 in amplicon_seq:
continue
amplicon_gc = spf.gc_content(amplicon_seq.upper())
if 'N' * 100 in amplicon_seq:
gaps = 'Yes'
else:
gaps = 'No'
if 'n' in amplicon_seq:
indel = 'Yes'
else:
indel = 'No'
amplicon_coords = (id_f, forward_chrom, data['p_stop_pos'],
amplicon_end)
amplicon_coords_list.append(amplicon_coords)
if data['Tm'] >= multiplex_Tm_min and data[
'Tm'] <= multiplex_Tm_max and data[
'Continuous_GC'] <= Continus_GC_num:
primer_info = {'primer_chr':forward_chrom, 'primer_name':primer_name_f, 'primer_sequence':nodeId, \
'strand':data['strand'], 'p_start_pos':data['p_start_pos'], 'p_stop_pos':data['p_stop_pos'], \
'Tm':data['Tm'], 'max_misprimeTm':data['max_misprimeTm'], 'GC':data['GC']}
amplicon_info = {
'amplicon_gc': amplicon_gc,
'gaps': gaps,
'indel': indel,
'amplicon_seq': amplicon_seq
}
Gfor_subsetting.add_node(amplicon_coords,
id_f=id_f,
primer_info=primer_info,
amplicon_info=amplicon_info)
mplex_ampl_coords = (id_f, forward_chrom,
data['p_stop_pos'], amplicon_end)
mplex_ampl_coords_list.append(mplex_ampl_coords)
primer_pair_counter += 1
output_primer_pairs.write(str(primer_pair_counter) + '\t' + str(primer_name_f)+'\t'+str(nodeId.split("_")[-1]) +'\t'+ \
str(data['strand']) +'\t'+ str(data['p_start_pos']) +'\t'+ str(data['p_stop_pos']) +'\t'+ str(data['Tm'])+'\t'+ \
str(data['max_misprimeTm'])+'\t'+ str(data['GC']) +'\t'+ \
str(amplicon_gc)+'\t'+ str(gaps)+'\t'+ str(indel)+'\t'+ str(amplicon_seq)+'\n')
if data['strand'] == "-":
reverse_chrom = data['p_chrom']
reverse_start = data['p_start_pos']
reverse_stop = data['p_stop_pos']
amplicon_start = int(reverse_start) - 120
amplicon_end = int(reverse_start)
id_r = nodeId.split('_')[1]
reverse_Tm = int(data['Tm'])
reverse_GC = int(data['GC'])
reverse_MaxMispTm = int(data['max_misprimeTm'])
r_primer_length = len(nodeId.split('_')[-1])
primer_name_r = "TA_" + str(
id_r) + "_" + reverse_chrom + "_" + str(
data['p_start_pos']) + "_" + str(r_primer_length) + "_R"
if reverse_Tm - reverse_MaxMispTm >= pair_misprimeTm_diff:
amplicon_seq = seq_extraction_loci(locus, id_r, amplicon_start,
amplicon_end)
if amplicon_seq == '':
continue
if amplicon_gap_filter == 1:
if 'N' * 100 in amplicon_seq:
continue
amplicon_gc = spf.gc_content(amplicon_seq.upper())
if 'N' * 100 in amplicon_seq:
gaps = 'Yes'
else:
gaps = 'No'
if 'n' in amplicon_seq:
indel = 'Yes'
else:
indel = 'No'
amplicon_coords = (id_r, reverse_chrom, amplicon_start,
amplicon_end)
amplicon_coords_list.append(amplicon_coords)
if data['Tm'] >= multiplex_Tm_min and data[
'Tm'] <= multiplex_Tm_max and data[
'Continuous_GC'] <= Continus_GC_num:
primer_info = {'primer_chr':reverse_chrom, 'primer_name':primer_name_r, 'primer_sequence':nodeId, \
'strand':data['strand'], 'p_start_pos':data['p_start_pos'], 'p_stop_pos':data['p_stop_pos'], \
'Tm':data['Tm'], 'max_misprimeTm':data['max_misprimeTm'], 'GC':data['GC']}
amplicon_info = {
'amplicon_gc': amplicon_gc,
'gaps': gaps,
'indel': indel,
'amplicon_seq': amplicon_seq
}
Gfor_subsetting.add_node(amplicon_coords,
id_r=id_r,
primer_info=primer_info,
amplicon_info=amplicon_info)
mplex_ampl_coords = (id_r, reverse_chrom, amplicon_start,
data['p_start_pos'])
mplex_ampl_coords_list.append(mplex_ampl_coords)
primer_pair_counter += 1
output_primer_pairs.write(str(primer_pair_counter) + '\t' + str(primer_name_r)+'\t'+str(nodeId.split("_")[-1]) +'\t'+ \
str(data['strand']) +'\t'+ str(data['p_start_pos']) +'\t'+ str(data['p_stop_pos']) +'\t'+ str(data['Tm'])+'\t'+ \
str(data['max_misprimeTm'])+'\t'+ str(data['GC']) +'\t'+ \
str(amplicon_gc)+'\t'+ str(gaps)+'\t'+ str(indel)+'\t'+ str(amplicon_seq)+'\n')
#primer_length = len(nodeId.split('_')[-1])
f8.close()
output_primer_pairs.close()
order_primer_pairs.close()
no_unique_primers_picked = len(unique_primers)
return {
'mplex_ampl_coords_list': mplex_ampl_coords_list,
'Gfor_subsetting': Gfor_subsetting,
'amplicon_coords_list': amplicon_coords_list,
'primer_pair_counter': primer_pair_counter
}