def Amplicon_pos(self):
"locate amplicon; the positions are 0 indexed."
F3 = self['F3']
B3c = self['B3c']
s, _ = REFape.locate_primer(F3)
_, e = REFape.locate_primer(B3c)
self['A_start'] = s
self['A_end'] = e
return self
def LoopHairpin(self):
"check loop region of amplicon hairpin"
lfs, _ = REFape.locate_primer(self['F2'])
lfe, _ = REFape.locate_primer(self['F1'])
_, lrs = REFape.locate_primer(self['B1c'])
_, lre = REFape.locate_primer(self['B2c'])
lf = revcomp(REFape[lfs:lfe])[0:60]
lr = REFape[lrs:lre][0:60]
lfr = primer3.bindings.calcHairpin(lf, mv_conc, dv_conc, dntp_conc)
lrr = primer3.bindings.calcHairpin(lr, mv_conc, dv_conc, dntp_conc)
self['FloopdG'] = round(lfr.dg / 1000, 4)
self['FloopTm'] = round(lfr.tm, 3)
self['RloopdG'] = round(lrr.dg / 1000, 4)
self['RloopTm'] = round(lrr.tm, 3)
return self
def iter_primerset_html(files):
"""
iterate over primerdesign result from PrimerExplorer website.
yield: PrimerSetRecord()
[setname,F3,B3,FIP,BIP,LF,LB,B2c,B1c,F2,F1,gene,B3c,LFc,PEdG]
"""
keys = [
'name', 'F3', 'B3', 'FIP', 'BIP', 'LF', 'LB', 'B2c', 'B1c', 'F2', 'F1',
'gene', 'B3c', 'LFc', 'PEdG'
]
# p1 = re.compile("""<td><span class="dnaString">\[(?P<id>\d*)\]</span></td>(?P<content>.*)<td><span class="dnaString">\[(?P=id)\]</span></td>""",flags=re.DOTALL)
p1 = re.compile(
"""<td>\[(?P<id>\d*)\]</td>(?P<content>.*)<td><span class="dnaString">\[(?P=id)\]</span></td>""",
flags=re.DOTALL)
p2 = re.compile(
'<span class="dnaString" style="color:#(?P<color>.{6});">(?P<seq>[ATCGatcg]*)</span>'
)
dG = re.compile('<td align="left">(?P<dG>[-.\d]+)</td>')
name_counter = Counter()
for file in files:
with open(file, 'rt') as fr:
text = fr.read()
for s in p1.finditer(text):
content = s['content']
PEdG = float(dG.search(content)['dG'])
out = []
color = ""
case = None
for d in p2.finditer(content):
seq = d['seq']
if d['color'] != color or case != seq.isupper():
color = d['color']
case = seq.isupper()
out.append("")
out[-1] += seq
F3, F2, F1c, B1c, B2, B3 = [i.upper() for i in out]
F1c, B2, B3 = F1c[::-1], B2[::-1], B3[::-1]
B2c = revcomp(B2)
B3c = revcomp(B3)
F1 = revcomp(F1c)
FIP = F1c + F2
BIP = B1c + B2
gene = REFape.name_primer(F1)
name_counter[gene[0]] += 1
setname = gene[0] + str(name_counter[gene[0]])
yield PrimerSetRecord(
zip(keys, [
setname, F3, B3, FIP, BIP, '', '', B2c, B1c, F2, F1, gene,
B3c, '', PEdG
]))
def iter_primerset_lamp_design_csv(*files,
skiprows=None,
usecols=[1, 2],
skipfooter=0,
return_df=False):
"""
read all csv files convert to a single DataFrame
then iterate over primer sets,give it a name based on locus
yield: PrimerSetRecord()
[setname,F3,B3,FIP,BIP,LF,LB,B2c,B1c,F2,F1,gene,B3c,LFc,]
"""
df = pd.DataFrame(columns=['name', 'seq'])
dfs = [df]
for f in files:
if skiprows == None:
with open(f, 'rt') as ff:
data = ff.read().split('\n')
for k, line in enumerate(data):
if line.startswith('set'):
skiprows = k
_df = pd.read_csv(f,
skiprows=list(range(skiprows)),
usecols=usecols,
skipfooter=skipfooter)
dfs.append(_df)
df = pd.concat(dfs, axis=0, ignore_index=True)
if return_df:
yield df
else:
name_counter = Counter()
for i in range((len(df) // 8)):
F3, F2, F1, B1c, B2c, B3c, LFc, LB = list(df.loc[i * 8:(i * 8 + 7),
'seq'])
names = list(df.loc[i * 8:(i * 8 + 7), 'name'])
assert len(set(names)) == 8, f"Primer set incomplete at index {i}."
gene = REFape.name_primer(F1)
name_counter[gene[0]] += 1
setname = gene[0] + str(name_counter[gene[0]])
yield PrimerSetRecord([
setname, F3,
revcomp(B3c),
revcomp(F1) + F2, B1c + revcomp(B2c),
revcomp(LFc), LB, B2c, B1c, F2, F1, gene, B3c, LFc
])
def iter_primerset_excel():
"yield:PrimerSetRecord([setname,F3,B3,FIP,BIP,LF,LB,B2c,B1c,F2,F1,gene,B3c,LFc,])"
ps = read_primerset_excel()
for p in ps:
name = p['set']
pm = p['feature']
pd = {i.replace(name + '-', ''): j for i, _, j in pm}
F3 = pd.get('F3', None)
B3 = pd.get('B3', None)
F2 = pd.get('F2', None)
F1c = pd.get('F1c', None)
B2 = pd.get('B2', None)
B1c = pd.get('B1c', None)
LF = pd.get('LF', None)
LB = pd.get('LB', None)
gene = REFape.name_primer(revcomp(F1c))
if all([F3, B3, F2, F1c, B2, B1c, LF, LB]):
yield PrimerSetRecord([
name, F3, B3, F1c + F2, B1c + B2, LF, LB,
revcomp(B2), B1c, F2,
revcomp(F1c), gene,
revcomp(B3),
revcomp(LF)
])
def draw_primerset(self,
basepairposition=None,
saveas=False,
alignwith=None,
drawgene=True,
drawproperty=[],
figwidth=None,
figheight=None,
drawgrid=False):
"""
draw ther primers on plot.
basepairposition: draw only primerset record with A_start and A_end within the interval given.
saveas: file path to save.
alignwith: the gene fragment to aligh, defalut align to gene. can be F3, F2, F1, B1c, LFc, LB etc.
drawgene: choose whether draw the genebar.
drawproperty: a list of (property_name, property_format) to draw. ('Inclusivity','{:.2%}')
"""
pl = self
if basepairposition:
pl = PrimerSetRecordList(i for i in pl
if i['A_start'] >= basepairposition[0]
and i['A_end'] <= basepairposition[1])
facecolor = ('tab:blue', 'tab:orange', 'tab:green', 'tab:red',
'tab:purple', 'tab:brown', 'tab:pink', 'tab:olive')
fig, ax = plt.subplots(figsize=(figwidth or 10, figheight or 0.26 *
(len(pl) + drawgene) + 0.68))
left_pos = [REFape.locate_primer(i['F3'])[0] for i in pl]
right_pos = [REFape.locate_primer(i['B3c'])[1] for i in pl]
left_min = min(left_pos)
right_min = max(right_pos)
common_fragment = REFape.truncate(left_min, right_min)
gene_bar = [(i['start'] - 1, i['end'] - i['start'] + 1)
for i in common_fragment.features]
# plot realative position to N gene:
gene_bar_name = [
f"{ i['tag']}:{i['start']+left_min - REFape.get_feature_pos(i['tag'])[0]}-{i['end']+left_min- REFape.get_feature_pos(i['tag'])[0]}"
for i in common_fragment.features
]
y_labels = [i['name'] for i in pl]
ax.set_yticks(list(range(len(y_labels))))
if drawgrid:
ax.grid(axis='y', linewidth=0.3, linestyle='-.')
ax.set_yticklabels(y_labels)
ax.set_ylim([-1, len(pl) + drawgene])
for y, p in enumerate(pl):
plot_bar = []
plot_bar_name = []
for n, i in p.iter('fragment'):
if i:
pos = REFape.locate_primer(i)
plot_bar_name.append(n)
plot_bar.append((pos[0], pos[1] - pos[0]))
# if alignwith = F3 or other fragment name, use that position.
if alignwith:
_index = plot_bar_name.index(alignwith)
left_min = plot_bar[_index][0]
# relative position of the primer to this gene.
_relative_left = REFape.get_relative_pos(plot_bar[0][0])
relative_left = f"{_relative_left[1]+1}" if _relative_left else f"{plot_bar[0][0]}"
_relative_right = REFape.get_relative_pos(plot_bar[3][0])
relative_right = f"{_relative_right[1]+plot_bar[3][1]}" if _relative_right else f"{plot_bar[3][0]}"
plot_bar = [(i - left_min, j) for i, j in plot_bar]
ax.broken_barh(plot_bar, (y - 0.3, 0.6), facecolors=facecolor)
for n, (_p, w) in zip(plot_bar_name, plot_bar):
ax.text(_p + w / 2, y - 0.3, n, ha='center', va='bottom')
ax.text(plot_bar[0][0] - plot_bar[0][1] * 0.05,
y - 0.3,
relative_left,
ha='right',
va='bottom')
ax.text(plot_bar[3][0] + plot_bar[3][1] * 1.05,
y - 0.3,
relative_right,
ha='left',
va='bottom')
if drawproperty:
propertytext = []
for i, f in drawproperty:
propertytext.append(f.format(p[i]))
ax.text((right_min - left_min) * 1.06,
y - 0.3,
" " + ' | '.join(propertytext),
ha='left',
va='bottom',
family='monospace')
if drawproperty:
ax.text(
(right_min - left_min) * 1.06,
y + 0.7,
'|'.join(i[0][0:(len(t) + 2)] + " " * (len(t) + 2 - len(i[0]))
for i, t in zip(drawproperty, propertytext)),
ha='left',
va='bottom',
family='monospace')
# if need to draw gen:
if drawgene:
ax.broken_barh(gene_bar, (y + 0.7, 0.6), facecolor=facecolor)
for n, (p, w) in zip(gene_bar_name, gene_bar):
ax.text(p + w / 2, y + 0.7, n, ha='center', va='bottom')
ax.set_xticks([])
plt.tight_layout()
if saveas:
plt.savefig(saveas)
else:
plt.show()
def loopR(self):
return REFape[REFape.locate_primer(self['B1c'])[1]:REFape.
locate_primer(self['B2c'])[1]]
def loopF(self):
return revcomp(REFape[REFape.locate_primer(self['F2'])[0]:REFape.
locate_primer(self['F1'])[0]])
def to_ape(self, ):
primers = dict(self.iter('primer'))
return REFape.label_from_primers(primers, name=self['name'])
def gap_positions(self):
"return a list of all 12 gap positions, 0 indexed."
return [
j for i in ['F3', 'F2', 'F1', 'B1c', 'B2c', 'B3c']
for j in REFape.locate_primer(self[i])
]