def _format_report_body(self):
body = ''
body += self._PCR_Simulation.format_quantity_explanation()
#PCR products by hit
body += hr(' histogram of all possible PCR products ', symbol='=')
if len(self._PCR_Simulation.hits()) == 1:
#all products histogram
hit = self._PCR_Simulation.hits()[0]
body += self._PCR_Simulation.per_hit_header(hit)
body += self._PCR_Simulation.per_hit_histogram(hit)
body += '\n'
body += hr(' electrophorogram of all possible PCR products ',
symbol='=')
body += self._PCR_Simulation.per_hit_electrophoresis(hit)
else:
products = self._PCR_Simulation.products().items()
products.sort(key=lambda
(d): max(p.quantity for p in d[1].values()),
reverse=True)
#all products histogram
body += self._PCR_Simulation.all_products_histogram(products)
body += '\n\n\n'
#per hit histogram and phoresis
body += hr(
' histograms and electrophorograms of PCR products of each hit ',
symbol='=')
body += self._PCR_Simulation.all_graphs_grouped_by_hit(products)
return body
#end def
#end class
def _format_report_body(self):
body = ''
body += self._PCR_Simulation.format_quantity_explanation()
#PCR products by hit
body += hr(' histogram of all possible PCR products ', symbol='=')
if len(self._PCR_Simulation.hits()) == 1:
#all products histogram
hit = self._PCR_Simulation.hits()[0]
body += self._PCR_Simulation.per_hit_header(hit)
body += self._PCR_Simulation.per_hit_histogram(hit)
body += '\n'
body += hr(' electrophorogram of all possible PCR products ', symbol='=')
body += self._PCR_Simulation.per_hit_electrophoresis(hit)
else:
products = self._PCR_Simulation.products().items()
products.sort(key=lambda(d): max(p.quantity for p in d[1].values()), reverse=True)
#all products histogram
body += self._PCR_Simulation.all_products_histogram(products)
body += '\n\n\n'
#per hit histogram and phoresis
body += hr(' histograms and electrophorograms of PCR products of each hit ', symbol='=')
body += self._PCR_Simulation.all_graphs_grouped_by_hit(products)
return body
#end def
#end class
def _format_str(self, full=True):
"""If 'full', for single sequence output self-dimers and hairpins.
For two sequences output only cross-dimers
If not 'full', for single sequence output COUNTS and min dG of self-dimers and hairpins.
For two sequences output the same only for cross-dimers"""
if full:
format_dimers = self._format_dimers
format_hairpins = self._format_hairpins
else:
format_dimers = self._format_dimers_short
format_hairpins = self._format_hairpins_short
string = '\n'
if self._seq2:
string += hr(' %s vs %s cross-dimers ' % (self._seq_rec1.id, self._seq_rec2.id), symbol='=')
dimers = self._cross_dimers.values()
dimers.sort(key=lambda(s): s.dG)
string += format_dimers(dimers, self._seq1, self._seq2)
else:
string += hr(' %s: %s ' % (self._seq_rec1.id, str(self._seq1)), symbol='=')
string += hr(' self-dimers ')
dimers = self._seq1_dimers.values()
dimers.sort(key=lambda(s): s.dG)
string += format_dimers(dimers, self._seq1, self._seq1)
string += hr(' hairpins ')
hairpins = self._seq1_hairpins.values()
hairpins.sort(key=lambda(s): s.dG)
string += format_hairpins(hairpins, self._seq1)
string += hr('',symbol='=')
return string
def _format_primers_report_header(self):
header_string = ''
header_string += time_hr()
header_string += wrap_text(
'For each degenerate primer provided, a set '
'of unambiguous primers is generated. '
'For each such set the minimum, maximum and '
'mean melting temperatures are calculated. '
'For each primer in each set stable self-'
'dimers and hairpins are predicted. '
'For every possible combination of two '
'unambiguous primers cross-dimers are also '
'predicted. If an unambiguous primer is '
'provided, it is treated as a set with a '
'single element.\n\n')
header_string += hr(' PCR conditions ')
header_string += TD_Functions.format_PCR_conditions(
self._primers) + '\n'
header_string += hr(' primers and their melting temperatures ')
for primer in self._primers:
header_string += repr(primer) + '\n'
#warning
if len(self._primers) > 1:
if abs(self._primers[0].Tm_min - self._primers[1].Tm_min) >= 5:
header_string += '\nWarning: lowest melting temperatures of sense and antisense primes \n'
header_string += ' differ more then by 5C\n'
header_string += '\n'
return header_string
def _format_primers_report_header(self):
header_string = ''
header_string += time_hr()
header_string += wrap_text('For each degenerate primer provided, a set '
'of unambiguous primers is generated. '
'For each such set the minimum, maximum and '
'mean melting temperatures are calculated. '
'For each primer in each set stable self-'
'dimers and hairpins are predicted. '
'For every possible combination of two '
'unambiguous primers cross-dimers are also '
'predicted. If an unambiguous primer is '
'provided, it is treated as a set with a '
'single element.\n\n')
header_string += hr(' PCR conditions ')
header_string += TD_Functions.format_PCR_conditions(self._primers)+'\n'
header_string += hr(' primers and their melting temperatures ')
for primer in self._primers:
header_string += repr(primer) + '\n'
#warning
if len(self._primers) > 1:
if abs(self._primers[0].Tm_min - self._primers[1].Tm_min) >= 5:
header_string += '\nWarning: lowest melting temperatures of sense and antisense primes \n'
header_string += ' differ more then by 5C\n'
header_string += '\n'
return header_string
def worker(hit_products):
hit = hit_products[0]
graphs = self.per_hit_histogram(hit)
graphs += self.per_hit_header(hit)
graphs += hr(' electrophorogram of PCR products ')
graphs += self.per_hit_electrophoresis(hit)
graphs += hr('')
graphs += '\n\n'
return graphs
def worker(hit_products):
hit = hit_products[0]
graphs = self.per_hit_histogram(hit)
graphs += self.per_hit_header(hit)
graphs += hr(' electrophorogram of PCR products ')
graphs += self.per_hit_electrophoresis(hit)
graphs += hr('')
graphs += '\n\n'
return graphs
def worker(hit):
prod_string = hr(' %s ' % hit, '*')
prod_string += hr(' %d products have been found ' % len(self._products[hit]), '*')
products = self._products[hit].values()
products.sort(key=lambda x: x.start)
for pi, product in enumerate(products):
prod_string += hr(' product %d ' % (pi+1), '=')
prod_string += product.pretty_print(with_name=False, include_fwd_3_mismatch=self._with_exonuclease)
prod_string += hr('', '=')
prod_string += hr('', '*')
return prod_string
def worker(hit):
prod_string = hr(' %s ' % hit, '*')
prod_string += hr(
' %d products have been found ' % len(self._products[hit]),
'*')
products = self._products[hit].values()
products.sort(key=lambda x: x.start)
for pi, product in enumerate(products):
prod_string += hr(' product %d ' % (pi + 1), '=')
prod_string += product.pretty_print(
with_name=False,
include_fwd_3_mismatch=self._with_exonuclease)
prod_string += hr('', '=')
prod_string += hr('', '*')
return prod_string
def print_structures(self, full=True):
strings = []
for i, primer in enumerate(self._primers):
structs = self._print_structures(self._self[i], full)
if structs:
strings.append(hr(' secondary structures of %s primers ' % primer.id, '#'))
strings.append(structs)
if self._cross:
cross_structs = self._print_structures(self._cross, full)
if cross_structs:
strings.append(hr(' cross-dimers ', '#'))
strings.append(cross_structs)
if strings:
strings.insert(0, hr(' stable secondary structures ', symbol='#'))
else: strings.append(hr(' no stable secondary structures found ', symbol='#'))
return ''.join(strings)
def pretty_print(self, with_name=True, include_fwd_3_mismatch=True):
rep = Region.pretty_print(self, with_name=with_name)
rep += '\n'
rep += 'concentration: %s\n' % tdf.format_concentration(self.quantity)
rep += 'number of cycles: %d\n' % self.cycles
rep += '\n'
rep += hr(' forward annealing site ')
rep += self.fwd_template.pretty_print(with_name=False)
rep += '\n'
rep += hr(' reverse annealing site ')
rep += self.rev_template.pretty_print(with_name=False)
rep += '\n'
rep += hr(' forward primers ')
rep += self._rep_primers(self.fwd_primers, lambda p: p.print_most_stable(include_fwd_3_mismatch))
rep += '\n'
rep += hr(' reverse primers ')
rep += self._rep_primers(self.rev_primers, lambda p: p.print_most_stable(include_fwd_3_mismatch))
return rep
def format_report_header(self):
header_string = ''
header_string += hr(' PCR conditions ')
if self._with_exonuclease:
header_string += "DNA polymerase HAS 3'-5'-exonuclease activity.\n"
else: header_string += "DNA polymerase doesn't have 3'-5'-exonuclease activity.\n"
header_string += 'Speed of DNA polymerase is considered to be 1 kbs/min\n\n'
header_string += 'Minimum amplicon size: %d\n' % self._min_amplicon
header_string += 'Maximum amplicon size: %d\n' % self._max_amplicon
header_string += 'Elongation time: %s\n' % timedelta(minutes=self._elongation_time)
header_string += 'Maximum cycles: %d\n' % self._num_cycles
header_string += '\n'
header_string += tdf.format_PCR_conditions(self._primers, self._polymerase)+'\n'
header_string += hr(' primers and their melting temperatures ')
for primer in self._primers:
header_string += repr(primer) + '\n'
header_string += '\n'
return header_string
def print_structures(self, full=True):
strings = []
for i, primer in enumerate(self._primers):
structs = self._print_structures(self._self[i], full)
if structs:
strings.append(
hr(' secondary structures of %s primers ' % primer.id,
'#'))
strings.append(structs)
if self._cross:
cross_structs = self._print_structures(self._cross, full)
if cross_structs:
strings.append(hr(' cross-dimers ', '#'))
strings.append(cross_structs)
if strings:
strings.insert(0, hr(' stable secondary structures ', symbol='#'))
else:
strings.append(
hr(' no stable secondary structures found ', symbol='#'))
return ''.join(strings)
def write_products_report(self):
if not self._have_results: return
#open report file
ipcr_products = self._open_report('BLAST PCR products', self._PCR_products_filename)
ipcr_products.write(time_hr())
for record_name in self._PCR_Simulations:
ipcr_products.write(hr(' query ID: %s ' % record_name, symbol='#'))
ipcr_products.write(self._PCR_Simulations[record_name].format_products_report())
ipcr_products.close()
print '\nThe list of BLAST PCR products was written to:\n ',self._PCR_products_filename
self._add_report('BLAST PCR products', self._PCR_products_filename)
def format_report_header(self):
header_string = ''
header_string += hr(' PCR conditions ')
if self._with_exonuclease:
header_string += "DNA polymerase HAS 3'-5'-exonuclease activity.\n"
else:
header_string += "DNA polymerase doesn't have 3'-5'-exonuclease activity.\n"
header_string += 'Speed of DNA polymerase is considered to be 1 kbs/min\n\n'
header_string += 'Minimum amplicon size: %d\n' % self._min_amplicon
header_string += 'Maximum amplicon size: %d\n' % self._max_amplicon
header_string += 'Elongation time: %s\n' % timedelta(
minutes=self._elongation_time)
header_string += 'Maximum cycles: %d\n' % self._num_cycles
header_string += '\n'
header_string += tdf.format_PCR_conditions(self._primers,
self._polymerase) + '\n'
header_string += hr(' primers and their melting temperatures ')
for primer in self._primers:
header_string += repr(primer) + '\n'
header_string += '\n'
return header_string
def _format_report_body(self):
body = ''
for record_name in self._PCR_Simulations:
body += hr(' query ID: %s ' % record_name, symbol='#')
if len(self._PCR_Simulations[record_name].hits()) == 1:
#all products histogram
hit = self._PCR_Simulations[record_name].hits()[0]
body += hr(' histogram of all possible PCR products ', symbol='=')
body += self._PCR_Simulations[record_name].per_hit_header(hit)
body += self._PCR_Simulations[record_name].per_hit_histogram(hit)
body += '\n'
body += hr(' electrophorogram of all possible PCR products ', symbol='=')
body += self._PCR_Simulations[record_name].per_hit_electrophoresis(hit)
else:
#all products histogram
body += hr(' histogram of all possible PCR products ', symbol='=')
body += self._PCR_Simulations[record_name].all_products_histogram()
body += '\n\n\n'
#per hit histogram and phoresis
body += hr(' histograms and electrophorograms of PCR products of each hit ', symbol='=')
body += self._PCR_Simulations[record_name].all_graphs_grouped_by_hit()
return body
def write_products_report(self):
if not self._have_results: return
#open report file
ipcr_products = self._open_report('iPCR products', self._PCR_products_filename)
ipcr_products.write(time_hr())
if self._PCR_Simulation:
ipcr_products.write(self._PCR_Simulation.format_products_report())
else: ipcr_products.write(hr(' No PCR products have been found ', symbol='!'))
ipcr_products.close()
print '\nThe list of PCR products was written to:\n %s' % self._PCR_products_filename
self._add_report('iPCR products', self._PCR_products_filename)
#end def
#end class
def pretty_print(self, with_name=True, include_fwd_3_mismatch=True):
rep = Region.pretty_print(self, with_name=with_name)
rep += '\n'
rep += 'concentration: %s\n' % tdf.format_concentration(
self.quantity)
rep += 'number of cycles: %d\n' % self.cycles
rep += '\n'
rep += hr(' forward annealing site ')
rep += self.fwd_template.pretty_print(with_name=False)
rep += '\n'
rep += hr(' reverse annealing site ')
rep += self.rev_template.pretty_print(with_name=False)
rep += '\n'
rep += hr(' forward primers ')
rep += self._rep_primers(
self.fwd_primers,
lambda p: p.print_most_stable(include_fwd_3_mismatch))
rep += '\n'
rep += hr(' reverse primers ')
rep += self._rep_primers(
self.rev_primers,
lambda p: p.print_most_stable(include_fwd_3_mismatch))
return rep
def format_quantity_explanation(self):
expl_string = ''
expl_string += hr(' estimation of PCR products concentrations ')
expl_string += 'The value of the objective function of at the solution ' + \
'(the lower the better):\n %e\n' % \
self._max_objective_value
expl_string += wrap_text('This value shows "distance" to the solution of '
'the system of equilibrium equations which were used '
'to calculate concentrations of PCR products.\n\n')
expl_string += wrap_text(('Products with concentration less than %.2f%% '
'of the concentration of the most abundant '
'product or less than initial DNA concentration '
'are not shown.'
'\n\n') % (self._min_quantity_factor*100))
expl_string += wrap_text('Boundaries of a product and it\'s length do '
'not include primers.\n\n')
expl_string += '\n'
return expl_string
def write_products_report(self):
if not self._have_results: return
#open report file
ipcr_products = self._open_report('iPCR products',
self._PCR_products_filename)
ipcr_products.write(time_hr())
if self._PCR_Simulation:
ipcr_products.write(self._PCR_Simulation.format_products_report())
else:
ipcr_products.write(
hr(' No PCR products have been found ', symbol='!'))
ipcr_products.close()
print '\nThe list of PCR products was written to:\n %s' % self._PCR_products_filename
self._add_report('iPCR products', self._PCR_products_filename)
#end def
#end class
def write_report(self):
if not self._have_results: return
#open report file
report = self._open_report(self._PCR_report_suffix, self._PCR_report_filename)
if not report: return
#header
report.write(time_hr())
report.write(self._format_header())
#if no PCR products have been found
if not self._have_results:
report.write(hr(' No PCR products have been found ', symbol='!'))
report.close()
return
#report body
report.write(self._format_report_body())
report.close()
print '\n%s report was written to:\n %s' % (self._PCR_report_suffix,
self._PCR_report_filename)
report_name = self._PCR_report_suffix.replace('_', ' ').replace('-', ' ')
self._add_report(report_name, self._PCR_report_filename)
def format_quantity_explanation(self):
expl_string = ''
expl_string += hr(' estimation of PCR products concentrations ')
expl_string += 'The value of the objective function of at the solution ' + \
'(the lower the better):\n %e\n' % \
self._max_objective_value
expl_string += wrap_text(
'This value shows "distance" to the solution of '
'the system of equilibrium equations which were used '
'to calculate concentrations of PCR products.\n\n')
expl_string += wrap_text(
('Products with concentration less than %.2f%% '
'of the concentration of the most abundant '
'product or less than initial DNA concentration '
'are not shown.'
'\n\n') % (self._min_quantity_factor * 100))
expl_string += wrap_text('Boundaries of a product and it\'s length do '
'not include primers.\n\n')
expl_string += '\n'
return expl_string
def write_report(self):
if not self._have_results: return
#open report file
report = self._open_report(self._PCR_report_suffix,
self._PCR_report_filename)
if not report: return
#header
report.write(time_hr())
report.write(self._format_header())
#if no PCR products have been found
if not self._have_results:
report.write(hr(' No PCR products have been found ', symbol='!'))
report.close()
return
#report body
report.write(self._format_report_body())
report.close()
print '\n%s report was written to:\n %s' % (
self._PCR_report_suffix, self._PCR_report_filename)
report_name = self._PCR_report_suffix.replace('_',
' ').replace('-', ' ')
self._add_report(report_name, self._PCR_report_filename)
def write_hits_report(self):
if not self._have_blast_results: return
blast_report = self._open_report('blast hits report', self._hits_report_filename)
if not blast_report: return
#header
blast_report.write(time_hr())
blast_report.write(wrap_text('All hits are filtered by dG of the annealing '
'of alignments and, if --no-exonuclease '
'option was provided, hits with mismatches on '
"3'-end are ignored.\n"))
blast_report.write('\n')
#filter parameters
blast_report.write(hr(' filtration parameters '))
if self._with_exonuclease:
blast_report.write("DNA polymerase HAS 3'-5'-exonuclease activity\n")
else: blast_report.write("DNA polymerase doesn't have 3'-5'-exonuclease activity\n")
blast_report.write('Maximum dG of an alignment: %.2f kcal/mol\n' % max_dimer_dG)
blast_report.write('\n')
blast_report.write(hr(''))
blast_report.write('\n\n')
#print records
for r, blast_record in enumerate(self._blast_results):
num_hits = len(blast_record.alignments)
blast_report.write(hr(' query ID: %s ' % blast_record.query, symbol='#'))
#filter hits by alignments and format report text for each hit
hits = []
for h in xrange(num_hits):
hit = blast_record.alignments[h]
desc = blast_record.descriptions[h]
#check and format hsps
hsps = []
for hsp in hit.hsps:
hsp_duplex = self._duplex_from_hsp(hsp)
#check if any stable dimers are formed by this duplex
if not hsp_duplex: continue
#check 3' mismatch
if not self._with_exonuclease \
and not hsp_duplex.have_3_matches: continue
#get primer concentration
for primer in self._primers:
if primer.has_subsequence(hsp_duplex.fwd_seq):
hsp_primer_concentration = primer.concentration
break
#format hsps representation
hsp_text = ('score: %d; bits: %d; E-value: %.2e;\n\n'
% (hsp.score, hsp.bits, hsp.expect))
hsp_text += hsp_duplex.print_most_stable(include_fwd_3_mismatch=self._with_exonuclease)
hsp_text += 'Conversion degree = %.2f%%\n\n' \
% (tdf.primer_DNA_conversion_degree(hsp_primer_concentration, hsp_duplex.K)*100)
hsp_text += 'Template strand: '
if hsp.frame[1] == 1:
hsp_text += 'antisense\n'
hsp_text += 'Position on template: %d ==> %d\n' \
% (hsp.sbjct_start, hsp.sbjct_end)
elif hsp.frame[1] == -1:
hsp_text += 'sense\n'
hsp_text += 'Position on template: %d <== %d\n' \
% (hsp.sbjct_start, hsp.sbjct_end)
hsp_text += hr('', '.')
hsps.append((hsp_duplex.dG, hsp_text))
#no need to include weak hits to the report
if not hsps: continue
#sort hsps by minimum dG
hsps.sort(key=lambda(x): x[0])
#format hit
hit_str = wrap_text(hit.title)+'\n'
hit_str += 'Length: %d\n' % hit.length
hit_str += 'Max bits: %d\n' % desc.bits
hit_str += 'Alignments: %d\n' % len(hit.hsps)
hit_str += '\n'
hit_str += hr(' %d alignments after filtration ' % len(hsps))
hit_str += ''.join(_hsp[1] for _hsp in hsps)[:-1]
hits.append((hsps[0][0], desc.title, desc.score, desc.bits, desc.e, len(hsps), hit_str))
if not hits:
blast_report.write(wrap_text('All hits were filtered out.\n'))
#write report to the file
else:
#print the short list of all hits
num_hits = len(hits)
num_hits_len = len(str(num_hits))
#sort hits by minimum dG
hits.sort(key=lambda(x): x[0])
#print header
blast_report.write(hr(' %d hits ' % num_hits, symbol='#'))
for h, hit in enumerate(hits):
spacer = ' '*(num_hits_len-len(str(h)))
blast_report.write(wrap_text('%d.%s %s\n'
% (h+1, spacer,
(hit[1].split('|')[-1]).strip())))
blast_report.write(('%s min dG: %.2f; score: %d; bits: %d; '
'E-value: %.2e; alignments: %d\n\n')
% (' '*num_hits_len, hit[0], hit[2],
hit[3], hit[4], hit[5]))
blast_report.write('\n')
#print each formatted hit
for h, hit in enumerate(hits):
blast_report.write(hr(' Hit #%d ' % (h+1), symbol='='))
blast_report.write(hit[6])
blast_report.write(hr('', symbol='='))
if h < num_hits-1: blast_report.write('\n\n')
blast_report.write(hr('', symbol='#'))
if r < len(self._blast_results)-1: blast_report.write('\n\n')
blast_report.close()
print '\nTop hits with top HSPs from BLAST results were written to:\n ' + \
self._hits_report_filename
self._add_report('BLAST hits', self._hits_report_filename)