def per_hit_header(self, hit):
if not self._nonzero:
return '\nNo PCR products have been found.\n'
header_string = ''
header_string += 'Reaction ended in: %d cycles.\n' \
% self._reaction_ends[hit]['cycles']
header_string += 'C(dNTP) after reaction: ~%s\n' \
% tdf.format_concentration(self._reaction_ends[hit]['dNTP'])
if self._reaction_ends[hit]['cycles'] < self._num_cycles:
if self._reaction_ends[hit]['dNTP'] == 0:
header_string += 'dNTP have been depleted.\n'
else:
header_string += 'Primers have been depleted.\n'
if self._reaction_ends[hit]['poly']:
header_string += wrap_text('Polymerase activity was '
'insufficient in these cycles:\n')
shortage_string = ''
for shortage_period in self._reaction_ends[hit]['poly']:
if shortage_string: shortage_string += ', '
if shortage_period[0] == shortage_period[1]:
shortage_string += str(shortage_period[0])
else:
shortage_string += '%d-%d' % tuple(shortage_period)
header_string += wrap_text(shortage_string + '\n')
header_string += '\n'
return header_string
def per_hit_header(self, hit):
if not self._nonzero:
return '\nNo PCR products have been found.\n'
header_string = ''
header_string += 'Reaction ended in: %d cycles.\n' \
% self._reaction_ends[hit]['cycles']
header_string += 'C(dNTP) after reaction: ~%s\n' \
% tdf.format_concentration(self._reaction_ends[hit]['dNTP'])
if self._reaction_ends[hit]['cycles'] < self._num_cycles:
if self._reaction_ends[hit]['dNTP'] == 0:
header_string += 'dNTP have been depleted.\n'
else:
header_string += 'Primers have been depleted.\n'
if self._reaction_ends[hit]['poly']:
header_string += wrap_text('Polymerase activity was '
'insufficient in these cycles:\n')
shortage_string = ''
for shortage_period in self._reaction_ends[hit]['poly']:
if shortage_string: shortage_string += ', '
if shortage_period[0] == shortage_period[1]:
shortage_string += str(shortage_period[0])
else:
shortage_string += '%d-%d' % tuple(shortage_period)
header_string += wrap_text(shortage_string + '\n')
header_string += '\n'
return header_string
def _format_header(self):
header = ''
if self._optimized:
header += 'Optimization was successful.\n'
header += wrap_text('Results of PCR simulation with optimized values of the parameters '
'are given below.\n\n')
else:
header += 'Optimization was unsuccessful: %s\n' % self._exit_status
header += wrap_text('Results of PCR simulation with the values of the parameters '
'from the last iteration of the optimization are given below. These '
'values, nevertheless, usually give better simulation results than '
'the initial ones.\n\n')
header += iPCR_Base._format_header(self)
header += self._PCR_Simulation.format_report_header()
return header
def format_products_report(self):
header = wrap_text('For each target sequence a list of possible '
'PCR products which were predicted by the '
'simulation is given. '
'Information about each product includes:\n'
'-start and end positions on a target sequence.\n'
' *the first nucleotide of a sequence is at the position 1\n'
' *primers are not included, so their 3\'-ends are located at '
'start-1 and end+1 positions.\n'
'-length in base pairs.\n'
' *the length too do not include primers.\n'
'-concentration which was calculated during PCR simulation.\n'
'-number of PCR cycles during which the product has been generated.\n'
' *if this number is lower than the number of simulated reaction cycles '
'it means that primers producing the product were depleted.\n'
'-lists of forward and reverse primers which produced the product'
'\n\n\n')
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
prod_strings = self.parallelize_work(1, worker, self._products.keys())
if not prod_strings:
return 'Failed to compile products report. See the log for errors.'
return header+''.join(prod_strings)+'\n'
#end class
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 _format_header(self):
header = ''
if self._optimized:
header += 'Optimization was successful.\n'
header += wrap_text(
'Results of PCR simulation with optimized values of the parameters '
'are given below.\n\n')
else:
header += 'Optimization was unsuccessful: %s\n' % self._exit_status
header += wrap_text(
'Results of PCR simulation with the values of the parameters '
'from the last iteration of the optimization are given below. These '
'values, nevertheless, usually give better simulation results than '
'the initial ones.\n\n')
header += iPCR_Base._format_header(self)
header += self._PCR_Simulation.format_report_header()
return header
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 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 _format_header(self):
header = wrap_text('All possible PCR products are '
'filtered by amplicon size.\n'
'If --no-exonuclease option was '
'provided, products which may be formed by '
'primers with '
"mismatches on 3'-end are ignored.\n"
'Quantities of the remaining products '
'are estimated using equilibrium equations '
'and current PCR parameters.\n\n')
header += iPCR_Base._format_header(self)
header += self._PCR_Simulation.format_report_header()
return header
def _format_header(self):
header = wrap_text('All possible PCR products are '
'filtered by amplicon size.\n'
'If --no-exonuclease option was '
'provided, products which may be formed by '
'primers with '
"mismatches on 3'-end are ignored.\n"
'Quantities of the remaining products '
'are estimated using equilibrium equations '
'and current PCR parameters.\n\n')
header += iPCR_Base._format_header(self)
header += self._PCR_Simulation.format_report_header()
return header
def _format_header(self):
header = wrap_text('For each hit all alignments are sorted '
'into "forward" and "reverse" groups. '
'Pairs of forward and reverse '
'alignments comprise possible PCR products.\n'
'If --no-exonuclease option was '
'provided, alignments with mismatches on '
"3'-end are ignored.\n"
'Quantities of products are estimated '
'using equilibrium equations and '
'current PCR parameters.\n')
header += self._PCR_Simulations.values()[0].format_report_header()
header += self._PCR_Simulations.values()[0].format_quantity_explanation()
return header
def format_products_report(self):
header = wrap_text(
'For each target sequence a list of possible '
'PCR products which were predicted by the '
'simulation is given. '
'Information about each product includes:\n'
'-start and end positions on a target sequence.\n'
' *the first nucleotide of a sequence is at the position 1\n'
' *primers are not included, so their 3\'-ends are located at '
'start-1 and end+1 positions.\n'
'-length in base pairs.\n'
' *the length too do not include primers.\n'
'-concentration which was calculated during PCR simulation.\n'
'-number of PCR cycles during which the product has been generated.\n'
' *if this number is lower than the number of simulated reaction cycles '
'it means that primers producing the product were depleted.\n'
'-lists of forward and reverse primers which produced the product'
'\n\n\n')
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
prod_strings = self.parallelize_work(1, worker, self._products.keys())
if not prod_strings:
return 'Failed to compile products report. See the log for errors.'
return header + ''.join(prod_strings) + '\n'
#end class
def formatted_desc(self):
return wrap_text(self.desc.replace('%%', '%')).strip()
'''
Created on 2016-01-14
@author: Allis Tauri <*****@*****.**>
'''
import cProfile
from BioUtils.Tools.Text import wrap_text, line_by_line
if __name__ == '__main__':
txt = '''If true, TextWrapper attempts to detect sentence endings and ensure
that sentences are always separated by exactly two spaces. This is generally
desired for text in a monospaced font. However, the sentence detection
algorithm is imperfect: it assumes that a sentence ending consists of a
lowercase letter followed by one of '.', '!', or '?', possibly followed by
one of '"' or "'", followed by a space. One problem with this is algorithm
is that it is unable to detect the difference between “Dr.” in'''
print wrap_text(txt)
print '='*80
texts = ['asdfasd sreydstnsr mywyy eratg AG RADFG SDFGA lkjoiuguivuasdfhpwoiefjahgaiohghouygmuimjiuh',
'qasf; a[r uq[ewjrfasdhfuiah [WERJ AOSF BA;We werqt',
'wreyqeuqy a poiertqprohg aspoei toeaprt a']
widths = [20,30,30]
print line_by_line(texts, widths)
cProfile.run('''for i in xrange(10000):
wrap_text(txt)''',
'word_wrap.profile')
print 'Done'
'''
Created on 2016-01-14
@author: Allis Tauri <*****@*****.**>
'''
import cProfile
from BioUtils.Tools.Text import wrap_text, line_by_line
if __name__ == '__main__':
txt = '''If true, TextWrapper attempts to detect sentence endings and ensure
that sentences are always separated by exactly two spaces. This is generally
desired for text in a monospaced font. However, the sentence detection
algorithm is imperfect: it assumes that a sentence ending consists of a
lowercase letter followed by one of '.', '!', or '?', possibly followed by
one of '"' or "'", followed by a space. One problem with this is algorithm
is that it is unable to detect the difference between “Dr.” in'''
print wrap_text(txt)
print '=' * 80
texts = [
'asdfasd sreydstnsr mywyy eratg AG RADFG SDFGA lkjoiuguivuasdfhpwoiefjahgaiohghouygmuimjiuh',
'qasf; a[r uq[ewjrfasdhfuiah [WERJ AOSF BA;We werqt',
'wreyqeuqy a poiertqprohg aspoei toeaprt a'
]
widths = [20, 30, 30]
print line_by_line(texts, widths)
cProfile.run('''for i in xrange(10000):
wrap_text(txt)''', 'word_wrap.profile')
print 'Done'
def formatted_desc(self):
return wrap_text(self.desc.replace('%%', '%')).strip()
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)
