def __init__(self, abort_event, *args, **kwargs):
MixtureFactory.__init__(self, abort_event, *args, **kwargs)
MultiprocessingBase.__init__(self, abort_event)
self._searcher = SearchEngine(self._abort_event)
self._p_weights = [p.num_components for p in self._primers]
self._pw_sum = sum(self._p_weights)
self._num_p = len(self._primers)
def __init__(self, abort_event, *args, **kwargs):
MixtureFactory.__init__(self, abort_event, *args, **kwargs)
MultiprocessingBase.__init__(self, abort_event)
self._searcher = SearchEngine(self._abort_event)
self._p_weights = [p.num_components for p in self._primers]
self._pw_sum = sum(self._p_weights)
self._num_p = len(self._primers)
def __init__(self, abort_event, reactions, concentrations, precision = 1e-10):
MultiprocessingBase.__init__(self, abort_event)
EquilibriumBase.__init__(self, reactions, concentrations, precision)
#input parameters
self.reactions = reactions
self.concentrations = concentrations
#group reactions by their connected graph components
self._reactions_groups = self._group_reactions()
def __init__(self,
abort_event,
polymerase,
with_exonuclease,
num_cycles,
):
MultiprocessingBase.__init__(self, abort_event)
self._polymerase = polymerase
self._with_exonuclease = with_exonuclease
self._num_cycles = num_cycles
self._PCR_P = deepcopy(tdf.PCR_P)
def __init__(
self,
abort_event,
polymerase,
with_exonuclease,
num_cycles,
):
MultiprocessingBase.__init__(self, abort_event)
self._polymerase = polymerase
self._with_exonuclease = with_exonuclease
self._num_cycles = num_cycles
self._PCR_P = deepcopy(tdf.PCR_P)
def __init__(self,
abort_event,
reactions,
concentrations,
precision=1e-10):
MultiprocessingBase.__init__(self, abort_event)
EquilibriumBase.__init__(self, reactions, concentrations, precision)
#input parameters
self.reactions = reactions
self.concentrations = concentrations
#group reactions by their connected graph components
self._reactions_groups = self._group_reactions()
def __init__(self, abort_event, *args, **kwargs):
iPCR_Interface.__init__(self, abort_event, *args, **kwargs)
MultiprocessingBase.__init__(self, abort_event)
self._blast_results = None
self._bounds = None
self._query = None
#PCR parameters
self._PCR_Simulations = dict()
#query_id use hash of primers instead of all-config hash as in job_id
self._primers_hash = (hash(tuple(self._primers)) & 0xFFFFFFF)
self._query_id = re.split('_[0-9]+\Z', self._job_id)[0]
self._query_id += '_%s' % str(self._primers_hash)
#results
self._results_filename = self._query_id+'-blast.xml'
self._query_filename = self._query_id+'-blast.cfg'
#reports
self._hits_report_filename = '%s-%s-hits.txt' % (self._job_id,
self._PCR_report_suffix.rstrip('-PCR'))
#flags
self._have_blast_results = False
self._have_saved_results = False
def __init__(self, abort_event, job_id, primers):
#initial check
try:
if len(primers) == 0:
raise ValueError('AllSecStructures: no primers given.')
except TypeError:
raise TypeError(('AllSecStructures: primers should be an iterable. '
'Given %s instead') % str(primers))
ReporterInterface.__init__(self)
MultiprocessingBase.__init__(self, abort_event)
#all primers list and concentrations dict
self._primers = primers
self._all_primers = []
self._concentrations = dict()
self._reactions = dict()
self._self = []
self._cross = []
self._all_structures = dict()
self._equilibrium_concentrations = None
#reports
self._job_id = job_id
self._short_structs_filename = job_id+'-structures-short.txt'
self._full_structs_filename = job_id+'-structures-full.txt'
def __init__(self, abort_event, job_id, primers):
#initial check
try:
if len(primers) == 0:
raise ValueError('AllSecStructures: no primers given.')
except TypeError:
raise TypeError(
('AllSecStructures: primers should be an iterable. '
'Given %s instead') % str(primers))
ReporterInterface.__init__(self)
MultiprocessingBase.__init__(self, abort_event)
#all primers list and concentrations dict
self._primers = primers
self._all_primers = []
self._concentrations = dict()
self._reactions = dict()
self._self = []
self._cross = []
self._all_structures = dict()
self._equilibrium_concentrations = None
#reports
self._job_id = job_id
self._short_structs_filename = job_id + '-structures-short.txt'
self._full_structs_filename = job_id + '-structures-full.txt'
def __init__(self, abort_event):
MultiprocessingBase.__init__(self, abort_event)
self._a = 5
class SearchEngine(MultiprocessingBase):
'''Fast search of a pattern sequence in a given set of template sequences
with parallelization using multiprocessing.'''
_w_3_0 = 1 #trivial 3d root of unity
_w_3_1 = (-1/2.0+np.sqrt(3)/2.0j) #3d root of unity in a power of 1
_w_3_2 = (-1/2.0-np.sqrt(3)/2.0j) #3d root of unity in a power of 2
_unambiguous = array('b','ATGC') #ATGC characters as byte array
#alphabet mappings to the 3d roots of unity for templates and patterns
_T_AT_mapping = tuple(zip(_unambiguous, (_w_3_1,_w_3_2,0,0)))
_T_GC_mapping = tuple(zip(_unambiguous, (0,0,_w_3_1,_w_3_2)))
_P_AT_mapping = {'A':_w_3_2,
'T':_w_3_1,
'G':_w_3_0,
'C':_w_3_0,
'R':_w_3_2,
'Y':_w_3_1,
'S':_w_3_0,
'W':_w_3_2+_w_3_1,
'K':_w_3_1,
'M':_w_3_2,
'B':_w_3_1,
'D':_w_3_2+_w_3_1,
'H':_w_3_2+_w_3_1,
'V':_w_3_2,
'N':_w_3_2+_w_3_1}
_P_GC_mapping = {'A':_w_3_0,
'T':_w_3_0,
'G':_w_3_2,
'C':_w_3_1,
'R':_w_3_2,
'Y':_w_3_1,
'S':_w_3_2+_w_3_1,
'W':_w_3_0,
'K':_w_3_2,
'M':_w_3_1,
'B':_w_3_2+_w_3_1,
'D':_w_3_2,
'H':_w_3_1,
'V':_w_3_2+_w_3_1,
'N':_w_3_2+_w_3_1}
#template sequences grater than this value will be split into slices of
#approximately that size
_max_chunk_size = 2**12
###########################################################################
@classmethod
def set_max_chunk(cls, chunk_size):
cls._max_chunk_size = chunk_size
@classmethod
def _map_pattern(cls, pattern, map_len):
'''Map pattern sequence to an alphabet of 3d roots of unity.'''
#this naive algorithm works ~5 times faster
#than the one used for template mapping due to short length of patterns
AT_map = np.zeros(map_len, dtype=complex)
GC_map = np.zeros(map_len, dtype=complex)
for i,letter in enumerate(pattern):
AT_map[i] = cls._P_AT_mapping[letter]
GC_map[i] = cls._P_GC_mapping[letter]
return (AT_map, GC_map)
#end def
@staticmethod
def _compile_duplexes_for_position(position, template, primer,
t_len, p_len, reverse):
'''Given a template strand, a primer and a location where the
primer matches the template, return a list of Duplexes formed by
unambiguous components of the primer'''
duplexes = []
for var in primer.seq_records:
dup = Duplex(str(var.seq), str(template[position:position+p_len]), name=var.id, revcomp=True)
if dup: duplexes.append(dup)
if reverse: return t_len+1-(position+p_len), tuple(duplexes)
else: return position+p_len, tuple(duplexes)
#end def
_compile_duplexes_mapper = staticmethod(MultiprocessingBase.data_mapper(_compile_duplexes_for_position.__func__))
@staticmethod
@MultiprocessingBase.results_assembler
def _duplexes_assembler(index, result, output):
if result[1]: output.append(result)
#end def
def compile_duplexes_mp(self, counter,
fwd_seq, rev_seq, primer,
t_len, p_len,
fwd_matches, rev_matches, num_jobs=None):
'''Compile duplexes for both strands of a template in parallel'''
if not len(fwd_matches)+len(rev_matches): return None
counter.set_subwork(2, map(len, (fwd_matches, rev_matches)))
if len(fwd_matches): counter[0].set_work(len(fwd_matches))
if len(rev_matches): counter[1].set_work(len(rev_matches))
#prepare and start two sets of jobs
with tdf.AcquireParameters():
fwd_results = []; rev_results = []
fwd_work = self.Work(timeout=0.1, counter=counter[0])
fwd_work.start_work(self._compile_duplexes_mapper,
fwd_matches, num_jobs,
fwd_seq, primer, t_len, p_len, False)
fwd_work.assemble(self._duplexes_assembler, fwd_results)
rev_work = self.Work(timeout=0.1, counter=counter[1])
rev_work.start_work(self._compile_duplexes_mapper,
rev_matches, num_jobs,
rev_seq, primer, t_len, p_len, True)
rev_work.assemble(self._duplexes_assembler, rev_results)
if not self.wait(fwd_work, rev_work): return None
if self.aborted() or not fwd_results and not rev_results: return None
#sort duplexes by position and return them
fwd_results.sort(key=lambda x: x[0])
rev_results.sort(key=lambda x: x[0])
return fwd_results,rev_results
#end def
def compile_duplexes(self, counter,
fwd_seq, rev_seq, primer,
t_len, p_len,
fwd_matches, rev_matches):
'''Compile duplexes for both strands of a template'''
if not len(fwd_matches)+len(rev_matches): return None
counter.set_work(len(fwd_matches)+len(rev_matches))
with tdf.AcquireParameters():
fwd_results = []
for pos in fwd_matches:
if self.aborted(): break
duplexes = self._compile_duplexes_for_position(pos, fwd_seq, primer,
t_len, p_len, reverse=False)
if duplexes[1]: fwd_results.append(duplexes)
counter.count()
rev_results = []
for pos in rev_matches:
if self.aborted(): break
duplexes = self._compile_duplexes_for_position(pos, rev_seq, primer,
t_len, p_len, reverse=True)
if duplexes[1]: rev_results.append(duplexes)
counter.count()
if self.aborted(): return None
if not fwd_results: fwd_results = None
if not rev_results: rev_results = None
if not fwd_results and not rev_results: return None
return fwd_results, rev_results
#end def
@classmethod
def _find_in_chunk(cls, t_chunk, p_fft, correction, c_size, c_stride):
'''Find number of matches of pattern at each position in a given
chunk of a template.
Pattern is given as a polynomial evaluated at n-th roots of unity
using fft.
map_len is a length of a map of template to the alphabet of 3-d roots
of unity chunk to build. It's a power of 2 integer for fft to work fast.
c_stride -- a part of chunk for which matches are calculated
(it is less than map_len, so chunks overlap each other)'''
t_AT_map = np.fromiter(array('b',t_chunk), dtype=complex)
t_AT_map.resize(c_size)
t_GC_map = t_AT_map.copy()
for k,v in cls._T_AT_mapping: t_AT_map[t_AT_map == k] = v
for k,v in cls._T_GC_mapping: t_GC_map[t_GC_map == k] = v
AT_score = ifft(fft(t_AT_map[::-1])*p_fft[0])[::-1][:c_stride]
GC_score = ifft(fft(t_GC_map[::-1])*p_fft[1])[::-1][:c_stride]
score = AT_score.real + GC_score.real
score = (score*(2.0/3.0) + correction)
return score
#end def
@classmethod
def _calculate_chunk_size(cls, t_len, p_len):
rem = lambda(c): ((t_len/(c-p_len))*(c-p_len)+c-t_len)
if t_len <= cls._max_chunk_size:
chunk = 2**int(np.ceil(np.log2(t_len)))
if chunk % t_len == 0: return chunk
else: chunk = cls._max_chunk_size
r = rem(chunk)
min_chunk = 2**int(np.ceil(np.log2(2*p_len)))
max_rem = chunk/2+1
while r > max_rem \
and chunk > min_chunk:
chunk /= 2
r = rem(chunk)
return max(chunk, min_chunk)
#end def
@staticmethod
def _check_length_inequality(t_len, p_len):
if t_len < p_len or p_len == 0:
raise ValueError('SearchEngine._find: template sequence should be '
'longer or equal to primer sequence and both '
'should be grater than zero.')
#end def
@staticmethod
def mp_better(t_len):
#based on computation time statistics
return cpu_count > 1 and t_len > 25000
#end def
@staticmethod
def _optimal_slices(t_len, p_len):
#linear regression of measured computing time with respect to
#number of slices and template length
linear = max(cpu_count, int(t_len*1.75e-5 + 1.75))
return min(60, linear, t_len/p_len)
#end def
@staticmethod
@MultiprocessingBase.worker
def _find_in_slice(abort_e, _id, start, end, fwd_seq, rev_seq,
p_fft, correction, s_stride, c_size, c_stride):
fwd_score = []
rev_score = []
pos = start
while pos < end:
if aborted(abort_e): return None
front = min(end, pos+c_size)
fwd_score.append(SearchEngine._find_in_chunk(fwd_seq[pos:front],
p_fft, correction,
c_size, c_stride))
rev_score.append(SearchEngine._find_in_chunk(rev_seq[pos:front],
p_fft, correction,
c_size, c_stride))
pos += c_stride
return (start,
np.concatenate(fwd_score)[:s_stride],
np.concatenate(rev_score)[:s_stride])
#end def
def _find_mp(self, counter, template, primer, t_len, p_len, mismatches):
'''Find all occurrences of a primer sequence in both strands of a
template sequence with at most k mismatches. Multiprocessing version.'''
slice_size = t_len/self._optimal_slices(t_len, p_len)+p_len+1
slice_stride = slice_size-p_len
chunk_size = self._calculate_chunk_size(slice_size, p_len)
chunk_stride = chunk_size-p_len
p_maps = self._map_pattern(str(primer.master_sequence.seq), chunk_size)
p_fft = (fft(p_maps[0]),fft(p_maps[1]))
fwd_seq = str(template.seq)
rev_seq = reverse_complement(fwd_seq)
correction = np.ndarray(chunk_stride); correction.fill(p_len/3.0)
#start find_in_slice jobs
counter.set_work(t_len/slice_stride+1)
pos = 0; work = self.Work(counter=counter)
while pos < t_len and not self.aborted():
front = min(t_len, pos+slice_size)
queue = self._Queue()
job = self._Process(target=self._find_in_slice,
args=(queue, self._abort_event,
len(work),
pos, front,
fwd_seq, rev_seq,
p_fft, correction,
slice_stride, chunk_size, chunk_stride))
job.daemon = 1
job.start()
work.add_job(job, queue)
pos += slice_stride
work.start_jobs()
#if scores arrays are allocated beforehand, the memory
#is returned upon deletion
scores_len = slice_stride*len(work)
scores = [np.zeros(scores_len), np.zeros(scores_len)]
def assembler(out, scores):
if out:
scores[0][out[0]:out[0]+slice_stride] = out[1]
scores[1][out[0]:out[0]+slice_stride] = out[2]
work.assemble(assembler, scores)
if not work.wait() or self.aborted(): return None
#compute match indices
matches = max(1, p_len - mismatches)-0.5
fwd_matches = np.where(scores[0][:t_len-p_len+1] >= matches)[0]
rev_matches = np.where(scores[1][:t_len-p_len+1] >= matches)[0]
return fwd_seq, rev_seq, primer, t_len, p_len, fwd_matches, rev_matches
#end def
def _find(self, counter, template, primer, t_len, p_len, mismatches):
'''Find all occurrences of a primer sequence in both strands of a
template sequence with at most k mismatches.'''
chunk_size = self._calculate_chunk_size(t_len, p_len)
chunk_stride = chunk_size-p_len
p_maps = self._map_pattern(str(primer.master_sequence.seq), chunk_size)
p_fft = (fft(p_maps[0]),fft(p_maps[1]))
fwd_seq = str(template.seq)
rev_seq = reverse_complement(fwd_seq)
correction = np.ndarray(chunk_stride); correction.fill(p_len/3.0)
fwd_score = np.zeros(t_len+chunk_stride)
rev_score = np.zeros(t_len+chunk_stride)
#_find in chunks of a template, which is faster due to lower cost of memory allocation
pos = 0; counter.set_work(chunk_stride*(t_len/chunk_stride+1))
while pos < t_len and not self.aborted():
front = min(t_len, pos+chunk_size)
fwd_score[pos:pos+chunk_stride] = self._find_in_chunk(fwd_seq[pos:front],
p_fft, correction,
chunk_size, chunk_stride)
rev_score[pos:pos+chunk_stride] = self._find_in_chunk(rev_seq[pos:front],
p_fft, correction,
chunk_size, chunk_stride)
counter.count(chunk_stride)
pos += chunk_stride
#if search was aborted, return empty results
if self.aborted(): return None
#match indexes
matches = max(1, p_len - mismatches)-0.5
fwd_matches = np.where(fwd_score[:t_len-p_len+1] >= matches)[0]; del fwd_score
rev_matches = np.where(rev_score[:t_len-p_len+1] >= matches)[0]; del rev_score
return fwd_seq, rev_seq, primer, t_len, p_len, fwd_matches, rev_matches
#end def
def find_matches(self, counter, template, primer, mismatches):
'''Find all occurrences of a primer sequence in both strands of a
template sequence with at most k mismatches. This method uses
multiprocessing to speedup the search process. Use it to perform
search in a long sequence.'''
p_len,t_len = len(primer),len(template)
self._check_length_inequality(t_len, p_len)
if self.mp_better(t_len): find = self._find_mp
else: find = self._find
return find(counter, template, primer, t_len, p_len, mismatches)
#end def
def find(self, counter, template, primer, mismatches):
'''Find occurrences of a degenerate primer in a template sequence.
Return positions and Duplexes formed. This method uses
multiprocessing to speedup the search process. Use it to perform
search in a long sequence.'''
t_len = len(template)
counter.set_subwork(2, (t_len, t_len*primer.num_components))
matches = self.find_matches(counter[0], template, primer, mismatches)
if matches is None: return None
duplexes = self.compile_duplexes_mp(counter[1], *matches)
return to_shelf(duplexes) if duplexes else None
#end def
@MultiprocessingBase.data_mapper_method
def _batch_find(self, template, primer, p_len, mismatches):
matches = self._find(WorkCounter(), template, primer, len(template), p_len, mismatches)
if matches is None: return None
duplexes = self.compile_duplexes(WorkCounter(), *matches)
return (template.id, to_shelf(duplexes)) if duplexes else None
#end def
def batch_find(self, counter, templates, primer, mismatches, **kwargs):
'''Find occurrences of a degenerate primer in each of the provided
templates. Return dictionary of results using template IDs as keys.
It uses multiprocessing to parallelize searches, each of which does
not use parallelization. Use it to search in many short sequences.'''
work = self.Work(0.1, counter=counter)
work.start_work(self._batch_find, templates, None,
primer, len(primer), mismatches, **kwargs)
@MultiprocessingBase.results_assembler
def assembler(index, result, results):
if result: results[result[0]] = result[1]
results = {}
work.assemble(assembler, results)
if not work.wait(): return None
return results
def __init__(self, abort_event):
MultiprocessingBase.__init__(self, abort_event)
self._a = 5
