def generate_contigs_two_sizes(genome, small_size, large_size, min_distance,
max_distance, distr_weight_large_ctgs):
position = 0
index = 0
while True:
r = random.uniform(0, 1)
if r < distr_weight_large_ctgs:
contig_len = large_size
else:
contig_len = small_size
position += random.randrange(min_distance, max_distance)
if position + contig_len > len(genome):
break
rev_comp = random.randrange(0, 2)
if rev_comp:
yield '>c{0},pos:{1}-{2},rc:1\n{3}\n'.format(
index, position, position + contig_len,
reverse_complement(genome[position:position + contig_len]))
else:
yield '>c{0},pos:{1}-{2},rc:0\n{3}\n'.format(
index, position, position + contig_len,
genome[position:position + contig_len])
index += 1
position += contig_len
def generate(self,reference_accession, reference_sequence, read_index):
if self.distribution == 'normal':
self.fragment_length = int(random.gauss(self.mean,self.sigma))
elif self.distribution == 'uniform':
self.fragment_length = int(random.uniform(self.min_size,self.max_size))
if self.fragment_length >= len(reference_sequence):
raise Exception("To short reference sequence length for \
simulated read. \nRead fragment: {0}\nTranscript \
length:{1}".format(self.fragment_length,len(reference_sequence)))
self.start_pos = random.randrange(len(reference_sequence) - self.fragment_length)
self.read1 = reverse_complement(reference_sequence[self.start_pos : self.start_pos + self.read_length])
self.read2 = reference_sequence[self.start_pos + self.fragment_length - self.read_length : self.start_pos+self.fragment_length]
self.reference_accession = reference_accession
self.read_index = read_index
def generate_contigs(genome,min_c_len,max_c_len,min_distance,max_distance):
position = 0
index = 0
while True:
contig_len = random.randrange(min_c_len,max_c_len)
position += random.randrange(min_distance,max_distance)
if position + contig_len > len(genome):
break
rev_comp = random.randrange(0,2)
if rev_comp:
yield '>c{0},pos:{1}-{2},rc:1\n{3}\n'.format(index,
position,position+contig_len, reverse_complement( genome[position:position+contig_len]))
else:
yield '>c{0},pos:{1}-{2},rc:0\n{3}\n'.format(index,
position,position+contig_len, genome[position:position+contig_len])
index += 1
position += contig_len
def generate_contigs(genome, min_c_len, max_c_len, min_distance, max_distance):
position = 0
index = 0
while True:
contig_len = random.randrange(min_c_len, max_c_len)
position += random.randrange(min_distance, max_distance)
if position + contig_len > len(genome):
break
rev_comp = random.randrange(0, 2)
if rev_comp:
yield '>c{0},pos:{1}-{2},rc:1\n{3}\n'.format(
index, position, position + contig_len,
reverse_complement(genome[position:position + contig_len]))
else:
yield '>c{0},pos:{1}-{2},rc:0\n{3}\n'.format(
index, position, position + contig_len,
genome[position:position + contig_len])
index += 1
position += contig_len
def generate_contigs_two_sizes(genome,small_size,large_size,min_distance,max_distance,distr_weight_large_ctgs):
position = 0
index = 0
while True:
r = random.uniform(0,1)
if r < distr_weight_large_ctgs:
contig_len = large_size
else:
contig_len = small_size
position += random.randrange(min_distance,max_distance)
if position + contig_len > len(genome):
break
rev_comp = random.randrange(0,2)
if rev_comp:
yield '>c{0},pos:{1}-{2},rc:1\n{3}\n'.format(index,
position,position+contig_len, reverse_complement( genome[position:position+contig_len]))
else:
yield '>c{0},pos:{1}-{2},rc:0\n{3}\n'.format(index,
position,position+contig_len, genome[position:position+contig_len])
index += 1
position += contig_len
def get_sequence(self):
"""
Generates an Transcript from a genome
Returns:
An exon
"""
nr_exons = random.randrange(1,5)
self.intron_length = [random.randrange(self.min_intron_size,self.max_intron_size) for i in range(nr_exons)]
self.exon_lengths = [random.randrange(self.min_exon_size,self.max_exon_size) for i in range(nr_exons)]
self.reverse_complement = random.randrange(2)
if sum(self.intron_length) + sum(self.exon_lengths) >= len(self.genome_strand):
self.get_sequence()
if self.reverse_complement:
self.start_position = random.randrange(sum(self.intron_length) + sum(self.exon_lengths),len(self.genome_strand))
else:
self.start_position = random.randrange(0,len(self.genome_strand)-sum(self.intron_length)-sum(self.exon_lengths))
position = self.start_position
self.positions = []
self.sequence = ''
for e_len,i_len in zip(self.exon_lengths,self.intron_length):
if self.reverse_complement:
self.sequence += reverse_complement( self.genome_strand[position-e_len:position])
self.positions.append((position-e_len,position))
position -= e_len + i_len
else:
self.sequence += self.genome_strand[position:position+e_len]
self.positions.append((position,position+e_len))
position += e_len + i_len
self.accession = '>spliced_variant{0},rc={1}'.format(self.positions,self.reverse_complement)
