def test_single_contig_1(self):
contigs_1 = ['ATCGCTGATT']
reads_1 = {\
'ATCG':[[0,0,0.5]],'TCGC':[[0,1,0.5]],'CCCT':[[0,2,0.5]],'GCTG':[[0,3,0.5]],\
'TTCA':[[0,4,0.5]],'TGAT':[[0,5,0.5]],'GATT':[[0,6,0.5]]}
freq = cs.consensus_sequence(reads_1)
self.assertEqual(contigs_1, cs.compute_new_contigs(freq))
def test_single_contig_2(self):
contigs_2 = ['ATCGCTGATT', 'ATCCCTCATT', 'ATCGCTCATT', 'ATCCCTGATT']
reads_2 = {\
'ATCC':[[0,0,0.5]],'TCGC':[[0,1,0.5]],'CCCT':[[0,2,0.5]],'GCTC':[[0,3,0.5]],\
'TTCA':[[0,4,0.5]],'TGAT':[[0,5,0.5]],'GATT':[[0,6,0.5]]}
freq = cs.consensus_sequence(reads_2)
self.assertTrue(cs.compute_new_contigs(freq)[0] in contigs_2)
def test_multiple_contigs_1(self):
contigs_3 = ['ATCGCTGATT', 'TTTACGATGC']
reads_3 = {\
'ATCG':[[0,0,0.5]],'TCGC':[[0,1,0.5]],'CCCT':[[0,2,0.5]],'GCTG':[[0,3,0.5]],\
'TTCA':[[0,4,0.5]],'TGAT':[[0,5,0.5]],'GATT':[[0,6,0.5]],\
'TTAA':[[1,0,0.5]],'TTAC':[[1,1,0.5]],'TGCG':[[1,2,0.5]],'ACGA':[[1,3,0.5]],\
'AGAT':[[1,4,0.5]],'GTTG':[[1,5,0.5]],'AAGC':[[1,6,0.5]]}
freq = cs.consensus_sequence(reads_3)
self.assertEqual(contigs_3, cs.compute_new_contigs(freq))
def test_multiple_contigs_2(self):
contigs_4 = ['ATCGCTGATT','ATCCCTCATT','ATCGCTCATT','ATCCCTGATT',\
'TTTACGATGC','TTTAAGATGC']
reads_4 = {\
'ATCG':[[0,0,0.5]],'TCGC':[[0,1,0.5]],'CCCT':[[0,2,0.5]],'GCTG':[[0,3,0.5]],\
'TTCA':[[0,4,0.5]],'TGAT':[[0,5,0.5]],'GATT':[[0,6,0.5]],\
'TTAA':[[1,0,0.5],[1,1,0.5]],'TGCG':[[1,2,0.5]],'CCGA':[[1,3,0.5]],\
'AGAT':[[1,4,0.5]],'GTTG':[[1,5,0.5]],'AAGC':[[1,6,0.5]]}
freq = cs.consensus_sequence(reads_4)
self.assertTrue(cs.compute_new_contigs(freq)[0] in contigs_4\
and cs.compute_new_contigs(freq)[1] in contigs_4)
def test_single_contig_2(self):
contigs_2 = ["ATCGCTGATT", "ATCCCTCATT", "ATCGCTCATT", "ATCCCTGATT"]
reads_2 = {
"ATCC": [[0, 0, 0.5]],
"TCGC": [[0, 1, 0.5]],
"CCCT": [[0, 2, 0.5]],
"GCTC": [[0, 3, 0.5]],
"TTCA": [[0, 4, 0.5]],
"TGAT": [[0, 5, 0.5]],
"GATT": [[0, 6, 0.5]],
}
freq = cs.consensus_sequence(reads_2)
self.assertTrue(cs.compute_new_contigs(freq)[0] in contigs_2)
def test_single_contig_1(self):
contigs_1 = ["ATCGCTGATT"]
reads_1 = {
"ATCG": [[0, 0, 0.5]],
"TCGC": [[0, 1, 0.5]],
"CCCT": [[0, 2, 0.5]],
"GCTG": [[0, 3, 0.5]],
"TTCA": [[0, 4, 0.5]],
"TGAT": [[0, 5, 0.5]],
"GATT": [[0, 6, 0.5]],
}
freq = cs.consensus_sequence(reads_1)
self.assertEqual(contigs_1, cs.compute_new_contigs(freq))
def test_multiple_contigs_2(self):
contigs_4 = ["ATCGCTGATT", "ATCCCTCATT", "ATCGCTCATT", "ATCCCTGATT", "TTTACGATGC", "TTTAAGATGC"]
reads_4 = {
"ATCG": [[0, 0, 0.5]],
"TCGC": [[0, 1, 0.5]],
"CCCT": [[0, 2, 0.5]],
"GCTG": [[0, 3, 0.5]],
"TTCA": [[0, 4, 0.5]],
"TGAT": [[0, 5, 0.5]],
"GATT": [[0, 6, 0.5]],
"TTAA": [[1, 0, 0.5], [1, 1, 0.5]],
"TGCG": [[1, 2, 0.5]],
"CCGA": [[1, 3, 0.5]],
"AGAT": [[1, 4, 0.5]],
"GTTG": [[1, 5, 0.5]],
"AAGC": [[1, 6, 0.5]],
}
freq = cs.consensus_sequence(reads_4)
self.assertTrue(cs.compute_new_contigs(freq)[0] in contigs_4 and cs.compute_new_contigs(freq)[1] in contigs_4)
def test_multiple_contigs_1(self):
contigs_3 = ["ATCGCTGATT", "TTTACGATGC"]
reads_3 = {
"ATCG": [[0, 0, 0.5]],
"TCGC": [[0, 1, 0.5]],
"CCCT": [[0, 2, 0.5]],
"GCTG": [[0, 3, 0.5]],
"TTCA": [[0, 4, 0.5]],
"TGAT": [[0, 5, 0.5]],
"GATT": [[0, 6, 0.5]],
"TTAA": [[1, 0, 0.5]],
"TTAC": [[1, 1, 0.5]],
"TGCG": [[1, 2, 0.5]],
"ACGA": [[1, 3, 0.5]],
"AGAT": [[1, 4, 0.5]],
"GTTG": [[1, 5, 0.5]],
"AAGC": [[1, 6, 0.5]],
}
freq = cs.consensus_sequence(reads_3)
self.assertEqual(contigs_3, cs.compute_new_contigs(freq))
def _main():
# Open files and process reads dictionary
f = open(sys.argv[1], 'r')
reads_dict = init._process(f)
# Get contigs from first consensus sequence
contigs = cs.run_consensus(reads_dict)
contig_file = open(sys.argv[2] + '/contig.txt', 'w+')
ll_file = open(sys.argv[2] + '/likelihood.txt', 'w+')
# Set initial parameters
likelihood = 0
likelihood_new = 0
#likelihood_list = []
for i in range(NUM_ITERS):
'''FILE WRITES'''
# Contigs file write data
contig_file.write('%s\tstart\t' % (str(i)))
for c in contigs:
contig_file.write('%s\t' % (str(c)))
contig_file.write('\n')
contig_file.flush()
# Likelihood file write data
ll_file.write(
'%s\t%s\t%s\n' %
(str(i), str(likelihood), str(len(contigs)))), ll_file.flush()
#likelihood_list.append(float(likelihood))
# Reads file write data
reads_file = open(sys.argv[2] + '/reads_trial_' + str(i) + '.txt', 'w')
for r in reads_dict:
for l in reads_dict[r]:
reads_file.write(
str(l[3]) + ',' + str(l[0]) + ',' + str(l[1]) + str(',') +
str(l[3]) + '\n')
reads_file.close()
'''COMPUTATION OF ALGORITHM'''
# Update likelihood
likelihood = likelihood_new
# Map reads
reads_dict = rm.run(reads_dict, contigs)
# Run Consensus Sequence
contigs = cs.run_consensus(reads_dict)
# Print data to file
contig_file.write('%s\tmerge\t' % (str(i)))
for c in contigs:
contig_file.write('%s\t' % (str(c)))
contig_file.write('\n')
# Run merge
contigs, reads_dict = mc.run_merge(
contigs, reads_dict
) # how do we know if a merge has happened..do we need to know?
# Get new likelihood
likelihood_new = ll._likelihood(reads_dict, contigs)
'''FILE WRITES'''
# Reads file write data
reads_file = open(sys.argv[2] + '/reads_trial_' + str(i + 1) + '.txt', 'w')
for r in reads_dict:
for l in reads_dict[r]:
reads_file.write(
str(l[3]) + ',' + str(l[0]) + ',' + str(l[1]) + str(',') +
str(l[3]) + '\n')
reads_file.close()
# Print data to file
for c in contigs:
contig_file.write('1000\tend\t%s\n' % (str(c)))
ll_file.write(
'%s\t%s\t%s\n' %
(str(NUM_ITERS), str(likelihood), str(len(contigs)))), ll_file.flush()
def _main():
# Open files and process reads dictionary
f = open(sys.argv[1], 'r')
reads_dict = init._process(f)
# Get contigs from first consensus sequence
contigs = cs.run_consensus(reads_dict)
contig_file = open(sys.argv[2] + '/contig.txt', 'w+')
ll_file = open(sys.argv[2] + '/likelihood.txt', 'w+')
# Set initial parameters
likelihood = 0
likelihood_new = 0
#likelihood_list = []
for i in range(NUM_ITERS):
'''FILE WRITES'''
# Contigs file write data
contig_file.write('%s\tstart\t' %(str(i)))
for c in contigs:
contig_file.write('%s\t' %(str(c)))
contig_file.write('\n')
contig_file.flush()
# Likelihood file write data
ll_file.write('%s\t%s\t%s\n' %(str(i), str(likelihood), str(len(contigs)))), ll_file.flush()
#likelihood_list.append(float(likelihood))
# Reads file write data
reads_file = open(sys.argv[2] + '/reads_trial_' + str(i) + '.txt','w')
for r in reads_dict:
for l in reads_dict[r]:
reads_file.write(str(l[3])+','+str(l[0])+','+str(l[1])+str(',')+str(l[3])+'\n')
reads_file.close()
'''COMPUTATION OF ALGORITHM'''
# Update likelihood
likelihood = likelihood_new
# Map reads
reads_dict = rm.run(reads_dict, contigs)
# Run Consensus Sequence
contigs = cs.run_consensus(reads_dict)
# Print data to file
contig_file.write('%s\tmerge\t' %(str(i)))
for c in contigs:
contig_file.write('%s\t' %(str(c)))
contig_file.write('\n')
# Run merge
contigs, reads_dict = mc.run_merge(contigs,reads_dict) # how do we know if a merge has happened..do we need to know?
# Get new likelihood
likelihood_new = ll._likelihood(reads_dict,contigs)
'''FILE WRITES'''
# Reads file write data
reads_file = open(sys.argv[2] + '/reads_trial_' + str(i+1) + '.txt','w')
for r in reads_dict:
for l in reads_dict[r]:
reads_file.write(str(l[3])+','+str(l[0])+','+str(l[1])+str(',')+str(l[3])+'\n')
reads_file.close()
# Print data to file
for c in contigs:
contig_file.write('1000\tend\t%s\n' %(str(c)))
ll_file.write('%s\t%s\t%s\n' %(str(NUM_ITERS), str(likelihood), str(len(contigs)))), ll_file.flush()