def test_three_contig_2(self):
c_1 = ['GATCAAAA', 'CCCGGAAA','AAAAGATC']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
bbl_truth_1 = {'AAAAGATC':['GATCAAAA', 4], 'GATCAAAA':['AAAAGATC',4]}
self.assertEqual(bbl_test_1, bbl_truth_1)
def test_three_contig_3(self):
c_1 = ['GATCTAAA', 'CCCGAAAA','AAAAGATC']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
contig_trace_test_1 = mc.trace_contigs(bbl_test_1)
contig_trace_truth_1 = [[['CCCGAAAA',0],['AAAAGATC',4],['GATCTAAA',4]]]
self.assertEqual(contig_trace_test_1, contig_trace_truth_1)
def test_three_contig_4(self):
c_1 = ['GATCTAAA', 'CCCGAAAA', 'AAAAGATC']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
contig_trace_test_1 = mc.trace_contigs(bbl_test_1)
new_contigs_test_1 = mc.merge_contigs(contig_trace_test_1, c_1)
new_contigs_truth_1 = ['CCCGAAAAGATCTAAA']
self.assertEqual(new_contigs_test_1, new_contigs_truth_1)
def test_three_contig_2(self):
c_1 = ['GATCAAAA', 'CCCGGAAA', 'AAAAGATC']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
bbl_truth_1 = {
'AAAAGATC': ['GATCAAAA', 4],
'GATCAAAA': ['AAAAGATC', 4]
}
self.assertEqual(bbl_test_1, bbl_truth_1)
def test_three_contig_1(self):
c_1 = ['GATCTTTT', 'GATCGATC','ATCAAAAA']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbr_truth_1 = {'GATCGATC':['GATCTTTT', 4]}
self.assertEqual(bbr_test_1,bbr_truth_1)
c_2 = ['GATCAAAA', 'CCCGGAAA','AAAAGATC']
contig_dict_2 = mc.merge_check_global(c_2, 3)
bbr_test_2 = mc.suffix_filter(contig_dict_2)
bbr_truth_2 = {'CCCGGAAA':['AAAAGATC', 3], 'AAAAGATC':['GATCAAAA', 4], 'GATCAAAA':['AAAAGATC', 4]}
self.assertEqual(bbr_test_2,bbr_truth_2)
def test_three_contig_1(self):
c_1 = ['GATCTTTT', 'GATCGATC', 'ATCAAAAA']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbr_truth_1 = {'GATCGATC': ['GATCTTTT', 4]}
self.assertEqual(bbr_test_1, bbr_truth_1)
c_2 = ['GATCAAAA', 'CCCGGAAA', 'AAAAGATC']
contig_dict_2 = mc.merge_check_global(c_2, 3)
bbr_test_2 = mc.suffix_filter(contig_dict_2)
bbr_truth_2 = {
'CCCGGAAA': ['AAAAGATC', 3],
'AAAAGATC': ['GATCAAAA', 4],
'GATCAAAA': ['AAAAGATC', 4]
}
self.assertEqual(bbr_test_2, bbr_truth_2)
def test_read_reverse_1(self):
reads_dict_1 = {'AAAAT':[[0,0,0.5,1]],'AAATC':[[0,1,0.5,1]],'AATCA':[[0,2,0.5,1],[1,0,0.5,1]],'ATCAG':[[1,1,0.5,1]],'TTTTT':[[2,0,0.5,1]]}
reverse_dict_test_1 = mc.reverse_reads_dict(reads_dict_1)
reverse_dict_truth_1 = {0:[['AAAAT',0,0.5,1],['AAATC',1,0.5,1],['AATCA',2,0.5,1]],1:[['AATCA',0,0.5,1],['ATCAG',1,0.5,1]],2:[['TTTTT',0,0.5,1]]}
for i in reverse_dict_test_1:
for j in reverse_dict_test_1[i]:
self.assertTrue(j in reverse_dict_truth_1[i])
def test_merge_check_1(self):
c_1 = ['GATCTTTT', 'GATCGATC']
test_1 = mc.merge_check_global(c_1, 3)
truth_1 = {
'GATCTTTT': Counter({'GATCGATC': 0}),
'GATCGATC': Counter({'GATCTTTT': 4})
}
self.assertEqual(test_1, truth_1)
def test_run(self):
c_1 = ['AAAATCA', 'AATCAGG', 'TTTTTTT']
reads_dict_1 = {'AAAAT':[[0,0,0.5,1]],'AAATC':[[0,1,0.5,1]],'AATCA':[[0,2,0.5,1],[1,0,0.5,1]],'ATCAG':[[1,1,0.5,1]],'TTTTT':[[2,0,0.5,1]]}
new_contigs_test_1, new_reads_test_1 = mc.run_merge(c_1,reads_dict_1,3)
new_contigs_truth_1 = ['AAAATCAGG','TTTTTTT']
new_reads_dict_truth_1 = {'ATCAG': [[0,3,0.5,1]], 'AATCA': [[0,2,0.5,1]], 'AAAAT': [[0,0,0.5,1]], 'TTTTT': [[1,0,0.5,1]], 'AAATC': [[0,1,0.5,1]]}
self.assertEqual(new_reads_dict_truth_1, new_reads_test_1)
self.assertEqual(new_contigs_truth_1,new_contigs_test_1)
def test_read_updates_1(self):
c_1 = ['AAAATCA', 'AATCAGG', 'TTTTTTT']
contig_dict_1 = mc.merge_check_global(c_1, 3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
contig_trace_test_1 = mc.trace_contigs(bbl_test_1)
new_contigs_test_1 = mc.merge_contigs(contig_trace_test_1, c_1[:])
reads_dict_1 = {
'AAAAT': [[0, 0, 0.5, 1]],
'AAATC': [[0, 1, 0.5, 1]],
'AATCA': [[0, 2, 0.5, 1], [1, 0, 0.5, 1]],
'ATCAG': [[1, 1, 0.5, 1]],
'TTTTT': [[2, 0, 0.5, 1]]
}
reverse_dict_test_1 = mc.reverse_reads_dict(reads_dict_1)
new_reads_dict_test_1 = mc.change_reads_on_merge(
reverse_dict_test_1, reads_dict_1, contig_trace_test_1, c_1,
new_contigs_test_1)
new_reads_dict_truth_1 = {
'ATCAG': [[0, 3, 0.5, 1]],
'AATCA': [[0, 2, 0.5, 1]],
'AAAAT': [[0, 0, 0.5, 1]],
'TTTTT': [[1, 0, 0.5, 1]],
'AAATC': [[0, 1, 0.5, 1]]
}
self.assertEqual(new_reads_dict_truth_1, new_reads_dict_test_1)
def test_read_updates_1(self):
c_1 = ['AAAATCA', 'AATCAGG', 'TTTTTTT']
contig_dict_1 = mc.merge_check_global(c_1,3)
bbr_test_1 = mc.suffix_filter(contig_dict_1)
bbl_test_1 = mc.extract_bbl(bbr_test_1)
contig_trace_test_1 = mc.trace_contigs(bbl_test_1)
new_contigs_test_1 = mc.merge_contigs(contig_trace_test_1, c_1[:])
reads_dict_1 = {'AAAAT':[[0,0,0.5,1]],'AAATC':[[0,1,0.5,1]],'AATCA':[[0,2,0.5,1],[1,0,0.5,1]],'ATCAG':[[1,1,0.5,1]],'TTTTT':[[2,0,0.5,1]]}
reverse_dict_test_1 = mc.reverse_reads_dict(reads_dict_1)
new_reads_dict_test_1 = mc.change_reads_on_merge(reverse_dict_test_1, reads_dict_1, contig_trace_test_1, c_1, new_contigs_test_1)
new_reads_dict_truth_1 = {'ATCAG': [[0,3,0.5,1]], 'AATCA': [[0,2,0.5,1]], 'AAAAT': [[0,0,0.5,1]], 'TTTTT': [[1,0,0.5,1]], 'AAATC': [[0,1,0.5,1]]}
self.assertEqual(new_reads_dict_truth_1, new_reads_dict_test_1)
def test_read_reverse_1(self):
reads_dict_1 = {
'AAAAT': [[0, 0, 0.5, 1]],
'AAATC': [[0, 1, 0.5, 1]],
'AATCA': [[0, 2, 0.5, 1], [1, 0, 0.5, 1]],
'ATCAG': [[1, 1, 0.5, 1]],
'TTTTT': [[2, 0, 0.5, 1]]
}
reverse_dict_test_1 = mc.reverse_reads_dict(reads_dict_1)
reverse_dict_truth_1 = {
0: [['AAAAT', 0, 0.5, 1], ['AAATC', 1, 0.5, 1],
['AATCA', 2, 0.5, 1]],
1: [['AATCA', 0, 0.5, 1], ['ATCAG', 1, 0.5, 1]],
2: [['TTTTT', 0, 0.5, 1]]
}
for i in reverse_dict_test_1:
for j in reverse_dict_test_1[i]:
self.assertTrue(j in reverse_dict_truth_1[i])
def test_run(self):
c_1 = ['AAAATCA', 'AATCAGG', 'TTTTTTT']
reads_dict_1 = {
'AAAAT': [[0, 0, 0.5, 1]],
'AAATC': [[0, 1, 0.5, 1]],
'AATCA': [[0, 2, 0.5, 1], [1, 0, 0.5, 1]],
'ATCAG': [[1, 1, 0.5, 1]],
'TTTTT': [[2, 0, 0.5, 1]]
}
new_contigs_test_1, new_reads_test_1 = mc.run_merge(
c_1, reads_dict_1, 3)
new_contigs_truth_1 = ['AAAATCAGG', 'TTTTTTT']
new_reads_dict_truth_1 = {
'ATCAG': [[0, 3, 0.5, 1]],
'AATCA': [[0, 2, 0.5, 1]],
'AAAAT': [[0, 0, 0.5, 1]],
'TTTTT': [[1, 0, 0.5, 1]],
'AAATC': [[0, 1, 0.5, 1]]
}
self.assertEqual(new_reads_dict_truth_1, new_reads_test_1)
self.assertEqual(new_contigs_truth_1, new_contigs_test_1)
def test_merge_check_2(self):
c_1 = ['GATCTTTT', 'GATCGATC']
test_1 = mc.merge_check_global(c_1, 5)
truth_1 = []
self.assertEqual(test_1, truth_1)
def test_merge_check_2(self):
c_1 = ['GATCTTTT', 'GATCGATC']
test_1 = mc.merge_check_global(c_1, 5)
truth_1 = []
self.assertEqual(test_1, truth_1)
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()
def test_merge_check_1(self):
c_1 = ['GATCTTTT', 'GATCGATC']
test_1 = mc.merge_check_global(c_1, 3)
truth_1 = {'GATCTTTT': Counter({'GATCGATC':0}), 'GATCGATC': Counter({'GATCTTTT':4})}
self.assertEqual(test_1, truth_1)