remaining_time = time_passed / count * (len(paired_end_reads) -
count)
print 'Approximately {:.3} minutes remaining'.format(
remaining_time)
return alignments, genome_aligned_reads
if __name__ == "__main__":
genome_name = 'practice_W_1'
input_folder = './{}'.format(genome_name)
chr_name = '{}_chr_1'.format(genome_name)
reads_fn_end = 'reads_{}.txt'.format(chr_name)
reads_fn = join(input_folder, reads_fn_end)
ref_fn_end = 'ref_{}.txt'.format(chr_name)
ref_fn = join(input_folder, ref_fn_end)
key_length = 7
start = time.clock()
reads = read_reads(reads_fn)
# If you want to speed it up, cut down the number of reads by
# changing the line to reads = read_reads(reads_fn)[:<x>] where <x>
# is the number of reads you want to work with.
genome_hash_table = build_hash_and_pickle(ref_fn, key_length)
ref = read_reference(ref_fn)
genome_aligned_reads, alignments = hashing_algorithm(
reads, genome_hash_table)
# print genome_aligned_reads
# print alignments
output_str = pretty_print_aligned_reads_with_ref(genome_aligned_reads,
alignments, ref)
print output_str[:5000]
read_alignment_locations.append(min_mismatch_location)
output_read_pair.append(read)
# # Note that there are some huge potential problems here.
all_read_alignment_locations.append(read_alignment_locations)
output_read_pairs.append(output_read_pair)
return all_read_alignment_locations, output_read_pairs
if __name__ == "__main__":
data_folder = 'hw1_W_2'
input_folder = join('../data/', data_folder)
f_base = '{}_chr_1'.format(data_folder)
reads_fn = join(input_folder, 'reads_{}.txt'.format(f_base))
start = time.clock()
input_reads = read_reads(reads_fn)
# This will take a while; you can use an array slice for example:
#
# input_reads = reads[:300]
#
# to generate some data quickly.
reference_fn = join(input_folder, 'ref_{}.txt'.format(f_base))
reference = read_reference(reference_fn)
alignments, reads = trivial_algorithm(input_reads, reference)
print alignments
print reads
output_str = pretty_print_aligned_reads_with_ref(reads, alignments, reference)
output_fn = join(input_folder, 'aligned_{}.txt'.format(f_base))
with(open(output_fn, 'w')) as output_file:
output_file.write(output_str)
n_mismatches = sum(mismatches)
if n_mismatches < max_mismatches:
min_mismatch_location = i - part
read = rev_read
read_alignment_locations.append(min_mismatch_location)
output_read_pair.append(read)
all_read_alignment_locations.append(read_alignment_locations)
output_read_pairs.append(output_read_pair)
return all_read_alignment_locations, output_read_pairs
if __name__ == "__main__":
data_folder = 'practice_W_1'
input_folder = join('./', data_folder)
f_base = '{}_chr_1'.format(data_folder)
reads_fn = join(input_folder, 'reads_{}.txt'.format(f_base))
start = time.clock()
input_reads = read_reads(reads_fn)
reference_fn = join(input_folder, 'ref_{}.txt'.format(f_base))
reference = read_reference(reference_fn)
alignments, reads = faster_algorithm(input_reads, reference)
print alignments
print reads
output_str = pretty_print_aligned_reads_with_ref(reads, alignments,
reference)
output_fn = join(input_folder, 'aligned_{}.txt'.format(f_base))
with (open(output_fn, 'w')) as output_file:
output_file.write(output_str)
consensus_string += consensus_base
return consensus_string
if __name__ == "__main__":
genome_name = 'hw2undergrad_E_2'
#genome_name = 'practice_E_1'
input_folder = '../data/{}'.format(genome_name)
chr_name = '{}_chr_1'.format(genome_name)
reads_fn_end = 'reads_{}.txt'.format(chr_name)
reads_fn = join(input_folder, reads_fn_end)
ref_fn_end = 'ref_{}.txt'.format(chr_name)
ref_fn = join(input_folder, ref_fn_end)
key_length = 8
start = time.clock()
reads = read_reads(reads_fn[:1000])
# If you want to speed it up, cut down the number of reads by
# changing the line to reads = read_reads(reads_fn)[:<x>] where <x>
# is the number of reads you want to work with.
#genome_hash_table = build_hash_and_pickle(ref_fn, key_length)
#reference = read_reference(ref_fn)
#genome_aligned_reads, alignments = hashing_algorithm(reads, genome_hash_table)
#g_aligned_reads = file('g_aligned_reads.txt', 'w'), 'aligned_reads'
#print genome_aligned_reads >> g_aligned_reads
#alignments_file = file('alignments.txt', 'w'), 'alignments'
#print alignments >> alignments_file
# print genome_aligned_reads
# print alignments
#output_str = pretty_print_aligned_reads_with_ref(genome_aligned_reads, alignments, reference)
# print output_str[:5000]
def read_assembly_reads(read_fn):
reads = read_reads(read_fn)
output_reads = [_[0] for _ in reads]
# Only taking one end of the read works okay, but
# this is an obvious area for improvement.
return output_reads
def read_assembly_reads(read_fn):
reads = read_reads(read_fn)
output_reads = [_[0] for _ in reads]
# Only taking one end of the read works okay, but
# this is an obvious area for improvement.
return output_reads
def read_assembly_reads(read_fn):
return read_reads(read_fn)
genome_aligned_reads.append(genome_aligned_read)
count += 1
if count % 100 == 0:
time_passed = (time.clock()-start)/60
print '{} reads aligned'.format(count), 'in {:.3} minutes'.format(time_passed)
remaining_time = time_passed/count*(len(paired_end_reads)-count)
print 'Approximately {:.3} minutes remaining'.format(remaining_time)
return alignments, genome_aligned_reads
if __name__ == "__main__":
genome_name = 'practice_W_1'
input_folder = './{}'.format(genome_name)
chr_name = '{}_chr_1'.format(genome_name)
reads_fn_end = 'reads_{}.txt'.format(chr_name)
reads_fn = join(input_folder, reads_fn_end)
ref_fn_end = 'ref_{}.txt'.format(chr_name)
ref_fn = join(input_folder, ref_fn_end)
key_length = 7
start = time.clock()
reads = read_reads(reads_fn)
# If you want to speed it up, cut down the number of reads by
# changing the line to reads = read_reads(reads_fn)[:<x>] where <x>
# is the number of reads you want to work with.
genome_hash_table = build_hash_and_pickle(ref_fn, key_length)
ref = read_reference(ref_fn)
genome_aligned_reads, alignments = hashing_algorithm(reads, genome_hash_table)
# print genome_aligned_reads
# print alignments
output_str = pretty_print_aligned_reads_with_ref(genome_aligned_reads, alignments, ref)
print output_str[:5000]