def write_event_durations_to_file(directories, destination):
# make the files to hold durations
template_file = open(destination + "template_durations.csv", 'w')
complement_file = open(destination + "complement_durations.csv", 'w')
all_together_file = open(destination + "all_durations.csv", 'w')
# go through each directory and gather up durations
for directory in directories:
directory_files = directory + "*.fast5"
nb_files = len(glob(directory_files))
sample_set = int(floor(0.25 * nb_files))
print("Found {nb_files} in folder {folder} sampling {nb_sample_set}".format(nb_files=nb_files,
folder=directory,
nb_sample_set=sample_set),
file=sys.stderr)
# make this random.sample, sample 10% of the files in the directory
for f in sample(glob(directory_files), sample_set):
npRead = NanoporeRead(f)
if hasattr(npRead, 'template_event_table') and hasattr(npRead, 'complement_event_table'):
file_name = f.split('/')[-1]
print(file_name, file=sys.stderr)
for t, c in map(None, npRead.template_event_table, npRead.complement_event_table):
if t is not None:
print(t[3], t[6], 't', sep=',', end='\n', file=template_file)
print(t[3], t[6], 't',sep=',', end='\n', file=all_together_file)
if c is not None:
print(c[3], c[6], 'c', sep=',', end='\n', file=complement_file)
print(c[3], c[6], 'c', sep=',', end='\n', file=all_together_file)
npRead.close()
def main():
if len(sys.argv) < 3:
print("USAGE: python thisScript.py /path/to/file.fast5 /path/to/destination")
if len(sys.argv) == 3:
# setup
out_file = open(sys.argv[2], 'w')
# load and transform
npRead = NanoporeRead(sys.argv[1])
npRead.get_2d_event_map()
npRead.transform_events(npRead.template_events, npRead.template_drift)
npRead.transform_events(npRead.complement_events, npRead.complement_drift)
# output
# line 1
print(len(npRead.twoD_read_sequence), end=' ', file=out_file) # 2D read length
print(len(npRead.template_events), end=' ', file=out_file) # nb of template events
print(len(npRead.complement_events), end=' ', file=out_file) # nb of complement events
print(npRead.template_scale, end=' ', file=out_file) # template scale
print(npRead.template_shift, end=' ', file=out_file) # template shift
print(npRead.template_var, end=' ', file=out_file) # template var
print(npRead.template_scale_sd, end=' ', file=out_file) # template scale_sd
print(npRead.template_var_sd, end=' ', file=out_file) # template var_sd
print(npRead.complement_scale, end=' ', file=out_file) # complement scale
print(npRead.complement_shift, end=' ', file=out_file) # complement shift
print(npRead.complement_var, end=' ', file=out_file) # complement var
print(npRead.complement_scale_sd, end=' ', file=out_file) # complement scale_sd
print(npRead.complement_var_sd, end='\n', file=out_file) # complement var_sd
# line 2
print(npRead.twoD_read_sequence, end='\n', file=out_file)
# line 3
for _ in npRead.template_event_map:
print(_, end=' ', file=out_file)
print("", end="\n", file=out_file)
# line 4
for mean, start, stdev, length in npRead.template_events:
print(mean, stdev, length, sep=' ', end=' ', file=out_file)
print("", end="\n", file=out_file)
# line 5
for _ in npRead.complement_event_map:
print(_, end=' ', file=out_file)
print("", end="\n", file=out_file)
# line 6
for mean, start, stdev, length in npRead.complement_events:
print(mean, stdev, length, sep=' ', end=' ', file=out_file)
print("", end="\n", file=out_file)
