def batch_convert_to_scorefile(list_of_files):
for query_file in list_of_files:
filetype = determine_filetype(query_file)
## Assume same filetype for all other files
query_df = pandas.read_table(query_file)
if filetype == "broadPeak":
query_df.columns = broadPeak_columns
elif filetype == "narrowPeak":
query_df.columns = narrowPeak_columns
elif filetype == "questPeak":
query_df.columns = questPeak_columns
if filetype in ["broadPeak", "narrowPeak"]:
outfile = get_sorted_filename(os.path.abspath(query_file))
convert_to_scorefile(query_file, filetype, outfile)
def batch_convert_to_scorefile(list_of_files):
for query_file in list_of_files:
filetype = determine_filetype(query_file)
## Assume same filetype for all other files
query_df = pandas.read_table(query_file)
if filetype == 'broadPeak':
query_df.columns = broadPeak_columns
elif filetype == 'narrowPeak':
query_df.columns = narrowPeak_columns
elif filetype == 'questPeak':
query_df.columns = questPeak_columns
if filetype in ['broadPeak', 'narrowPeak']:
outfile = get_sorted_filename(os.path.abspath(query_file))
convert_to_scorefile(query_file, filetype, outfile)
def perform_bed_intersection(query_file, list_of_target_files):
target_files = [os.path.abspath(f) for f in list_of_target_files]
target_files_abs = (' ').join(target_files)
query_file_abs = os.path.abspath(query_file)
command = 'bedtools intersect -c -sorted -sortout -a {} -b {}'.format(query_file_abs, target_files_abs)
outfile = os.path.join(os.path.dirname(query_file), 'intersection.bed')
handle = open(outfile, 'w')
cwd = os.path.dirname(query_file)
run_subprocess(command, stdout=handle, cwd=cwd)
handle.close()
broad_or_narrow = is_broad_or_narrow(query_file_abs)
print broad_or_narrow
filter_outfile = os.path.join(os.path.dirname(query_file), 'intersection_filtered.bed')
filter_peaks(outfile, broad_or_narrow, filter_outfile)
convert_to_scorefile(filter_outfile, broad_or_narrow)
