def output_data(data):
# Print the header first
filenames = [filename.split("/")[-1] for filename, _ in data]
print_tab_delimited(["Chromosome", "Left", "Right", "Name", "Strand"] + filenames)
for _, tsr in data[0][1]:
print_tab_delimited(list(tsr) + [file_data[tsr] for _, file_data in data])
def output_pausing_distances(pausing_distances, sequencing_files):
# Print the headers first
print_tab_delimited(
["Transcript Length"] +
[seq_filename.split("/")[-1] for seq_filename in sequencing_files])
for i in range(len(pausing_distances[0])):
print_tab_delimited([i] + [x[i] for x in pausing_distances])
def output_data(combined_dict, sequencing_files, upstream_distance,
interval_size):
# Now the data is in the combined_dict, we need to reduce it back down to positions again
# First print out the headers
print_tab_delimited(
["Position"] +
[seq_file.split("/")[-1] for seq_file in sequencing_files])
real_position = upstream_distance * -1
# Now output all of the data
for position in combined_dict:
print_tab_delimited([real_position] + combined_dict[position])
real_position += interval_size
def output_data(avgs_dict, region_length):
# Write the header
print_tab_delimited(["Position"] + list(avgs_dict.keys()))
position = region_length / 2 * -1
# We go through each position and output the averages
for i in range(region_length):
if position == 0:
position += 1
print_tab_delimited([position] +
[avgs_dict[nt][i] for nt in avgs_dict.keys()])
position += 1
def run_sequence_searches(regions_file, searching_sequences, region_length):
# Has keys of gene names and values of dictionary which has keys of "Sequence" and "Region" and "Motifs".
master_dict = {}
# 1. Read in the contents of the bed file
with open(regions_file) as file:
bed_lines = file.readlines()
fasta_file = run_getfasta(regions_file)
fasta_sequences = read_fasta(fasta_file)
remove_files(fasta_file)
# Fill the dictionary
for i, line in enumerate(bed_lines):
chromosome, left, right, gene_name, _, strand = line.split()
master_dict[gene_name] = {
"Sequence": "",
"Region": line.split(),
"Motifs": {}
}
master_dict[gene_name]["Sequence"] = fasta_sequences[i]
for search in searching_sequences:
sequence, _, _ = search
master_dict[gene_name]["Motifs"][sequence] = False
for gene_name in master_dict:
for search in searching_sequences:
find_sequences(master_dict[gene_name], search, region_length)
# Output the results
print_tab_delimited(
["Chromosome", "Left", "Right", "Gene", "Score", "Strand"] +
[search[0] for search in searching_sequences])
for gene_name in master_dict:
print_tab_delimited(master_dict[gene_name]["Region"] + [
has_motif
for _, has_motif in master_dict[gene_name]["Motifs"].items()
])
def output_data(pausing_distances):
output_dict = {}
for tup in pausing_distances:
ret_dict, seq_filename = tup
for gene_name in ret_dict:
if gene_name not in output_dict:
output_dict[gene_name] = {}
output_dict[gene_name][seq_filename] = ret_dict[gene_name]
for i, gene_name in enumerate(output_dict):
if i == 0:
# We print the headers
print_tab_delimited(
["Gene"] +
[x.split("/")[-1] for x in output_dict[gene_name].keys()])
print_tab_delimited([gene_name] + [
output_dict[gene_name][sequencing_filename]
for sequencing_filename in output_dict[gene_name]
])
def output_metaplot_data(averages, region_length, prime_name):
"""
:param averages: averages list from the metaplots programs
:type averages: list
:param region_length: length of the region
:type region_length: int
:param prime_name: either "five prime" or "three prime"
:type prime_name: str
:return:
"""
avgs_data, files = [x for x in zip(*averages)]
# Merge all of the lists together
merged_list = [list(chain.from_iterable(x)) for x in zip(*avgs_data)]
# 5. Put the data into a file
header = ["Position"]
# Write the header first
for file in files:
if prime_name:
# Include a space before print the prime name
header.append(
file.split("/")[-1] + " " + prime_name + " sense strand")
header.append(
file.split("/")[-1] + " " + prime_name + " divergent strand")
else:
header.append(file.split("/")[-1] + " sense strand")
header.append(file.split("/")[-1] + " divergent strand")
print_tab_delimited(header)
for i, base_list in enumerate(merged_list):
position = i - (region_length / 2)
if position >= 0:
position += 1
print_tab_delimited([position] + base_list)
def output_data(expanded_regions):
for region in expanded_regions:
print_tab_delimited(region)