def _profile_load_files_shared(max_read_size, min_read_no, min_read_size,
seq_file_list):
"""
Shared function for loading seq files
:param max_read_size: exclude reads with lengths > max_read_size (int)
:param min_read_no: exclude reads with counts below min_read_no (int)
:param min_read_size: exclude reads with lengths < min_read_size (int)
:param seq_file_list: [path/to/seq/, path/to/seq2,...] (list(str))
"""
print(
colored("-----------------LOADING SEQUENCES----------------", 'green'))
seq = SRNASeq()
if len(seq_file_list) == 1:
seq.load_seq_file(seq_file_list[0], max_read_size, min_read_no,
min_read_size)
else:
seq.load_seq_file_arg_list(seq_file_list, max_read_size, min_read_no,
min_read_size)
seq_name = ah.single_file_output(seq_file_list[0])
if len(seq_file_list) > 1:
for i in range(len(seq_file_list)):
if i == 0:
pass
else:
seq_name += "_{0}".format(
ah.single_file_output(seq_file_list[i]))
return seq, seq_name
def _cdp_output(counts_by_ref, file_fig, file_name, onscreen, no_csv, seq_name_1,
seq_name_2, ref_file, nt, pub, bok):
"""
Organise csv or pdf output for CDP analysis
"""
ref_name = ah.single_file_output(ref_file)
if file_fig or onscreen:
if file_name == "auto":
file_name = ah.cdp_file_output(seq_name_1,
seq_name_2,
ref_name,
nt,
"pdf")
pr.cdp_plot(counts_by_ref,
seq_name_1,
seq_name_2,
nt,
onscreen,
file_fig,
file_name,
pub,
bok)
if no_csv:
out_csv_name = ah.cdp_file_output(seq_name_1,
seq_name_2,
ref_name,
nt,
"csv")
wtf.cdp_output(counts_by_ref,
seq_name_1,
seq_name_2,
out_csv_name)
def _cdp_load_files_shared(max_read_size, min_read_no, min_read_size,
seq_file_list_1, seq_file_list_2):
"""
:param max_read_size: exclude reads with lengths > max_read_size (int)
:param min_read_no: exclude reads with counts below min_read_no (int):
:param min_read_size: exclude reads with lengths < min_read_size (int):
:param seq_file_list_1: [path/to/seq/, path/to/seq2,...] (list(str))
:param seq_file_list_2: [path/to/seq/, path/to/seq2,...] (list(st_2:
:return: seq1(sRNASeq), seq2 (sRNASeq), seq_name_1 (str), seq_name_2 (str)
"""
print(
colored("-----------------LOADING SEQUENCES----------------", 'green'))
seq_1 = SRNASeq()
if len(seq_file_list_1) == 1:
seq_1.load_seq_file(seq_file_list_1[0], max_read_size, min_read_no,
min_read_size)
else:
seq_1.load_seq_file_arg_list(seq_file_list_1, max_read_size,
min_read_no, min_read_size)
seq_2 = SRNASeq()
if len(seq_file_list_2) == 1:
seq_2.load_seq_file(seq_file_list_2[0], max_read_size, min_read_no,
min_read_size)
else:
seq_2.load_seq_file_arg_list(seq_file_list_2, max_read_size,
min_read_no, min_read_size)
seq_name_1 = ah.single_file_output(seq_file_list_1[0])
if len(seq_file_list_1) > 1:
for i in range(len(seq_file_list_1)):
if i == 0:
pass
else:
seq_name_1 += "_{0}".format(
ah.single_file_output(seq_file_list_1[i]))
seq_name_2 = ah.single_file_output(seq_file_list_2[0])
if len(seq_file_list_2) > 1:
for i in range(len(seq_file_list_2)):
if i == 0:
pass
else:
seq_name_2 += "_{0}".format(
ah.single_file_output(seq_file_list_2[i]))
return seq_1, seq_2, seq_name_1, seq_name_2
def _load_ref_shared(ref_file):
"""
Shared function for loading reference file
:param ref_file:
:return:
"""
ref = RefSeq()
ref.load_ref_file(ref_file)
single_ref = ""
if len(ref) > 1:
print("\nMultiple reference sequences in file. Exiting.\n")
sys.exit()
ref_output = ah.single_file_output(ref_file)
for header in ref.headers():
single_ref = ref[header]
print(colored("------------------ALIGNING READS------------------\n", 'green'))
return ref_output, single_ref
def _load_ref_shared(ref_file):
"""
Shared function for loading reference file
:param ref_file:
:return:
"""
ref = RefSeq()
ref.load_ref_file(ref_file)
single_ref = ""
if len(ref) > 1:
print("\nMultiple reference sequences in file. Exiting.\n")
sys.exit()
ref_output = ah.single_file_output(ref_file)
for header in ref.headers():
single_ref = ref[header]
print(
colored("------------------ALIGNING READS------------------\n",
'green'))
return ref_output, single_ref
def _cdp_output(counts_by_ref, file_fig, file_name, onscreen, no_csv,
seq_name_1, seq_name_2, ref_file, nt, pub):
"""
Organise csv or pdf output for CDP analysis
"""
ref_name = ah.single_file_output(ref_file)
if file_fig or onscreen:
if file_name == "auto":
file_name = ah.cdp_file_output(seq_name_1, seq_name_2, ref_name,
nt, "pdf")
pr.cdp_plot(counts_by_ref, seq_name_1, seq_name_2, nt, onscreen,
file_fig, file_name, pub)
if no_csv:
out_csv_name = ah.cdp_file_output(seq_name_1, seq_name_2, ref_name, nt,
"csv")
wtf.cdp_output(counts_by_ref, seq_name_1, seq_name_2, out_csv_name)
def reads_aligned_per_seq(seq_file_list,
ref_file,
nt,
split,
min_read_len=18,
max_read_len=32,
min_read_no=1,
processes=4):
"""
Get RPMR alignments for each sequence file in the list - no plot
:param seq_file_list: [path/to/seq/, path/to/seq2,...] (list(str))
:param ref_file: path/to/reference (str):
:param nt: read length to align (int)
:param split: spit reads or not (bool)
:param min_read_size: exclude reads with lengths < min_read_size (int)
:param max_read_size: exclude reads with lengths > max_read_size (int)
:param min_read_no: exclude reads with counts below min_read_no (int)
:param pub: publication plot with no axes, legend (bool)
:param processes: no of processes to generate at a time i.e. threads (int)
"""
"""
Calculates normalised reads aligned to multiple reference sequences for each seq file individually
Outputs a csv only (no scatter plot)
"""
print(
colored("-----------------LOADING SEQUENCES----------------", 'green'))
loaded_seq_list = [] # list of SRNASeq objects
loaded_seq_name_list = [] # list of seq names in same order
for seq_file in range(len(seq_file_list)):
seq = SRNASeq()
seq.load_seq_file(seq_file_list[seq_file], max_read_len, min_read_no,
min_read_len)
loaded_seq_list.append(seq)
seq_name = ah.single_file_output(seq_file_list[seq_file])
loaded_seq_name_list.append(seq_name)
if split:
cdp.cdp_no_split_single(loaded_seq_list, loaded_seq_name_list,
ref_file, nt, processes)
else:
cdp.cdp_split_single(loaded_seq_list, loaded_seq_name_list, ref_file,
nt, processes)