def main():
try:
debug=ast.literal_eval(sys.argv[1])
except IndexError:
debug=True
if (debug):
print ("***************************************\n"
"\t\t\t DEBUG \n"
"***************************************\n")
interaction_file = str(Path("Papers/1-s2.0-S009286741300439X-mmc1.txt"))
log_dir = "Datafiles_Prepare/Logs/"
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
organisms = ["Human"]
for organism in organisms:
JsonLog.set_filename(
utils.filename_date_append(Path(log_dir) / Path("Mapping_the_Human_miRNA_" + organism + ".json")))
JsonLog.add_to_json('file name', interaction_file)
JsonLog.add_to_json('paper',
"Mapping the Human miRNA Interactome by CLASH Reveals Frequent Noncanonical Binding")
JsonLog.add_to_json('Organism', organism)
JsonLog.add_to_json('paper_url', "https://www.sciencedirect.com/science/article/pii/S009286741300439X")
p = Pipeline(paper_name="Mapping_the_Human_miRNA",
organism=organism,
in_df=df_prepare(read_paper_data(interaction_file, debug)),
tmp_dir=tmp_dir)
p.run()
def main():
try:
debug = ast.literal_eval(sys.argv[1])
except IndexError:
debug = True
if (debug):
print("***************************************\n"
"\t\t\t DEBUG \n"
"***************************************\n")
mouse_config = {
"organism": "Mouse",
"interaction_file": "Papers/ncomms9864-s2.xlsx"
}
human_config = {
"organism": "Human",
"interaction_file": "Papers/ncomms9864-s4.xlsx"
}
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
log_dir = "Datafiles_Prepare/Logs/"
for cnfg in [mouse_config, human_config]:
organism = cnfg["organism"]
interaction_file = cnfg["interaction_file"]
JsonLog.set_filename(
utils.filename_date_append(
Path(log_dir) /
Path("Darnell_miRNA_target_chimeras_" + organism + ".json")))
JsonLog.add_to_json('file name', interaction_file)
JsonLog.add_to_json(
'paper',
"miRNA–target chimeras reveal miRNA 3-end pairing as a major determinant of Argonaute target specificity"
)
JsonLog.add_to_json('Organism', organism)
JsonLog.add_to_json('paper_url',
"https://www.nature.com/articles/ncomms9864")
org = Darnell_miRNA_target_chimeras(interaction_file,
tmp_dir,
organism,
debug=debug)
org.run()
print("Pipeline start")
p = Pipeline(paper_name="Darnell_miRNA_target_chimeras",
organism=organism,
in_df=org.prepare_for_pipeline(),
tmp_dir=tmp_dir)
p.run()
def main():
p = Path("Datafiles_Prepare/CSV")
log_dir = "Datafiles_Prepare/Logs/"
files = list(p.glob('**/*.csv'))
run_list = [p for p in files if not p.match("*duplex*")]
process_list = []
for fin in run_list:
fout = utils.filename_suffix_append(fin, "_duplex")
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
p = Process(target=seed_interaction_add, args=(fin, fout, tmp_dir))
p.start()
process_list.append(p)
print(f"start process {p.name} {fin}")
for p in process_list:
p.join()
def main():
try:
debug = ast.literal_eval(sys.argv[1])
except IndexError:
debug = True
if (debug):
print("***************************************\n"
"\t\t\t DEBUG \n"
"***************************************\n")
interaction_file = str(Path("Papers/1-s2.0-S1097276516305214-mmc3.xlsx"))
log_dir = "Datafiles_Prepare/Logs/"
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
organisms = ["Celegans"]
for organism in organisms:
JsonLog.set_filename(
utils.filename_date_append(
Path(log_dir) /
Path("Pairing_Beyond_Seed_" + organism + ".json")))
JsonLog.add_to_json('file name', interaction_file)
JsonLog.add_to_json(
'paper',
"Pairing beyond the Seed Supports MicroRNA Targeting Specificity")
JsonLog.add_to_json('Organism', organism)
JsonLog.add_to_json(
'paper_url',
"https://www.sciencedirect.com/science/article/pii/S1097276516305214#mmc3"
)
ce = Pairing_Beyond_Seed(input_file=interaction_file,
organism=organism,
tmp_dir=tmp_dir,
debug=debug)
ce.run()
p = Pipeline(paper_name="Pairing_Beyond_Seed",
organism=organism,
in_df=ce.prepare_for_pipeline(),
tmp_dir=tmp_dir)
p.run()
def main():
try:
debug = ast.literal_eval(sys.argv[1])
except IndexError:
debug = True
if (debug):
print("***************************************\n"
"\t\t\t DEBUG \n"
"***************************************\n")
interaction_file = str(Path("Papers/41598_2017_7880_MOESM4_ESM.csv"))
log_dir = "Datafiles_Prepare/Logs/"
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
organisms = ["Cow"]
for organism in organisms:
JsonLog.set_filename(
utils.filename_date_append(
Path(log_dir) /
Path("Global_Mapping_Cattle_" + organism + ".json")))
JsonLog.add_to_json('file name', interaction_file)
JsonLog.add_to_json(
'paper',
"Global mapping of miRNA-target interactions in cattle (Bos taurus)"
)
JsonLog.add_to_json('Organism', organism)
JsonLog.add_to_json(
'paper_url',
"https://www.nature.com/articles/s41598-017-07880-8#MOESM1")
cow = Global_Mapping_Cattle(input_file=interaction_file,
tmp_dir=tmp_dir,
debug=debug)
cow.run()
p = Pipeline(paper_name="Global_Mapping_Cattle",
organism=organism,
in_df=cow.prepare_for_pipeline(),
tmp_dir=tmp_dir)
p.run()
def main():
try:
debug = ast.literal_eval(sys.argv[1])
except IndexError:
debug = True
if (debug):
print("***************************************\n"
"\t\t\t DEBUG \n"
"***************************************\n")
interaction_file = str(Path("Papers/1-s2.0-S1097276514003566-mmc3.xls"))
log_dir = "Datafiles_Prepare/Logs/"
tmp_dir = utils.make_tmp_dir("Datafiles_Prepare/tmp_dir", parents=True)
organisms = ["Celegans", "Human", "Mouse"]
for organism in organisms:
JsonLog.set_filename(
utils.filename_date_append(
Path(log_dir) /
Path("Unambiguous_Identification_" + organism + ".json")))
JsonLog.add_to_json('file name', interaction_file)
JsonLog.add_to_json(
'paper',
"Unambiguous Identification of miRNA:Target Site Interactions by Different Types of Ligation Reactions"
)
JsonLog.add_to_json('Organism', organism)
JsonLog.add_to_json(
'paper_url',
"https://www.sciencedirect.com/science/article/pii/S1097276514003566#app3"
)
p = Pipeline(paper_name="Unambiguous_Identification",
organism=organism,
in_df=df_prepare(
read_paper_data(interaction_file, organism, debug)),
tmp_dir=tmp_dir)
p.run()
def main():
input_dir = Path("Datafiles_Prepare/CSV")
output_dir = Path("Features/CSV")
log_dir = Path("Features/Logs")
tmp_base = "Features/tmp_dir"
files = list(input_dir.glob("*_duplex_*.csv"))
process_list = []
for fin in files:
tmp_dir = utils.make_tmp_dir(tmp_base, parents=True)
fout = output_dir / f"{fin.stem}_feature.csv"
if fout.exists():
continue
flog = log_dir / f"{fin.stem}_feature.json"
p = Process(target=worker, args=(fin, fout, tmp_dir))
p.start()
process_list.append(p)
print(f"start process {p.name} {fin}")
for p in process_list:
p.join()
def main():
input_dir = Path("Datafiles_Prepare/CSV")
tmp_base = "Features/tmp_dir"
files = list(input_dir.glob("*duplex*.csv"))
files = [f for f in files if not f.match("*negative*")]
print(files)
process_list = []
for fin in files:
tmp_dir = utils.make_tmp_dir(tmp_base, parents=True)
organism = fin.stem.split("_")[0]
print(organism)
p = Process(target=worker, args=(organism, fin, tmp_dir))
p.start()
process_list.append(p)
print(f"start process {p.name} {fin}")
for p in process_list:
p.join()