def Pipeline_Files(self):
self.blast_db_fasta_biomart = str(
Path("Biomart") / f"{self.organism}_biomart_3utr.fasta")
self.blast_db_fasta_biomart_valid = str(
self.tmp_dir / Path(self.organism + "_biomart_valid.fasta"))
self.blast_db_biomart = str(self.tmp_dir / "blast_files" /
"blastdb_biomart")
self.blast_db_csv_ucsc = str(self.tmp_dir /
Path(self.organism + "_ucsc.csv"))
self.blast_db_fasta_ucsc_valid = str(
self.tmp_dir / Path(self.organism + "_ucsc_valid.fasta"))
self.blast_db_ucsc = str(self.tmp_dir / "blast_files" / "blastdb_ucsc")
self.blast_tmp_result = str(self.tmp_dir / "tmp_blast_result.csv")
self.blast_with_mRNA = str(self.tmp_dir /
Path(self.organism + "_mRNA.csv"))
self.blast_with_mRNA = utils.filename_date_append(self.blast_with_mRNA)
self.final_output = str(
"Datafiles_Prepare/CSV" /
Path(self.organism + "_" + self.paper_name + "_Data.csv"))
self.final_output = utils.filename_date_append(self.final_output)
self.blast_no_unique = str("Datafiles_Prepare/Logs" /
Path(self.organism + "_" + self.paper_name +
"_Blast_Nonunique.fasta"))
self.blast_no_unique = utils.filename_date_append(self.blast_no_unique)
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 file_formatting(self):
in_df = pd.read_csv(self.blast_with_mRNA)
in_df['Source'] = self.paper_name
in_df['Organism'] = self.organism
in_df['Creation_time'] = JsonLog.get_creation_time()
# Take only the valid rows: Status=OK
valid_rows = in_df['biomart_blast_status'] == "OK"
JsonLog.add_to_json("Pipeline valid blast results", sum(valid_rows))
JsonLog.add_to_json("Pipeline invalid blast results",
(in_df.shape[0] - sum(valid_rows)))
in_df = in_df[valid_rows]
#Remove miRNA with XXX/stars
rows_without_XXX = in_df['miRNA sequence'].apply(
lambda x: x.find('X') == -1)
JsonLog.add_to_json("Pipeline valid miRNA_no_xxx",
sum(rows_without_XXX))
JsonLog.add_to_json("Pipeline invalid miRNA (xxx)",
(in_df.shape[0] - sum(rows_without_XXX)))
in_df = in_df[rows_without_XXX]
# Remove miRNA with stars
rows_without_stars = in_df['microRNA_name'].apply(
lambda x: x.find('star') == -1)
JsonLog.add_to_json("Pipeline valid miRNA_no_***",
sum(rows_without_stars))
JsonLog.add_to_json("Pipeline invalid miRNA (star)",
(in_df.shape[0] - sum(rows_without_stars)))
in_df = in_df[rows_without_stars]
# Choose the necessary columns
in_df_filter = in_df.filter([
'Source', 'Organism', 'GI_ID', 'microRNA_name', 'miRNA sequence',
'target sequence', 'number of reads', 'biomart_title',
'biomart_sbjct_start', 'biomart_sbjct_end', 'biomart_full_mrna'
],
axis=1)
in_df_filter.rename(columns={
'biomart_title': 'mRNA_name',
'biomart_sbjct_start': 'mRNA_start',
'biomart_sbjct_end': 'mRNA_end',
'biomart_full_mrna': 'full_mrna'
},
inplace=True)
# reset the index
in_df_filter.reset_index(drop=True, inplace=True)
# self.log.append("miRNA statistics")
# self.log.append(dict(in_df_filter['microRNA_name'].value_counts()))
# save to file
in_df_filter.to_csv(utils.filename_date_append(self.final_output))
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():
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()