def test_sorf_detection(self):
fasta = os.path.join(self.fasta, "fasta")
gen_file(fasta, ">aaa\nTAGGAGGCCGCTATGCCATTA")
srna_gff = os.path.join(self.gff, "srna.gff")
inter_gff = os.path.join(self.gff, "inter.gff")
tss_file = os.path.join(self.gff, "tss.gff")
sd.get_coverage = self.mock.mock_get_coverage
sd.read_libs = self.mock.mock_read_libs
sd.read_wig = self.mock.mock_read_wig
sd.get_inter_coverage = self.mock.mock_get_inter_coverage
gen_file(srna_gff, self.example.srna)
gen_file(inter_gff, self.example.inter)
gen_file(tss_file, self.example.tss)
args = self.mock_args.mock()
args.start_codon = ["ATG"]
args.stop_codon = ["TTA"]
args.cutoff_5utr = "p_0.5"
args.cutoff_intercds = "n_20"
args.cutoff_3utr = "n_11"
args.cutoff_inter = 50
args.cutoff_anti = 50
args.libs = ["frag:frag:1:a:+"]
args.merge_wigs = "wig_folder"
args.utr_detect = True
args.background = 10
args.print_all = True
sd.sorf_detection(fasta, srna_gff, inter_gff, tss_file, "wig_f_file",
"wig_r_file", "test_folder/test", args)
sd.get_coverage = copy.deepcopy(get_coverage)
sd.replicate_comparison = self.mock.mock_replicate_comparison
self.assertTrue(os.path.exists("test_folder/test_all.csv"))
self.assertTrue(os.path.exists("test_folder/test_all.gff"))
self.assertTrue(os.path.exists("test_folder/test_best.csv"))
self.assertTrue(os.path.exists("test_folder/test_best.gff"))
def test_sorf_detection(self):
fasta = os.path.join(self.fasta, "fasta")
gen_file(fasta, ">aaa\nTAGGAGGCCGCTATGCCATTA")
srna_gff = os.path.join(self.gff, "srna.gff")
inter_gff = os.path.join(self.gff, "inter.gff")
tss_file = os.path.join(self.gff, "tss.gff")
sd.get_coverage = self.mock.mock_get_coverage
sd.read_libs = self.mock.mock_read_libs
sd.read_wig = self.mock.mock_read_wig
sd.get_inter_coverage = self.mock.mock_get_inter_coverage
gen_file(srna_gff, self.example.srna)
gen_file(inter_gff, self.example.inter)
gen_file(tss_file, self.example.tss)
args = self.mock_args.mock()
args.start_codon = ["ATG"]
args.stop_codon = ["TTA"]
args.cutoff_5utr = "p_0.5"
args.cutoff_intercds = "n_20"
args.cutoff_3utr = "n_11"
args.cutoff_inter = 50
args.cutoff_anti = 50
args.libs = ["frag:frag:1:a:+"]
args.merge_wigs = "wig_folder"
args.utr_detect = True
args.background = 10
args.print_all = True
sd.sorf_detection(fasta, srna_gff, inter_gff, tss_file, "wig_f_file",
"wig_r_file", "test_folder/test", args)
sd.get_coverage = copy.deepcopy(get_coverage)
sd.replicate_comparison = self.mock.mock_replicate_comparison
self.assertTrue(os.path.exists("test_folder/test_all.csv"))
self.assertTrue(os.path.exists("test_folder/test_all.gff"))
self.assertTrue(os.path.exists("test_folder/test_best.csv"))
self.assertTrue(os.path.exists("test_folder/test_best.gff"))
def _start_stop_codon(self, prefixs, args_sorf, log):
'''detect the sORF based on start and stop codon
and ribosome binding site'''
log.write("Running sORF_detection.py for detecting sORFs.\n")
log.write("The following files are generated:\n")
for prefix in prefixs:
print("Searching sORFs of {0}".format(prefix))
if self.srna_path is not None:
srna_file = os.path.join(self.srna_path,
"_".join([prefix, "sRNA.gff"]))
else:
srna_file = None
if self.tss_path is not None:
tss_file = os.path.join(self.tss_path,
"_".join([prefix, "TSS.gff"]))
else:
tss_file = None
sorf_detection(
os.path.join(self.fasta_path, prefix + ".fa"), srna_file,
os.path.join(args_sorf.out_folder,
"_".join([prefix, "inter.gff"])), tss_file,
os.path.join(args_sorf.wig_path,
"_".join([prefix, "forward.wig"])),
os.path.join(args_sorf.wig_path,
"_".join([prefix, "reverse.wig"])),
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF"])), args_sorf)
if "_".join([prefix, "sORF_all.gff"]) in os.listdir(
os.path.join(self.gff_output, self.all_cand)):
gff_all = os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF.gff"]))
gff_best = os.path.join(self.gff_output, self.best,
"_".join([prefix, "sORF.gff"]))
csv_all = os.path.join(self.table_output, self.all_cand,
"_".join([prefix, "sORF.csv"]))
csv_best = os.path.join(self.table_output, self.best,
"_".join([prefix, "sORF.csv"]))
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.gff"])), gff_all)
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.gff"])),
gff_best)
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.csv"])), csv_all)
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.csv"])),
csv_best)
log.write("\t" + gff_all + "\n")
log.write("\t" + gff_best + "\n")
log.write("\t" + csv_all + "\n")
log.write("\t" + csv_best + "\n")
def _start_stop_codon(self, prefixs, args_sorf, log):
'''detect the sORF based on start and stop codon
and ribosome binding site'''
log.write("Running sORF_detection.py for detecting sORFs.\n")
log.write("The following files are generated:\n")
for prefix in prefixs:
print("Searching sORFs of {0}".format(prefix))
if self.srna_path is not None:
srna_file = os.path.join(self.srna_path,
"_".join([prefix, "sRNA.gff"]))
else:
srna_file = None
if self.tss_path is not None:
tss_file = os.path.join(self.tss_path,
"_".join([prefix, "TSS.gff"]))
else:
tss_file = None
sorf_detection(os.path.join(self.fasta_path, prefix + ".fa"),
srna_file, os.path.join(args_sorf.out_folder,
"_".join([prefix, "inter.gff"])), tss_file,
os.path.join(args_sorf.wig_path,
"_".join([prefix, "forward.wig"])),
os.path.join(args_sorf.wig_path,
"_".join([prefix, "reverse.wig"])),
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF"])), args_sorf)
if "_".join([prefix, "sORF_all.gff"]) in os.listdir(
os.path.join(self.gff_output, self.all_cand)):
gff_all = os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF.gff"]))
gff_best = os.path.join(self.gff_output, self.best,
"_".join([prefix, "sORF.gff"]))
csv_all = os.path.join(self.table_output, self.all_cand,
"_".join([prefix, "sORF.csv"]))
csv_best = os.path.join(self.table_output, self.best,
"_".join([prefix, "sORF.csv"]))
shutil.move(os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.gff"])), gff_all)
shutil.move(os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.gff"])), gff_best)
shutil.move(os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.csv"])), csv_all)
shutil.move(os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.csv"])), csv_best)
log.write("\t" + gff_all + "\n")
log.write("\t" + gff_best + "\n")
log.write("\t" + csv_all + "\n")
log.write("\t" + csv_best + "\n")
def _start_stop_codon(self, prefixs, args_sorf):
'''detect the sORF based on start and stop codon
and ribosome binding site'''
for prefix in prefixs:
if self.srna_path is not None:
srna_file = os.path.join(self.srna_path,
"_".join([prefix, "sRNA.gff"]))
else:
srna_file = None
if self.tss_path is not None:
tss_file = os.path.join(self.tss_path,
"_".join([prefix, "TSS.gff"]))
else:
tss_file = None
sorf_detection(
os.path.join(self.fasta_path, prefix + ".fa"), srna_file,
os.path.join(args_sorf.out_folder,
"_".join([prefix, "inter.gff"])), tss_file,
os.path.join(args_sorf.wig_path,
"_".join([prefix, "forward.wig"])),
os.path.join(args_sorf.wig_path,
"_".join([prefix, "reverse.wig"])),
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF"])), args_sorf)
if "_".join([prefix, "sORF_all.gff"]) in os.listdir(
os.path.join(self.gff_output, self.all_cand)):
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.gff"])),
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF.gff"])))
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.gff"])),
os.path.join(self.gff_output, self.best,
"_".join([prefix, "sORF.gff"])))
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_all.csv"])),
os.path.join(self.table_output, self.all_cand,
"_".join([prefix, "sORF.csv"])))
shutil.move(
os.path.join(self.gff_output, self.all_cand,
"_".join([prefix, "sORF_best.csv"])),
os.path.join(self.table_output, self.best,
"_".join([prefix, "sORF.csv"])))