def run_sorf_detection(self, args_sorf, log):
if args_sorf.fuzzy_rbs > 6:
log.write("--fuzzy_rbs should be equal or less than 6!\n")
print("Error: --fuzzy_rbs should be equal or less than 6!")
sys.exit()
self._check_necessary_files(args_sorf, log)
self.multiparser.parser_gff(args_sorf.trans, "transcript")
self.multiparser.combine_gff(args_sorf.gffs, self.tran_path,
None, "transcript")
self.multiparser.parser_fasta(args_sorf.fastas)
self.multiparser.combine_fasta(args_sorf.gffs, self.fasta_path, None)
prefixs = self._compare_tran_cds(args_sorf, log)
self._start_stop_codon(prefixs, args_sorf, log)
log.write("Running stat_sorf.py to do statistics.\n")
for sorf in os.listdir(os.path.join(self.gff_output, self.all_cand)):
print("Running statistics of {0}".format(sorf))
if sorf.endswith("_sORF.gff"):
stat_file = os.path.join(args_sorf.out_folder, "statistics",
"_".join(["stat", sorf.replace(".gff", ".csv")]))
stat(os.path.join(self.gff_output, self.all_cand, sorf),
os.path.join(self.gff_output, self.best, sorf), stat_file,
args_sorf.utr_detect)
log.write("\t" + stat_file + " is generated.\n")
self._re_table(args_sorf, prefixs, log)
self._remove_tmp(args_sorf)
def run_sorf_detection(self, args_sorf, log):
if args_sorf.fuzzy_rbs > 6:
log.write("--fuzzy_rbs should be equal or less than 6!\n")
print("Error: --fuzzy_rbs should be equal or less than 6!")
sys.exit()
self._check_necessary_files(args_sorf, log)
self.multiparser.parser_gff(args_sorf.trans, "transcript")
self.multiparser.combine_gff(args_sorf.gffs, self.tran_path, None,
"transcript")
self.multiparser.parser_fasta(args_sorf.fastas)
self.multiparser.combine_fasta(args_sorf.gffs, self.fasta_path, None)
prefixs = self._compare_tran_cds(args_sorf, log)
self._start_stop_codon(prefixs, args_sorf, log)
log.write("Running stat_sorf.py to do statistics.\n")
for sorf in os.listdir(os.path.join(self.gff_output, self.all_cand)):
print("Running statistics of {0}".format(sorf))
if sorf.endswith("_sORF.gff"):
stat_file = os.path.join(
args_sorf.out_folder, "statistics",
"_".join(["stat", sorf.replace(".gff", ".csv")]))
stat(os.path.join(self.gff_output, self.all_cand, sorf),
os.path.join(self.gff_output, self.best, sorf), stat_file,
args_sorf.utr_detect)
log.write("\t" + stat_file + " is generated.\n")
self._re_table(args_sorf, prefixs, log)
self._remove_tmp(args_sorf)
def test_stat(self):
sorf_all = os.path.join(self.test_folder, "aaa_all.gff")
sorf_best = os.path.join(self.test_folder, "aaa_best.gff")
gen_file(sorf_all, self.example.sorf_all)
gen_file(sorf_best, self.example.sorf_best)
stat_file = os.path.join(self.test_folder, "stat")
ss.stat(sorf_all, sorf_best, stat_file, True)
datas = import_data(stat_file)
for data in datas:
if "total sORF in this strain are " in data:
self.assertEqual(data, "\ttotal sORF in this strain are 3")
if "total sORF of intergenic sORF candidates are " in data:
self.assertEqual(data,
("\ttotal sORF of intergenic sORF candidates "
"are 1(for this genome - "
"0.3333333333333333)"))
def test_stat(self):
sorf_all = os.path.join(self.test_folder, "aaa_all.gff")
sorf_best = os.path.join(self.test_folder, "aaa_best.gff")
gen_file(sorf_all, self.example.sorf_all)
gen_file(sorf_best, self.example.sorf_best)
stat_file = os.path.join(self.test_folder, "stat")
ss.stat(sorf_all, sorf_best, stat_file, True)
datas = import_data(stat_file)
for data in datas:
if "total sORF in this strain are " in data:
self.assertEqual(data, "\ttotal sORF in this strain are 3")
if "total sORF of intergenic sORF candidates are " in data:
self.assertEqual(data,
("\ttotal sORF of intergenic sORF candidates "
"are 1(for this genome - "
"0.3333333333333333)"))