def main():
sorfs = []
pres = []
num_ref = 0
detect = 0
for sorf in Gff3Parser().entries(open(args.benchmark_file)):
num_ref += 1
sorfs.append(sorf)
for pre in Gff3Parser().entries(open(args.predict_file)):
pres.append(pre)
for sorf in sorfs:
for pre in pres:
if pre.strand == sorf.strand:
if ((pre.start >= sorf.start) and (pre.end <= sorf.end)) or (
(pre.start <= sorf.start) and (pre.end >= sorf.end)) or (
(pre.start >= sorf.start) and
(pre.start <= sorf.end) and (pre.end >= sorf.end)) or (
(pre.start <= sorf.start) and
(pre.end >= sorf.start) and (pre.end <= sorf.end)):
detect += 1
sorf.attributes["detect"] = True
break
print("the number of known sORFs which can be detected by ANNOgesic:" +
str(detect))
print("the total number of known sORFs:" + str(num_ref))
print("the detection rate:" + str(float(detect) / float(num_ref)))
def main():
trans = {}
pres = []
total = 0
detect = 0
for entry in Gff3Parser().entries(open(args.predict_file)):
pres.append(entry)
fh = open(args.ecocyc_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if row[0] not in trans.keys():
total += 1
trans[row[0]] = {"start": int(row[1]), "end": int(row[2])}
else:
if int(row[1]) < trans[row[0]]["start"]:
trans[row[0]]["start"] = int(row[1])
if int(row[2]) > trans[row[0]]["end"]:
trans[row[0]]["end"] = int(row[2])
for ref in trans.values():
for pre in pres:
if ((pre.start >= ref["start"]) and (
pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and (
pre.start <= ref["end"]) and (
pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["start"]) and (
pre.end <= ref["end"])):
detect += 1
break
print("the number of published transcripts which can be detected by ANNOgesic:" + str(detect))
print("total number of transcripts in EcoCyc:" + str(total))
print("detection rate:" + str(float(detect)/float(total)))
def main():
terms = []
detect = 0
total = 0
fh = open(args.regulondb_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if row[3] == "forward":
strand = "+"
else:
strand = "-"
total += 1
terms.append({"id": row[0], "start": int(row[1]),
"end": int(row[2]), "strand": strand})
if row[3] == "both":
terms.append({"id": row[0], "start": int(row[1]),
"end": int(row[2]), "strand": "+"})
total += 1
for pre in Gff3Parser().entries(open(args.predict_file)):
for ref in terms:
if pre.strand == ref["strand"]:
if ((pre.start >= ref["start"]) and (
pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and (
pre.start <= ref["end"]) and (
pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["start"]) and (
pre.end <= ref["end"])):
detect += 1
break
print("the number of published terminators which can be detected by ANNOgesic:" + str(detect))
print("total number of terminators in RegulonDB:" + str(total))
print("detection rate:" + str(float(detect)/float(total)))
def main():
terms = []
detect = 0
total = 0
fh = open(args.ecocyc_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if len(row) >= 4:
total += 1
terms.append({"id": row[0], "start": int(row[1]),
"end": int(row[2])})
tot_term = 0
for pre in Gff3Parser().entries(open(args.predict_file)):
tot_term += 1
for ref in terms:
if ((pre.start >= ref["start"]) and (
pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and (
pre.start <= ref["end"]) and (
pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["start"]) and (
pre.end <= ref["end"])):
detect += 1
break
print("the number of published terminators can be detected by ANNOgesic:" + str(detect))
print("total number of terminators in EcoCyc:" + str(total))
print("detection rate:" + str(float(detect)/float(total)))
def main():
pros = {}
tsss = []
total = 0
detect = 0
for entry in Gff3Parser().entries(open(args.predict_file)):
tsss.append(entry)
fh = open(args.regulondb_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if (not row[0].startswith("#")) and (row[-1] != "weak"):
total += 1
if row[5] == "forward":
strand = "+"
else:
strand = "-"
pros[row[1]] = {"start": int(row[3]), "strand": strand}
for ref in pros.values():
for pre in tsss:
if pre.strand == ref["strand"]:
if (math.fabs(ref["start"] - pre.start) <= args.fuzzy):
detect += 1
break
print("the number of published TSSs which can be detected by ANNOgesic:" + str(detect))
print("the total number of TSSs from Mendoza-Vargas in Regulon DB" + str(total))
print("detection rate:" + str(float(detect)/float(total)))
def main():
pres = []
for entry in Gff3Parser().entries(open(args.predict_file)):
pres.append(entry)
refs = []
num_ref = 0
# fh = open(args.refseq_file, "r")
# for row in csv.reader(fh, delimiter='\t'):
# num_ref += 1
# refs.append({"start": int(row[0]), "end": int(row[1]), "strand": row[2]})
for entry in Gff3Parser().entries(open(args.refseq_file)):
if entry.feature == "ncRNA":
num_ref += 1
refs.append(entry)
detect = 0
for ref in refs:
for pre in pres:
# if pre.strand == ref["strand"]:
# if ((pre.start >= ref["start"]) and (
# pre.end <= ref["end"])) or (
# (pre.start <= ref["start"]) and (
# pre.end >= ref["end"])) or (
# (pre.start >= ref["start"]) and (
# pre.start <= ref["end"]) and (
# pre.end >= ref["end"])) or (
# (pre.start <= ref["start"]) and (
# pre.end >= ref["start"]) and (
# pre.end <= ref["end"])):
if pre.strand == ref.strand:
if ((pre.start >= ref.start) and (pre.end <= ref.end)) or (
(pre.start <= ref.start) and (pre.end >= ref.end)) or (
(pre.start >= ref.start) and (pre.start <= ref.end) and
(pre.end >= ref.end)) or ((pre.start <= ref.start) and
(pre.end >= ref.start) and
(pre.end <= ref.end)):
detect += 1
break
print("the number of published sRNAs which can be detected by ANNOgesic:" +
str(detect))
print("total number of sRNAs in RefSeq:" + str(num_ref))
print("detection rate:" + str(float(detect) / float(num_ref)))
def main():
pros = {}
tsss = []
total = 0
detect = 0
for entry in Gff3Parser().entries(open(args.predict_file)):
tsss.append(entry)
refs = []
fh = open(args.regulondb_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if not row[0].startswith("#"):
if row[5] == "forward":
strand = "+"
else:
strand = "-"
total += 1
refs.append({"start": int(row[0]),
"end": int(row[1]), "strand": strand})
for ref in refs:
ref["start"] = ref["start"] - args.fuzzy
ref["end"] = ref["end"] + args.fuzzy
for pre in tsss:
if pre.strand == ref["strand"]:
if ((pre.start >= ref["start"]) and (
pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and (
pre.start <= ref["end"]) and (
pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and (
pre.end >= ref["start"]) and (
pre.end <= ref["end"])):
detect += 1
break
print("the number of reported TSSs which can be detected by ANNOgesic:" + str(detect))
print("total number of TSSs from Salgado et. al in RegulonDB:" + str(detect))
print("detection rate:" + str(float(detect)/float(total)))
def main():
utr5s = {}
utr3s = {}
detect5 = 0
detect3 = 0
total5 = 0
total3 = 0
fh = open(args.regulondb_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if not row[0].startswith("#"):
if row[4] == "forward":
strand = "+"
else:
strand = "-"
if len(row[9]) != 0:
if row[0] not in utr5s.keys():
total5 += 1
start = int(row[9].split("-")[0])
end = int(row[9].split("-")[-1])
utr5s[row[0]] = {
"start": start,
"end": end,
"strand": strand
}
else:
start = int(row[9].split("-")[0])
end = int(row[9].split("-")[-1])
if start < utr5s[row[0]]["start"]:
utr5s[row[0]]["start"] = start
if end < utr5s[row[0]]["end"]:
utr5s[row[0]]["end"] = end
if len(row[11]) != 0:
if row[0] not in utr3s.keys():
total3 += 1
start = int(row[11].split("-")[0])
end = int(row[11].split("-")[-1])
utr3s[row[0]] = {
"start": start,
"end": end,
"strand": strand
}
else:
start = int(row[11].split("-")[0])
end = int(row[11].split("-")[-1])
if start < utr3s[row[0]]["start"]:
utr3s[row[0]]["start"] = start
if end < utr3s[row[0]]["end"]:
utr3s[row[0]]["end"] = end
for pre in Gff3Parser().entries(open(args.predict5_file)):
for ref in utr5s.values():
if pre.strand == ref["strand"]:
if ((pre.start >= ref["start"]) and
(pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and
(pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and
(pre.start <= ref["end"]) and
(pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and
(pre.end >= ref["start"]) and
(pre.end <= ref["end"])):
detect5 += 1
break
for pre in Gff3Parser().entries(open(args.predict3_file)):
for ref in utr3s.values():
if pre.strand == ref["strand"]:
if ((pre.start >= ref["start"]) and
(pre.end <= ref["end"])) or (
(pre.start <= ref["start"]) and
(pre.end >= ref["end"])) or (
(pre.start >= ref["start"]) and
(pre.start <= ref["end"]) and
(pre.end >= ref["end"])) or (
(pre.start <= ref["start"]) and
(pre.end >= ref["start"]) and
(pre.end <= ref["end"])):
detect3 += 1
break
print(
"the number of published 5'UTRs which can be detected by ANNOgesic:" +
str(detect5))
print(
"the number of published 5'UTRs which can be detected by ANNOgesic:" +
str(detect3))
print("total number of 5'UTRs in RegulonDB:" + str(total5))
print("total number of 5'UTRs in RegulonDB:" + str(total3))
print("detection rate:" + str(float(detect5) / float(total5)))
print("detection rate:" + str(float(detect3) / float(total3)))
editable=True, height=4000, width=5000)
return data_table
def main():
gos = {}
goh = open(args.go_file, "r")
for row in csv.reader(goh, delimiter='\t'):
gos[row[0]] = row[1].split(";")
genes = []
names = {}
srnas = []
nh = open(args.name_file, "r")
for row in csv.reader(nh, delimiter='\t'):
names[row[0]] = row[3]
gh = open(args.gff_file, "r")
for entry in Gff3Parser().entries(gh):
if entry.feature == "gene":
genes.append(entry)
elif entry.feature == "ncRNA":
srnas.append(entry)
for srna in srnas:
members = {"role": [], "feature": [], "start": [], "end": [],
"strand": [], "link": [], "gene_name": [], "GO": [],
"cc": [], "pMEM_OD_0.2": [], "pMEM_OD_0.5": [],
"pMEM_OD_1": [], "pMEM_t0": [], "pMEM_t1": [], "pMEM_t2": [],
"pMEM_ON": [], "TSB_OD_0.2": [], "TSB_OD_0.5": [],
"TSB_OD_1": [], "TSB_t0": [], "TSB_t1": [], "TSB_t2": [],
"TSB_ON": []}
exps ={}
infos = []
print("_".join([srna.feature, str(srna.start),
def main():
gffs = {}
names = {}
quants = []
if args.features == "all":
output_file("main.html", mode='inline')
data = {"link": [], "features": [], "start": [], "end": [], "strand": [],
"gene_name": [], "pMEM_OD_0.2": [], "pMEM_OD_0.5": [],
"pMEM_OD_1": [], "pMEM_t0": [], "pMEM_t1": [], "pMEM_t2": [],
"pMEM_ON": [], "TSB_OD_0.2": [], "TSB_OD_0.5": [],
"TSB_OD_1": [], "TSB_t0": [], "TSB_t1": [], "TSB_t2": [],
"TSB_ON": [], "pMEM_OD_0.2_TEX": [], "pMEM_OD_0.5_TEX": [],
"pMEM_OD_1_TEX": [], "pMEM_t0_TEX": [], "pMEM_t1_TEX": [],
"pMEM_t2_TEX": [], "pMEM_ON_TEX": [], "TSB_OD_0.2_TEX": [],
"TSB_OD_0.5_TEX": [], "TSB_OD_1_TEX": [], "TSB_t0_TEX": [],
"TSB_t1_TEX": [], "TSB_t2_TEX": [], "TSB_ON_TEX": [],
"frag": [], "tss": [], "ps": [], "term": [], "tran": []}
nh = open(args.name_file, "r")
for row in csv.reader(nh, delimiter='\t'):
names[row[0]] = row[3]
fh = open(args.gene_quanti_file, "r")
for row in csv.reader(fh, delimiter='\t'):
if not row[0].startswith("Orientation"):
quants.append(row)
gff_f = open(args.input_file, "r")
for entry in Gff3Parser().entries(gff_f):
if entry.feature not in gffs.keys():
gffs[entry.feature] = []
gffs[entry.feature].append(entry)
for feature in gffs.keys():
if (feature == args.features) or (args.features == "all"):
if feature == "riboswitch":
gen_html("riboswitch.html")
get_rfam_info(gffs["riboswitch"], gffs, data, quants,
"riboswitch")
elif feature == "RNA_thermometer":
gen_html("RNA_thermometer.html")
get_rfam_info(gffs["RNA_thermometer"], gffs, data,
quants, "RNA_thermometer")
elif feature == "CRISPR":
gen_html("CRISPR.html")
get_crispr_info(gffs["CRISPR"], gffs, data, quants)
elif feature == "tRNA":
gen_html("tRNA.html")
get_rna_info(gffs["tRNA"], gffs, data, quants, "tRNA")
elif feature == "rRNA":
gen_html("rRNA.html")
get_rna_info(gffs["rRNA"], gffs, data, quants, "rRNA")
elif feature == "sORF":
gen_html("sORF.html")
get_sorf_info(gffs["sORF"], gffs, data, quants)
elif feature == "ncRNA":
gen_html("ncRNA.html")
get_srna_info(gffs["ncRNA"], gffs, data, quants)
elif feature == "CDS":
gen_html("CDS.html")
get_cds_info(gffs["CDS"], gffs, data, quants, names)
source = ColumnDataSource(data)
columns = gen_column()
data_table = DataTable(source=source, columns=columns, height=3000, width=6000)
save(widgetbox(data_table))