def Main():
'''
IO TEMPLATE
'''
global args,out
args=ParseArg()
fin=IO.fopen(args.input,"r")
out=IO.fopen(args.output,"w")
'''
END OF IO TEMPLATE
'''
print >>out,"# This data was generated by program ",sys.argv[0]," (version: %s)"%VERSION,
print >>out,"in bam2x ( https://github.com/nimezhu/bam2x )"
print >>out,"# Date: ",time.asctime()
print >>out,"# The command line is :"
print >>out,"#\t"," ".join(sys.argv)
dbi=DBI.init(args.db,Tools.guess_format(args.db))
references=dbi.bamfiles[0].references
for i in TableIO.parse(fin,args.format):
print i
n=0
c_count=0
reads=dbi.query(i,args.method)
for read in reads:
compatible=Tools.compatible_with_transcript(read,i,references=references,strand=args.strand)
print "HT:"
for i0,r in enumerate(TableIO.parse(read.reads,"bam2bed12",references=references)):
print "READ"+str(i0)+"\t",r
print "COMPATIBLE:",compatible,"\n\n"
if compatible: c_count+=1
n+=1
print "COMPATIBLE / ALL OVERLAP READS = ",c_count,"/",n
print "RATIO\t%.4f"%float(c_count)/n
def fopen(file,mode="r",**kwargs):
'''
'''
if Tools.guess_format(file)=="bam" and mode=="r":
return pysam.Samfile(file,"rb")
if mode=="w":
return open_output(file)
if mode=="r":
return open_input(file)
return None
def fopen(file, mode="r", **kwargs):
'''
'''
if Tools.guess_format(file) == "bam" and mode == "r":
return pysam.Samfile(file, "rb")
if mode == "w":
return open_output(file)
if mode == "r":
return open_input(file)
return None
def Main():
'''
This program is a test for TableIO.parse(file.bam,"bam2bed")
'''
global args,out
args=ParseArg()
fin=IO.fopen(args.input,"r")
out=IO.fopen(args.output,"w")
if args.format=="guess":
args.format=Tools.guess_format(args.input)
s=TableIO.parse(args.input,args.format)
for i in s:
print >>out,i
def Main():
'''
IO TEMPLATE
'''
global args, out
args = ParseArg()
fin = IO.fopen(args.input, "r")
out = IO.fopen(args.output, "w")
'''
END OF IO TEMPLATE
'''
print >> out, "# This data was generated by program ", sys.argv[
0], " (version: %s)" % VERSION,
print >> out, "in bam2x ( https://github.com/nimezhu/bam2x )"
print >> out, "# Date: ", time.asctime()
print >> out, "# The command line is :"
print >> out, "#\t", " ".join(sys.argv)
dbi = DBI.init(args.db, Tools.guess_format(args.db))
references = dbi.bamfiles[0].references
for i in TableIO.parse(fin, args.format):
print i
n = 0
c_count = 0
reads = dbi.query(i, args.method)
for read in reads:
compatible = Tools.compatible_with_transcript(
read, i, references=references, strand=args.strand)
print "HT:"
for i0, r in enumerate(
TableIO.parse(read.reads,
"bam2bed12",
references=references)):
print "READ" + str(i0) + "\t", r
print "COMPATIBLE:", compatible, "\n\n"
if compatible: c_count += 1
n += 1
print "COMPATIBLE / ALL OVERLAP READS = ", c_count, "/", n
print "RATIO\t%.4f" % float(c_count) / n
def Main():
global args,out
args=ParseArg()
dict={}
if args.output=="stdout":
out=sys.stdout
else:
try:
out=open(args.output,"w")
except IOError:
print >>sys.stderr,"can't open file ",args.output,"to write. Using stdout instead"
out=sys.stdout
argv=sys.argv
argv[0]=argv[0].split("/")[-1]
print >>out,"# This data was generated by program ",argv[0],"(version %s)"%VERSION,
print >>out,"in bam2x ( https://github.com/nimezhu/bam2x )"
print >>out,"# Date: ",time.asctime()
print >>out,"# The command line is :\n#\t"," ".join(argv)
init_dict={}
if args.dbformat=="guess":
if Tools.suffix(args.db)=="gz":
args.dbformat="tabix"
args.tabix_format=Tools.guess_format(args.db)
else:
args.dbformat=Tools.guess_format(args.db)
if args.query_method:
dict["method"]=args.query_method
if args.tabix_format:
init_dict["tabix"]=args.tabix_format
dbi=DBI.init(args.db,args.dbformat,**init_dict)
hits=0
query=0
if args.input=="stdin":
input=sys.stdin
else:
input=args.input
query_length=0
hits_number=0
if (args.input_format=="guess"):
args.input_format=Tools.guess_format(args.input)
for (i0,x) in enumerate(TableIO.parse(input,args.input_format)):
if i0%100==0:
print >>sys.stderr,"query ",i0," entries\r",
print >>out,"QR\t",x
hit=0
query+=1
query_length+=len(x)
#print dbi;#debug
results=dbi.query(x,**dict)
#results=dbi.query(x) #DEBUG
#print >>sys.stderr,type(results)
if isinstance(results,numpy.ndarray) or isinstance(results,list):
print >>out,"HT\t",
for value in results:
print >>out,str(value)+",",
print >>out,""
hit=1
hits_number+=1
elif isinstance(results,str):
print >>out,"HT\t",
print >>out,results
hit=1
hits_number+=1
else:
for j in results:
print >>out,"HT\t",j
hit=1
hits_number+=1
if args.dbformat=="tabix":
x.chr=x.chr.replace("chr","")
for j in dbi.query(x,**dict):
print >>out,"HT\t",j
hit=1
hits_number+=1
hits+=hit
print >>out,"# Query Number:",query,"\n# Query Have Hits:",hits
print >>out,"# Query Length:",query_length
print >>out,"# Hits Number:",hits_number
def Main():
global args, out
args = ParseArg()
dict = {}
if args.output == "stdout":
out = sys.stdout
else:
try:
out = open(args.output, "w")
except IOError:
print >> sys.stderr, "can't open file ", args.output, "to write. Using stdout instead"
out = sys.stdout
argv = sys.argv
argv[0] = argv[0].split("/")[-1]
print >> out, "# This data was generated by program ", argv[
0], "(version %s)" % VERSION,
print >> out, "in bam2x ( https://github.com/nimezhu/bam2x )"
print >> out, "# Date: ", time.asctime()
print >> out, "# The command line is :\n#\t", " ".join(argv)
init_dict = {}
if args.dbformat == "guess":
if Tools.suffix(args.db) == "gz":
args.dbformat = "tabix"
args.tabix_format = Tools.guess_format(args.db)
else:
args.dbformat = Tools.guess_format(args.db)
if args.query_method:
dict["method"] = args.query_method
if args.tabix_format:
init_dict["tabix"] = args.tabix_format
dbi = DBI.init(args.db, args.dbformat, **init_dict)
hits = 0
query = 0
if args.input == "stdin":
input = sys.stdin
else:
input = args.input
query_length = 0
hits_number = 0
if (args.input_format == "guess"):
args.input_format = Tools.guess_format(args.input)
for (i0, x) in enumerate(TableIO.parse(input, args.input_format)):
if i0 % 100 == 0:
print >> sys.stderr, "query ", i0, " entries\r",
print >> out, "QR\t", x
hit = 0
query += 1
query_length += len(x)
#print dbi;#debug
results = dbi.query(x, **dict)
#results=dbi.query(x) #DEBUG
#print >>sys.stderr,type(results)
if isinstance(results, numpy.ndarray) or isinstance(results, list):
print >> out, "HT\t",
for value in results:
print >> out, str(value) + ",",
print >> out, ""
hit = 1
hits_number += 1
elif isinstance(results, str):
print >> out, "HT\t",
print >> out, results
hit = 1
hits_number += 1
else:
for j in results:
print >> out, "HT\t", j
hit = 1
hits_number += 1
if args.dbformat == "tabix":
x.chr = x.chr.replace("chr", "")
for j in dbi.query(x, **dict):
print >> out, "HT\t", j
hit = 1
hits_number += 1
hits += hit
print >> out, "# Query Number:", query, "\n# Query Have Hits:", hits
print >> out, "# Query Length:", query_length
print >> out, "# Hits Number:", hits_number
def Main():
'''
IO TEMPLATE
'''
global args,out
args=ParseArg()
if args.output=="stdout":
out=sys.stdout
else:
try:
out=open(args.output,"w")
except IOError:
print >>sys.stderr,"can't open file ",args.output,"to write. Using stdout instead"
out=sys.stdout
if args.input=="stdin":
fin=sys.stdin
else:
try:
x=args.input.split(".")
if x[-1]=="gz":
fin=gzip.open(args.input,"r")
else:
fin=open(args.input,"r")
except IOError:
print >>sys.stderr,"can't read file",args.input
fin=sys.stdin
'''
END OF IO TEMPLATE
'''
print >>out,"# This data was generated by program ",sys.argv[0]," (version: %s)"%VERSION,
print >>out,"in bam2x ( https://github.com/nimezhu/bam2x )"
print >>out,"# Date: ",time.asctime()
print >>out,"# The command line is :"
print >>out,"#\t"," ".join(sys.argv)
gene=DBI.init(args.genetab,args.gene_format);
upstream_list=[]
downstream_list=[]
exons_list=[]
introns_list=[]
utr3_list=[]
utr5_list=[]
for g in gene:
upstream_list.append(g.upstream(args.upstream));
downstream_list.append(g.downstream(args.downstream));
for e in g.Exons():
exons_list.append(e)
for i in g.Introns():
introns_list.append(i)
if not (g.utr3() is None):
utr3_list.append(g.utr3())
if not (g.utr5() is None):
utr5_list.append(g.utr5())
upstream=DBI.init(upstream_list,"bed")
downstream=DBI.init(downstream_list,"bed")
exons=DBI.init(exons_list,"bed")
introns=DBI.init(introns_list,"bed")
utr3=DBI.init(utr3_list,"genebed")
utr5=DBI.init(utr5_list,"genebed")
if args.format=="guess":
args.format=Tools.guess_format(args.input)
for (i0,i) in enumerate(TableIO.parse(fin,args.format)):
if i0==0:
if isinstance(i,Bed12):
print >>out,"#chr\tstart\tend\tname\tscore\tstrand\tthick_start\tthick_end\titem_rgb\tblock_count\tblock_sizes\tblock_starts\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
elif isinstance(i,GeneBed):
print >>out,"#name\tchr\tstrand\tstart\tend\tcds_start\texon_count\texon_starts\texont_ends\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
else:
print >>out,"#chr\tstart\tend\tname\tscore\tstrand\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
print >>out,i,
print >>out,"\t",toIDs(gene.query(i)),
print >>out,"\t",toIDs(upstream.query(i)),
print >>out,"\t",toIDs(downstream.query(i)),
print >>out,"\t",toIDs(exons.query(i)),
print >>out,"\t",toIDs(introns.query(i)),
print >>out,"\t",toIDs(utr3.query(i)),
print >>out,"\t",toIDs(utr5.query(i))
def Main():
"""
IO TEMPLATE
"""
global args, out
args = ParseArg()
if args.output == "stdout":
out = sys.stdout
else:
try:
out = open(args.output, "w")
except IOError:
print >>sys.stderr, "can't open file ", args.output, "to write. Using stdout instead"
out = sys.stdout
if args.input == "stdin":
fin = sys.stdin
else:
try:
x = args.input.split(".")
if x[-1] == "gz":
fin = gzip.open(args.input, "r")
else:
fin = open(args.input, "r")
except IOError:
print >>sys.stderr, "can't read file", args.input
fin = sys.stdin
"""
END OF IO TEMPLATE
"""
print >> out, "# This data was generated by program ", sys.argv[0], " (version: %s)" % VERSION,
print >> out, "in bam2x ( https://github.com/nimezhu/bam2x )"
print >> out, "# Date: ", time.asctime()
print >> out, "# The command line is :"
print >> out, "#\t", " ".join(sys.argv)
gene = DBI.init(args.genetab, args.gene_format)
upstream_list = []
downstream_list = []
exons_list = []
introns_list = []
utr3_list = []
utr5_list = []
for g in gene:
upstream_list.append(g.upstream(args.upstream))
downstream_list.append(g.downstream(args.downstream))
for e in g.Exons():
exons_list.append(e)
for i in g.Introns():
introns_list.append(i)
if not (g.utr3() is None):
utr3_list.append(g.utr3())
if not (g.utr5() is None):
utr5_list.append(g.utr5())
upstream = DBI.init(upstream_list, "bed")
downstream = DBI.init(downstream_list, "bed")
exons = DBI.init(exons_list, "bed")
introns = DBI.init(introns_list, "bed")
utr3 = DBI.init(utr3_list, "genebed")
utr5 = DBI.init(utr5_list, "genebed")
if args.format == "guess":
args.format = Tools.guess_format(args.input)
for (i0, i) in enumerate(TableIO.parse(fin, args.format)):
if i0 == 0:
if isinstance(i, Bed12):
print >> out, "#chr\tstart\tend\tname\tscore\tstrand\tthick_start\tthick_end\titem_rgb\tblock_count\tblock_sizes\tblock_starts\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
elif isinstance(i, GeneBed):
print >> out, "#name\tchr\tstrand\tstart\tend\tcds_start\texon_count\texon_starts\texont_ends\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
else:
print >> out, "#chr\tstart\tend\tname\tscore\tstrand\tgene\tupstream\tdownstream\texon\tintron\tutr3\tutr5"
print >> out, i,
print >> out, "\t", toIDs(gene.query(i)),
print >> out, "\t", toIDs(upstream.query(i)),
print >> out, "\t", toIDs(downstream.query(i)),
print >> out, "\t", toIDs(exons.query(i)),
print >> out, "\t", toIDs(introns.query(i)),
print >> out, "\t", toIDs(utr3.query(i)),
print >> out, "\t", toIDs(utr5.query(i))
