def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta [can be gzipped]" )
parser.add_option("-i", dest="fpath",
help="input file [stdin]")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=10, type=int,
help="minimal depth [%default]")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# parse pileup
parse_vcf( o.fpath,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def main():
usage = "usage: %prog [options]"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta [can be gzipped]" )
parser.add_option("-i", dest="fpath",
help="input file [stdin]")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=10, type=int,
help="minimal depth [%default]")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# parse pileup
parse_vcf( o.fpath,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def get_options():
'''
subroutine to capture the optional inputs
'''
from os import remove as rmfile
from optparse import OptionParser, OptionGroup
parser = OptionParser(usage="Usage: %prog [options] <station list filename>", \
description="Program to query a datacenter using the obspy fdsn client. " \
"All station returned in this query are saved into both a csv format 1sls " \
"file as well as a stationdb (stdb.StDbElement) pickled dictionary. The input " \
"argument, <station file name> is the prefix for the output file, which is by " \
"default <station file name>.csv and <station file name>.pkl.")
# General Settings
parser.add_option("-D", "--debug", action="store_true", dest="debug", default=False, \
help="Debug mode. After the client query is complete (and successful), instead of " \
"parsing the inventory, it is instead pickled to <station file name>_query_debug.pkl " \
"which can be loaded in ipython to examine manually.")
parser.add_option("--long-keys", action="store_true", dest="lkey", default=False, \
help="Specify Key format. Default is Net.Stn. Long keys are Net.Stn.Chn")
parser.add_option("-a", "--ascii", action="store_false", dest="use_binary", default=True, \
help="Specify to write ascii Pickle files instead of binary. Ascii are larger file size, " \
"but more likely to be system independent.")
# Server Settings
ServerGroup = OptionGroup(parser, title="Server Settings", description="Settings associated with " \
"which datacenter to log into.")
ServerGroup.add_option("--Server", action="store", type=str, dest="Server", default="IRIS", \
help="Specify the server to connect to. Options include: BGR, ETH, GEONET, GFZ, INGV, IPGP, " \
"IRIS, KOERI, LMU, NCEDC, NEIP, NERIES, ODC, ORFEUS, RESIF, SCEDC, USGS, USP. [Default IRIS]")
ServerGroup.add_option("--User-Auth", action="store", type=str, dest="UserAuth", default="", \
help="Enter your IRIS Authentification Username and Password (--User-Auth='username:authpassword') " \
"to access and download restricted data. [Default no user and password]")
# Selection Settings
SelectGroup = OptionGroup(parser, title="Channel Priority/Selection Settings", description="Settings " \
"associated with selecting the channels to retain.")
SelectGroup.add_option("--channel-rank", action="store", type=str, dest="chnrank", default="HH,BH,LH", \
help="If requesting more than one type of channel, specify a comma separated list of the first two " \
"lettres of the desired components to retain. Default is HH > BH > LH : ['HH,BH,LH']")
# Channel Settings
ChannelGroup=OptionGroup(parser, title="Station-Channel Settings", description="Options to narrow down " \
"the specific channels based on network, station, etc")
ChannelGroup.add_option("-N","--networks", action="store", type=str, dest="nets", default="*", \
help="Specify a comma separated list of network codes to search for [Default *]")
ChannelGroup.add_option("-S","--stations", action="store", type=str, dest="stns", default="*", \
help="Specify a comma separated list of station names. If you want wildcards, enclose in quotes [Default *]")
ChannelGroup.add_option("-L","--locations", action="store", type=str, dest="locs", default="*", \
help="Specify a comma separated list of location codes. If you want wildcards, enclose in quotes [Default *]")
ChannelGroup.add_option("-C","--channels", action="store", type=str, dest="chns", default="HH*,BH*,LH*", \
help="Specify a comma separated, wildcarded list of channel names. [Default HH*,BH*,LH*]")
# Geographic Settings
BoxGroup = OptionGroup(parser, title="Geographic Lat/Lon Box Search", description="Define the coordinates " \
"of a lat/lon box in which to select stations. If filled out, takes precedence over values for " \
"Radius Search (below).")
BoxGroup.add_option("--minlat","--min-latitude", action="store", type="float", dest="minlat", default=None, \
help="Specify minimum latitude to search (must specify all of minlat, maxlat, minlon, maxlon).")
BoxGroup.add_option("--maxlat","--max-latitude", action="store", type="float", dest="maxlat", default=None, \
help="Specify maximum latitude to search (must specify all of minlat, maxlat, minlon, maxlon).")
BoxGroup.add_option("--minlon","--min-longitude", action="store", type="float", dest="minlon", default=None, \
help="Specify minimum longitude to search (must specify all of minlat, maxlat, minlon, maxlon).")
BoxGroup.add_option("--maxlon","--max-longitude", action="store", type="float", dest="maxlon", default=None, \
help="Specify maximum longitude to search (must specify all of minlat, maxlat, minlon, maxlon).")
RadGroup=OptionGroup(parser, title="Geographic Radius Search", description="Central point and min/max " \
"radius search settings. Box Search Settings take precedence over radius search.")
RadGroup.add_option("--lat","--latitude", action="store", type="float", dest="lat", default=None, \
help="Specify a Lat (if any of --lon --min-radius and --max-radius are empty, an error will prompt).")
RadGroup.add_option("--lon","--longitude", action="store", type="float", dest="lon", default=None, \
help="Specify a Lon (if any of --lat --min-radius and --max-radius are empty, an error will prompt).")
RadGroup.add_option("--minr","--min-radius", action="store", type="float", dest="minr", default=0., \
help="Specify a minimum search radius (in degrees) around the point defined by --lat and --lon " \
"(if any of --lat --lon and --max-radius are empty, an error will prompt). [Default 0. degrees]")
RadGroup.add_option("--maxr","--max-radius", action="store", type="float", dest="maxr", default=None, \
help="Specify a maximum search radius (in degrees) around the point defined by --lat and --lon " \
"(if any of --lat --lon and --min-radius are empty, an error will prompt).")
# Temporal Settings
FixedRangeGroup = OptionGroup(parser, title="Fixed Time Range Settings", description="Find all stations " \
"operating within the start and end date/time. If either are filled out, they take precedence over " \
"Non-Specific time range search (below)")
FixedRangeGroup.add_option("--start","--start-date", action="store", type=None, dest="stdate", default=None, \
help="Specify the Start Date/Time in a UTCDateTime compatible String (ie, 2010-01-15 15:15:45.2). [Default Blank]")
FixedRangeGroup.add_option("--end","--end-date", action="store", type=None, dest="enddate", default=None, \
help="Specify the End Date/Time in a UTCDateTime compatible String (ie, 2010-01-15 15:15:45.2). [Default Blank]")
VarRangeGroup = OptionGroup(parser, title="Non-Specific Time Range Settings", description="Time settings " \
"with less specificity. Ensure that those you specify do not interfere with each other. If above Fixed " \
"Range values are set, they will take precedence over these values.")
VarRangeGroup.add_option("--start-before", action="store", type=None, dest="stbefore", default=None, \
help="Specify a Date/Time which stations must start before (must be UTCDateTime compatible string, " \
"ie 2010-01-15 15:15:45.2). [Default empty]")
VarRangeGroup.add_option("--start-after", action="store", type=None, dest="stafter", default=None, \
help="Specify a Date/Time which stations must start after (must be UTCDateTime compatible string, " \
"ie 2010-01-15 15:15:45.2). [Default empty]")
VarRangeGroup.add_option("--end-before", action="store", type=None, dest="endbefore", default=None, \
help="Specify a Date/Time which stations must end before (must be UTCDateTime compatible string, " \
"ie 2010-01-15 15:15:45.2). [Default empty]")
VarRangeGroup.add_option("--end-after", action="store", type=None, dest="endafter", default=None, \
help="Specify a Date/Time which stations must end after (must be UTCDateTime compatible string, " \
"ie 2010-01-15 15:15:45.2). [Default empty]")
# Add All Groups
parser.add_option_group(ServerGroup)
parser.add_option_group(SelectGroup)
parser.add_option_group(ChannelGroup)
parser.add_option_group(BoxGroup)
parser.add_option_group(RadGroup)
parser.add_option_group(FixedRangeGroup)
parser.add_option_group(VarRangeGroup)
# Run Parser
(opts, args) = parser.parse_args()
# Check output file name
if len(args) != 1: parser.error("Need station database file")
outpref = args[0]
if not opts.debug:
if exists(outpref + ".csv") and exists(outpref + ".pkl"):
print ("Warning: Output Files " + outpref + ".csv and " + outpref + \
".pkl already exist. These will be overwritten...")
rmfile(outpref + ".pkl")
rmfile(outpref + ".csv")
elif exists(outpref + ".csv"):
print("Warning: Output File " + outpref +
".csv already exists. It will be overwritten...")
rmfile(outpref + ".csv")
elif exists(outpref + ".pkl"):
print("Warning: Output File " + outpref +
".pkl already exists. It will be overwritten...")
rmfile(outpref + ".pkl")
# Parse User Authentification
if not len(opts.UserAuth) == 0:
tt = opts.UserAuth.split(':')
if not len(tt) == 2:
parser.errer(
"Error: Incorrect Username and Password Strings for User Authentification"
)
else:
opts.UserAuth = tt
else:
opts.UserAuth = []
# Parse Channel Rank to List
opts.chnrank = opts.chnrank.split(',')
# Check Geographic Settings
if opts.minlat is not None or opts.maxlat is not None or opts.minlon is not None or opts.maxlon is not None:
if opts.minlat is None or opts.maxlat is None or opts.minlon is None or opts.maxlon is None:
# Not all value set
opts.minlat = None
opts.maxlat = None
opts.minlon = None
opts.maxlon = None
print(
"Warning: one of minlat,maxlat,minlon,maxlon were not set. All values reset to None. "
)
print("")
else:
# Ensure proper min/max set
tempminlat = min([opts.minlat, opts.maxlat])
tempmaxlat = max([opts.minlat, opts.maxlat])
opts.minlat = tempminlat
opts.maxlat = tempmaxlat
tempminlon = min([opts.minlon, opts.maxlon])
tempmaxlon = max([opts.minlon, opts.maxlon])
opts.minlon = tempminlon
opts.maxlon = tempmaxlon
print("Performing Geographic Box Search:")
print(" LL: {0:9.4f}, {1:8.4f}".format(opts.minlat,
opts.minlon))
print(" UR: {0:9.4f}, {1:8.4f}".format(opts.maxlat,
opts.maxlon))
print(" ")
# set all other box parameters to none
opts.minr = None
opts.maxr = None
opts.lat = None
opts.lon = None
elif opts.lat is not None or opts.lon is not None or opts.minr is not None or opts.maxr is not None:
if opts.lat is None or opts.lon is None or opts.minr is None or opts.maxr is None:
opts.lat = None
opts.lon = None
opts.minr = None
opts.maxr = None
print(
"Warning: one of lat,lon,minr,maxr were not set. All values reset to None. "
)
print(" ")
else:
# Ensure minr/maxr set
opts.minr = min([opts.minr, opts.maxr])
opts.maxr = max([opts.minr, opts.maxr])
print("Performing Geographic Radius Search: ")
print(" Centre Point: {0:9.4f}, {1:8.4f}".format(
opts.lon, opts.lat))
print(" Radius: {0:6.2f} to {1:6.2f} degrees".format(
opts.minr, opts.maxr))
print(" ")
# Check Time Settings
if opts.stdate is not None or opts.enddate is not None:
# Use Fixed Range, not other
opts.stbefore = None
opts.stafter = None
opts.endbefore = None
opts.endafter = None
# Fix End Date
if opts.enddate is None:
opts.enddate = UTCDateTime("2599-12-31 23:59:59.9")
else:
opts.enddate = UTCDateTime(opts.enddate)
# Assign stdate as UTCDateTime
if opts.stdate is not None:
opts.stdate = UTCDateTime(opts.stdate)
print("Performing Fixed Time Range Search: ")
print(" Start: " + opts.stdate.strftime("%Y-%m-%d %H:%M:%S"))
print(" End: " + opts.enddate.strftime("%Y-%m-%d %H:%M:%S"))
print(" ")
else:
# No Fixed Range Set. Are other values set?
if opts.stbefore is not None or opts.stafter is not None or opts.endbefore is not None or opts.endafter is not None:
print("Performing Non-Specific Time Search: ")
if opts.stbefore is not None:
opts.stbefore = UTCDateTime(opts.stbefore)
print(" Start Before: " +
opts.stbefore.strftime("%Y-%m-%d %H:%M:%S"))
if opts.stafter is not None:
opts.stafter = UTCDateTime(opts.stafter)
print(" Start After: " +
opts.stafter.strftime("%Y-%m-%d %H:%M:%S"))
if opts.endbefore is not None:
opts.endbefore = UTCDateTime(opts.endbefore)
print(" End Before: " +
opts.endbefore.strftime("%Y-%m-%d %H:%M:%S"))
if opts.endafter is not None:
opts.endafter = UTCDateTime(opts.endafter)
print(" End After: " +
opts.endafter.strftime("%Y-%m-%d %H:%M:%S"))
print(" ")
else:
print("Warning: No Time Range Specified for Search")
print(" ")
# Station/Channel Search Parameters
print("Station/Channel Search Parameters:")
print(" Network: {0:s}".format(opts.nets))
print(" Stations: {0:s}".format(opts.stns))
print(" Locations: {0:s}".format(opts.locs))
print(" Channels: {0:s}".format(opts.chns))
print(" Channel Rank: {0:s}".format(",".join(opts.chnrank)))
print(" ")
if opts.debug:
print("Output Files: {0:s}_query_debug.pkl and {0:s}_query_debug.kcsv".
format(outpref))
else:
print("Output Files: {0:s}.csv and {0:s}.pkl".format(outpref))
print(" ")
# Return Values
return opts, outpref
def main():
usage = "usage: %prog [options] *.vcf"
parser = OptionParser( usage=usage,version="%prog 1.0" ) # allow_interspersed_args=True
parser.add_option("-g", dest="gtf",
help="genome annotation gtf/gff [requires -f]" )
parser.add_option("-f", dest="fasta",
help="genome fasta" )
parser.add_option("-1", dest="bam1",
help="sample bam")
parser.add_option("-2", dest="bam2",
help="reference bam")
parser.add_option("-o", dest="outfn",
help="output fname [stdout]")
parser.add_option("-d", dest="minDepth", default=5, type=int,
help="""minimal depth; note both samples need to have pass depth filtering [%default]""")
parser.add_option("-m", dest="minFreq", default=0.8, type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n", dest="indels", default=True, action="store_false",
help="ignore indels [%default]")
parser.add_option("-b", dest="bothStrands", default=True, action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
( o, args ) = parser.parse_args()
if o.verbose:
sys.stderr.write( "%s\n" % ( str(o), ) )
if not args:
parser.error( "At least one vcf file has to be specified!" )
for fn in args:
if not os.path.isfile( fn ):
parser.error( "No such file: %s" % fn )
ctg2cds,id2gene,ctg2seq = {},{},{}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer( "Fasta file (-f) is requeired!" )
elif not os.path.isfile( o.fasta ):
parser.error( "No such file: %s" % o.fasta )
ctg2seq = genome2dict( o.fasta )
# load genome annotation
if not os.path.isfile( o.gtf ): # check if correct file
parser.error( "No such file: %s" % o.gtf )
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene,ctg2cds = load_gff( o.gtf )
else:
id2gene,ctg2cds = load_gtf( o.gtf )
if o.verbose:
sys.stderr.write( "Loaded annotation of %s CDS from %s\n" % ( len(id2gene),o.gtf ) )
# load possible SNPs coordinates
coords = load_vcf( args,o.indels )
# check with mpileup
check_snps( coords,o.bam1,o.bam2,o.fasta,o.outfn,ctg2cds,id2gene,ctg2seq,o.minDepth,o.minFreq,o.indels,o.bothStrands )
def main():
usage = "usage: %prog [options] *.vcf"
parser = OptionParser(usage=usage,
version="%prog 1.0") # allow_interspersed_args=True
parser.add_option("-g",
dest="gtf",
help="genome annotation gtf/gff [requires -f]")
parser.add_option("-f", dest="fasta", help="genome fasta")
parser.add_option("-1", dest="bam1", help="sample bam")
parser.add_option("-2", dest="bam2", help="reference bam")
parser.add_option("-o", dest="outfn", help="output fname [stdout]")
parser.add_option(
"-d",
dest="minDepth",
default=5,
type=int,
help=
"""minimal depth; note both samples need to have pass depth filtering [%default]"""
)
parser.add_option("-m",
dest="minFreq",
default=0.8,
type=float,
help="min frequency of alternative base [%default]")
parser.add_option("-n",
dest="indels",
default=True,
action="store_false",
help="ignore indels [%default]")
parser.add_option("-b",
dest="bothStrands",
default=True,
action="store_false",
help="report events confirmed by single strand algs")
parser.add_option("-v", dest="verbose", default=True, action="store_false")
(o, args) = parser.parse_args()
if o.verbose:
sys.stderr.write("%s\n" % (str(o), ))
if not args:
parser.error("At least one vcf file has to be specified!")
for fn in args:
if not os.path.isfile(fn):
parser.error("No such file: %s" % fn)
ctg2cds, id2gene, ctg2seq = {}, {}, {}
if o.gtf: # if annotation
# load genome
if not o.fasta: # fasta has to be provided
parser.errer("Fasta file (-f) is requeired!")
elif not os.path.isfile(o.fasta):
parser.error("No such file: %s" % o.fasta)
ctg2seq = genome2dict(o.fasta)
# load genome annotation
if not os.path.isfile(o.gtf): # check if correct file
parser.error("No such file: %s" % o.gtf)
# load gtf/gff
if o.gtf.endswith(".gff"):
id2gene, ctg2cds = load_gff(o.gtf)
else:
id2gene, ctg2cds = load_gtf(o.gtf)
if o.verbose:
sys.stderr.write("Loaded annotation of %s CDS from %s\n" %
(len(id2gene), o.gtf))
# load possible SNPs coordinates
coords = load_vcf(args, o.indels)
# check with mpileup
check_snps(coords, o.bam1, o.bam2, o.fasta, o.outfn, ctg2cds, id2gene,
ctg2seq, o.minDepth, o.minFreq, o.indels, o.bothStrands)
