def load_genomes(UTRfilestring, twobitfile): """ make this a separate function so that these only need to be loaded a single time """ UTRdict= rph.readindict(open(UTRfilestring, "rU")) genome= twobitreader.TwoBitFile(twobitfile) # do we actually need to load this in here? return UTRdict, genome
def main():
## using argparser to load arguments from workflow
parser = argparse.ArgumentParser()
parser.add_argument('--trspdictfilestring',
help='input transcript density files')
parser.add_argument('--UTRfilestring', help='UTRs file')
parser.add_argument('--cdsDenThresh',
help='boolean value- should density filter be used?')
parser.add_argument(
'--norm_type', help='type of normalizaion, should be raw reads or rpm')
parser.add_argument('--raw_dense_thresh',
help='threshold for CDS density for raw normalization')
parser.add_argument('--rpm_dense_thresh',
help='threshold for CDS density for rpm normalization')
parser.add_argument(
'--inset_choice',
help='inset values to be used to avoid start and stop codon peaks')
parser.add_argument('--outfilestring', help='output file name')
# parser.add_argument
args = parser.parse_args()
args.cdsDenThresh = args.cdsDenThresh == 'True'
print "ARGS: ", args.cdsDenThresh
# print bool(args.cdsDenThresh)
trspdict = rph.readcountsf(args.trspdictfilestring)
UTRdict = rph.readindict(open(args.UTRfilestring, "rU"))
countsIDlist, countsOutdict = build_count_tables(
trspdict, UTRdict, args.inset_choice, args.cdsDenThresh,
args.norm_type, float(args.raw_dense_thresh),
float(args.rpm_dense_thresh), args.outfilestring)
write_countTable_to_csv(countsIDlist, countsOutdict, args.outfilestring)
def load_genomes(UTRfilestring, firstStopsCSV, twobitfile): """ make this a separate function so that these only need to be loaded a single time """ UTRdict= rph.readindict(open(UTRfilestring, "rU")) utr3adj = pd.read_csv(firstStopsCSV, index_col=0) genome= twobitreader.TwoBitFile(twobitfile) # do we actually need to load this in here? return UTRdict, utr3adj, genome
def main():
## using argparser to load arguments from workflow
parser = argparse.ArgumentParser()
parser.add_argument('--trspdictfilestring',
help='input transcript density files')
parser.add_argument('--UTRfilestring', help='UTRs file')
parser.add_argument('--cdsDenThresh',
help='boolean value- should density filter be used?')
parser.add_argument(
'--norm_type', help='type of normalizaion, should be raw reads or rpm')
parser.add_argument('--raw_dense_thresh',
help='threshold for CDS density for raw normalization')
parser.add_argument('--rpm_dense_thresh',
help='threshold for CDS density for rpm normalization')
parser.add_argument(
'--inset_choice',
help='inset values to be used to avoid start and stop codon peaks')
parser.add_argument('--outfilestring', help='output file name')
parser.add_argument(
'--totreads',
help='total number of reads used after raw densebuilder run')
parser.add_argument(
'--stopcodons',
help=
'csv file with positions of all stopcodons, riboseq_stopcodon_finder.py'
)
# parser.add_argument
args = parser.parse_args()
# utr3adj = pd.read_csv(stopframe_csv, index_col=0)
utr3adj = pd.read_csv(args.stopcodons, index_col=0)
# print utr3adj.head()
# print utr3adj.loc['ENST00000426362.6']
# print utr3adj.loc[utr3adj['#transcript'] == 'ENST00000426362.6']
trspdict = rph.readcountsf(args.trspdictfilestring)
UTRdict = rph.readindict(open(args.UTRfilestring, "rU"))
# print UTRdict['ENST00000426362.6']
countsIDlist, countsOutdict = build_count_tables(
trspdict, UTRdict, utr3adj, args.inset_choice, bool(args.cdsDenThresh),
args.norm_type, float(args.raw_dense_thresh),
float(args.rpm_dense_thresh), args.outfilestring, int(args.totreads),
minUtr3len)
write_countTable_to_csv(countsIDlist, countsOutdict, args.outfilestring)
def codonaverage(self):
outlist, headers, motiffilelist = [], [], []
headers.append("motif")
for motif in self.motifs:
motiffile = args.motiffilerootpath + motif + "_1.csv"
motiffilelist.append(motiffile)
headers.append(motif)
outlist.append(headers)
codon_occu = []
codon_occu.append(self.sample_name)
f_output = open(args.outfileparams, "w")
f_output.write("Density file is " + str(self.sample_name) + "\n")
f_output.write("cds5trim is " + str(args.cds5trim) + "\n")
f_output.write("cds3trim is " + str(args.cds3trim) + "\n")
f_output.write("Seqwin is " + str(args.seqwin) + "\n")
f_output.write("Motiflist is " + str(motiffilelist) + "\n")
readcountsdict = rph.readcountsf(args.trspdictfilestring)
exclusionmodule = exclusionfiles[0]
if exclusionmodule != '0':
exclusiondict = self.readindict(open(exclusionmodule, "rU"))
else:
exclusiondict = '0'
print "Exclusion file is " + str(exclusionmodule)
UTRdict = rph.readindict(open(args.UTRfilestring, "rU"))
occupancy = self.occupancy(readcountsdict, motiffilelist,
exclusiondict, codon_occu, UTRdict,
f_output)
outlist.append(codon_occu)
f_output.close()
co = np.asarray(outlist) # convert outlist to a np.array
output = co.T
# print "output: ", output
# print "self.outlistfile: ", self.outlistfile
self.writerows(output, self.outlistfile) # write these rows to a csv
comments += "Threshold signifies minimal rpkm needed in coding region for gene to be in the average.\n"
comments += "alignpos =1 anchors average around the start codon and only includes 5'UTRs. alignpos =2 is the same for stop codon."
fc = open(args.outfilebase + "_" + str(args.alignpos) + "_output.txt", "w")
fc.write(comments)
fc.write("\n")
fc.write("Avggene was called with parameters:\n")
fc.write("transcripts= " + str(args.trspdictfilestring) + "\n")
fc.write("filtermodule= " + str(args.filtermodule) + "\n")
fc.write("exclusionmodule= " + str(args.exclusionmodule) + "\n")
fc.write("threshold= " + str(args.threshold) + "\n")
fc.write("regionlength5= " + str(args.regionlength5) + "\n")
fc.write("regionlength3= " + str(args.regionlength3) + "\n")
fc.write("equalweight= " + str(args.equalweight) + "\n")
fc.write("alignpos= " + str(args.alignpos) + "\n")
fc.close()
if args.filtermodule != '0':
filterdict = rph.readindict(open(args.filtermodule, "rU"))
else:
filterdict = '0'
if args.exclusionmodule != '0':
exclusiondict = rph.readindict(open(args.exclusionmodule, "rU"))
else:
exclusiondict = '0'
trspdict = rph.readcountsf(args.trspdictfilestring)
UTRdict = rph.readindict(open(args.UTRfilestring, "rU"))
metagene = Avggene(args.regionlength5, args.regionlength3, trspdict,
UTRdict, filterdict, exclusiondict, args.threshold,
args.alignpos, args.equalweight, args.outfilebase)
metagene.totalavg()
for attr in dir(libset):
if not attr.startswith("_"):
globals()[attr] = getattr(libset, attr)
threadNumb = str(args.threadNumb)
import rphelper as rph
### function inputs
inset_choice = 'zero'
# samplelist = samplelist
### load UTRdict to be used for all samples
UTRdict= rph.readindict(open(UTRfilestring, "rU"))
# countsIDlist, countsOutdict = build_count_tables(trspdict, UTRdict, utr3adj, args.inset_choice,
# bool(args.cdsDenThresh), args.norm_type, float(args.raw_dense_thresh),
# float(args.rpm_dense_thresh), args.outfilestring, int(args.totreads),
# minUtr3len)
### sample inputs:
# def build_count_table_single(sample, UTRdict = UTRdict, inset_choice = 'default'):
def build_count_table_single(sample, UTRdict = UTRdict,):
"""
This is the function that returns total counts within the following regions:
