def main():
GTFgen = GFF.parse(GTFfile)
GFFlist = makeGFFlist(GTFgen)
ucscIDlist, transcriptdict = build_stopcodon_table(GFFlist,
inculde_noncanon_start,
include_noncanon_stop)
write_utr_stopcodon_csvfile(ucscIDlist, transcriptdict)
def main(gff_file, fasta_file):
out_file = "%s.gbk" % os.path.splitext(gff_file)[0]
fasta_input = SeqIO.to_dict(SeqIO.parse(fasta_file, "fasta", generic_dna))
gff_iter = GFF.parse(gff_file, fasta_input)
record = next(_check_gff(_fix_ncbi_id(gff_iter)))
## hack to fix bug where DNAAlphabet turns into SingleLetterAlphabet() in the parser..
record.seq.alphabet = generic_dna
SeqIO.write(record, out_file, "genbank")
def writegene_wf2(shift5, shift3, riboshift, densityfile, feature, gfffile,
utrgfffilename, outfile):
GFFgen = GFF.parse(gfffile)
counts1 = readcountsf(densityfile + "_plus_")
counts2 = readcountsf(densityfile + "_minus_")
counts = [counts1, counts2]
idtable = makeidtable2(GFFgen)
GFFgen = GFF.parse(gfffile)
GFFlist = makeGFFlist(GFFgen)
goodgenes = 2
print feature
if utrgfffilename == "-1": utrtable = {}
else:
utrtable = utrgffgen = GFF.parse(utrgfffilename)
utrtable = genometools.makeutrtable(utrgffgen)
bp1 = shift5
chromosome = idtable[feature][2]
featurenum = idtable[feature][1]
longfeature = idtable[feature][0].id
if utrtable.has_key(longfeature):
bp2 = utrtable[longfeature][1] - utrtable[longfeature][0] + shift3
else:
bp2 = 0 + shift3
bp = [bp1, bp2, riboshift]
retval = givegene(chromosome, featurenum, GFFlist, counts, bp, goodgenes)
if retval[0] == -1: print "Not a good gene..."
t = []
t.append(["pos", "rpm"])
i = -shift5
while i < len(retval[0]) - shift5:
newline = [i, retval[0][i + shift5]]
t.append(newline)
i += 1
fcsv = open(outfile + "_" + feature + ".csv", "w")
writer = csv.writer(fcsv)
writer.writerows(t)
fcsv.close()
def main():
### not sure what I was using the for here...
# # mRNAdict = pandas.read_csv(mRNAseqsInfile, index_col=0, skiprows=1).T.to_dict()
# mRNAdict = pandas.read_csv(mRNAseqsInfile, index_col=0, skiprows=1)
# print mRNAdict.head()
# # print mRNAdict['']
### The actual funciton:
GTFgen = GFF.parse(GTFfile)
GFFlist = makeGFFlist(GTFgen)
ucscIDlist, transcriptdict = get_Prot_sequence(GFFlist)
write_utr_stopcodon_csvfile(ucscIDlist, transcriptdict)
def parse_GFF(utrGFF):
""" Very thin wrapper that tries to do makeutrtable(GFF.parse(utrGFF))
but checks for IOError and returns an empty dictionary instead.
"""
try:
return makeutrtable(GFF.parse(utrGFF))
except IOError:
print "Warning! " + utrGFF + " couldn't be found."
if raw_input("'c' to continue with empty dictionary\n") == 'c':
return {}
else:
quit()
def makeGFFlist(GFFname):
""" Tool for loading the entire yeast genome into memory
From seqtools
Called st.makeGFFlist(GFF.parse(codingGFF))
Returns dictionary GFFlist[chr.id] = chr for chr in GFFgen
Called for main coding GFF but not utr5GFF and utr3GFF -- generalize?
Will this be affected it GFF is changed? Probably not, no parsing here, just storing
"""
GFFlist = {}
for chr in GFF.parse(GFFname):
GFFlist[chr.id] = chr
return GFFlist
def main():
GTFgen = GFF.parse(GTFfile)
GFFlist = makeGFFlist(GTFgen)
ucscIDlist, transcriptdict = build_utr3_stop_positions(GFFlist)
write_utr_stopcodon_csvfile(ucscIDlist, transcriptdict)
parser.add_argument('--threshold',
default=1,
help='thresholding read counts')
parser.add_argument('--totreads',
default=-1,
help='reads for normalization')
parser.add_argument('--outputdata', help='output data filepath')
parser.add_argument('--bamfileoutput', help='output bam file')
parser.add_argument
args = parser.parse_args()
import ast
riboshiftdict = ast.literal_eval(
args.riboshiftdict) #convert string into dictionary
print riboshiftdict
print "parsing gff..."
GTFgen = GFF.parse(args.GTFfile)
print "loading bam file..."
bamfile = pysam.AlignmentFile(args.bamfileinput, "rb")
print "loading genome..."
genome = twobitreader.TwoBitFile(args.twobitfile)
print "writing bam out file..."
bamfileout = pysam.AlignmentFile(args.bamfileoutput,
"wb",
template=bamfile)
rfpdense = densebuilder(bamfile, GTFgen, genome, riboshiftdict,
int(args.threshold), args.totreads,
args.outputdata, args.assignment, bamfileout)
rfpdense.builddense()
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--GFFfile', help='coding GFF or GTF file')
parser.add_argument('--bamfile1', help='bamfile from first genome mapping')
parser.add_argument('--bamfile2', help='bamfile from polyA removal')
parser.add_argument('--densitypathandfilestring',
help='density file output path')
parser.add_argument('--wigpathandfile', help='wig file output path')
parser.add_argument('--totreads',
default=-1,
help='total reads for normalization')
parser.add_argument('--assignment', help='5 or 3 end', required=True)
parser.add_argument('--riboshiftdict', help='dictionary of riboshifts')
parser.add_argument('--bamfileoutput', help='output bam file')
parser.add_argument('--softclipped', help='number of soft clipped allowed')
args = parser.parse_args()
import ast
riboshiftdict = ast.literal_eval(args.riboshiftdict)
GFFgen = GFF.parse(args.GFFfile)
bamgen0 = pysam.AlignmentFile(args.bamfile1, "rb")
bamfileout = pysam.AlignmentFile(args.bamfileoutput,
"wb",
template=bamgen0)
rfpdense = densebuilder(GFFgen, args.bamfile1, args.bamfile2,
args.densitypathandfilestring, args.wigpathandfile,
args.totreads, args.assignment, riboshiftdict,
bamfileout, args.softclipped)
rfpdense.setdense()
help = ".gff file")
parser.add_argument("--out",
metavar = "STRING",
type = str,
help = "Output directory",
default = ".")
args = parser.parse_args()
filBAM = args.bam
name = os.path.splitext(os.path.basename(filBAM))[0]
filGFF = args.gff
# Open the gff file.
gffHandle = GFF.parse(open(filGFF))
# Open the bam file
bamHandle = pysam.AlignmentFile(filBAM, "rb")
### Functions for read directions ###
def Forward(read):
if read.is_reverse: return False
else: return True
def Reverse(read):
if read.is_reverse: return True
else: return False
### CALCULATE COVERAGE AND ANNOTATION FOR EVERY LOCUS_TAG ###
coverages=list()
def main(): GTFgen = GFF.parse(GTFfile) GFFlist = makeGFFlist(GTFgen) ucscIDlist, transcriptdict = get_mRNA_sequence(GFFlist) write_utr_stopcodon_csvfile(ucscIDlist, transcriptdict)
def main():
GTFgen = GFF.parse(GTFfile)
GFFlist = makeGFFlist(GTFgen)
find_uORFs(GFFlist)
