def __init__(self,
reader,
chrom_col=0,
feature_col=2,
start_col=3,
end_col=4,
strand_col=6,
score_col=5,
fix_strand=False,
convert_to_bed_coord=False,
**kwargs):
NiceReaderWrapper.__init__(self,
reader,
chrom_col=chrom_col,
start_col=start_col,
end_col=end_col,
strand_col=strand_col,
fix_strand=fix_strand,
**kwargs)
self.feature_col = feature_col
self.score_col = score_col
self.convert_to_bed_coord = convert_to_bed_coord
self.last_line = None
self.cur_offset = 0
self.seed_interval = None
self.seed_interval_line_len = 0
def main():
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg(
options.cols2)
in_fname, in2_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
g2 = NiceReaderWrapper(fileinput.FileInput(in2_fname),
chrom_col=chr_col_2,
start_col=start_col_2,
end_col=end_col_2,
strand_col=strand_col_2,
fix_strand=True)
out_file = open(out_fname, "w")
try:
for line in coverage([g1, g2]):
if type(line) is GenomicInterval:
out_file.write("%s\n" % "\t".join(line.fields))
else:
out_file.write("%s\n" % line)
except ParseError, exc:
out_file.close()
fail("Invalid file format: %s" % str(exc))
def __init__( self, reader, chrom_col=0, feature_col=2, start_col=3,
end_col=4, strand_col=6, score_col=5, fix_strand=False, convert_to_bed_coord=False, **kwargs ):
NiceReaderWrapper.__init__( self, reader, chrom_col=chrom_col, start_col=start_col, end_col=end_col,
strand_col=strand_col, fix_strand=fix_strand, **kwargs )
self.feature_col = feature_col
self.score_col = score_col
self.convert_to_bed_coord = convert_to_bed_coord
self.last_line = None
self.cur_offset = 0
self.seed_interval = None
self.seed_interval_line_len = 0
def subtract_files(cls, fn1, fn2, out_fn):
g1 = NiceReaderWrapper(fileinput.FileInput(fn1), fix_strand=True)
g2 = NiceReaderWrapper(fileinput.FileInput(fn2), fix_strand=True)
out_file = open(out_fn, "w")
try:
for feature in subtract([g1, g2], pieces=True, mincols=1):
out_file.write("%s\n" % feature)
except ParseError, exc:
out_file.close()
fail("Invalid file format: %s" % str(exc))
def main():
mincols = 1
leftfill = False
rightfill = False
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg(
options.cols2)
if options.mincols:
mincols = int(options.mincols)
if options.fill:
if options.fill == "both":
rightfill = leftfill = True
else:
rightfill = options.fill == "right"
leftfill = options.fill == "left"
in_fname, in2_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
g2 = NiceReaderWrapper(fileinput.FileInput(in2_fname),
chrom_col=chr_col_2,
start_col=start_col_2,
end_col=end_col_2,
strand_col=strand_col_2,
fix_strand=True)
out_file = open(out_fname, "w")
try:
for outfields in join(g1,
g2,
mincols=mincols,
rightfill=rightfill,
leftfill=leftfill):
if type(outfields) is list:
out_file.write("%s\n" % "\t".join(outfields))
else:
out_file.write("%s\n" % outfields)
except ParseError, exc:
out_file.close()
fail("Invalid file format: %s" % str(exc))
def main():
distance = 0
minregions = 2
output = 1
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
if options.distance:
distance = int(options.distance)
if options.overlap:
distance = -1 * int(options.overlap)
if options.output:
output = int(options.output)
if options.minregions:
minregions = int(options.minregions)
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
# Get the cluster tree
try:
clusters, extra = find_clusters(g1,
mincols=distance,
minregions=minregions)
except ParseError, exc:
fail("Invalid file format: %s" % str(exc))
def main():
skipped = 0
not_pairwise = 0
if int_file == "None":
try:
maf_reader = bx.align.maf.Reader( open(inp_file, 'r') )
except:
stop_err("Your MAF file appears to be malformed.")
print >> fout, "#Seq1\tStart1\tEnd1\tSeq2\tStart2\tEnd2\tL\tN\tp"
for block in maf_reader:
if len(block.components) != 2:
not_pairwise += 1
continue
try:
rateEstimator(block)
except:
skipped += 1
else:
index, index_filename = maf_utilities.build_maf_index( inp_file, species = [dbkey_i] )
if index is None:
print >> sys.stderr, "Your MAF file appears to be malformed."
sys.exit()
win = NiceReaderWrapper( fileinput.FileInput( int_file ),
chrom_col=chr_col_i,
start_col=start_col_i,
end_col=end_col_i,
strand_col=strand_col_i,
fix_strand=True)
species = None
mincols = 0
global alignlen, mismatches
for interval in win:
alignlen = 0
mismatches = 0.0
src = "%s.%s" % ( dbkey_i, interval.chrom )
for block in maf_utilities.get_chopped_blocks_for_region( index, src, interval, species, mincols ):
if len(block.components) != 2:
not_pairwise += 1
continue
try:
rateEstimator(block)
except:
skipped += 1
if alignlen:
p = mismatches/alignlen
else:
p = 'NA'
interval.fields.append(str(alignlen))
interval.fields.append(str(mismatches))
interval.fields.append(str(p))
print >> fout, "\t".join(interval.fields)
#num_blocks += 1
if not_pairwise:
print "Skipped %d non-pairwise blocks" % (not_pairwise)
if skipped:
print "Skipped %d blocks as invalid" % (skipped)
def main():
sameformat = False
options, args = doc_optparse.parse( __doc__ )
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
if options.sameformat:
sameformat = True
in_file_1, in_file_2, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper( fileinput.FileInput( in_file_1 ),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True )
g2 = NiceReaderWrapper( fileinput.FileInput( in_file_2 ),
chrom_col=chr_col_2,
start_col=start_col_2,
end_col=end_col_2,
strand_col=strand_col_2,
fix_strand=True )
out_file = open( out_fname, "w" )
try:
for line in concat( [g1, g2], sameformat=sameformat ):
if type( line ) is GenomicInterval:
out_file.write( "%s\n" % "\t".join( line.fields ) )
else:
out_file.write( "%s\n" % line )
except ParseError as exc:
out_file.close()
fail( "Invalid file format: %s" % str( exc ) )
out_file.close()
if g1.skipped > 0:
print(skipped( g1, filedesc=" of 1st dataset" ))
if g2.skipped > 0:
print(skipped( g2, filedesc=" of 2nd dataset" ))
def main():
mincols = 1
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
if options.mincols:
mincols = int(options.mincols)
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
out_file = open(out_fname, "w")
try:
for line in merge(g1, mincols=mincols):
if options.threecol:
if type(line) is GenomicInterval:
out_file.write(
"%s\t%s\t%s\n" %
(line.chrom, str(line.startCol), str(line.endCol)))
elif type(line) is list:
out_file.write("%s\t%s\t%s\n" %
(line[chr_col_1], str(line[start_col_1]),
str(line[end_col_1])))
else:
out_file.write("%s\n" % line)
else:
if type(line) is GenomicInterval:
out_file.write("%s\n" % "\t".join(line.fields))
elif type(line) is list:
out_file.write("%s\n" % "\t".join(line))
else:
out_file.write("%s\n" % line)
except ParseError as exc:
out_file.close()
fail("Invalid file format: %s" % str(exc))
out_file.close()
if g1.skipped > 0:
print(skipped(g1, filedesc=" of 1st dataset"))
def main():
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
try:
bases = base_coverage(g1)
except ParseError, exc:
fail("Invalid file format: %s" % str(exc))
def main():
options, args = doc_optparse.parse( __doc__ )
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True )
try:
bases = base_coverage(g1)
except ParseError as exc:
fail( "Invalid file format: %s" % str( exc ) )
out_file = open( out_fname, "w" )
out_file.write( "%s\n" % str( bases ) )
out_file.close()
if g1.skipped > 0:
print(skipped( g1, filedesc="" ))
def main():
allchroms = False
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
lengths = options.lengths
if options.all:
allchroms = True
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
lens = dict()
chroms = list()
# dbfile is used to determine the length of each chromosome. The lengths
# are added to the lens dict and passed copmlement operation code in bx.
dbfile = fileinput.FileInput(lengths)
if dbfile:
if not allchroms:
try:
for line in dbfile:
fields = line.split("\t")
lens[fields[0]] = int(fields[1])
except:
# assume LEN doesn't exist or is corrupt somehow
pass
elif allchroms:
try:
for line in dbfile:
fields = line.split("\t")
end = int(fields[1])
chroms.append("\t".join([fields[0], "0", str(end)]))
except:
pass
# Safety...if the dbfile didn't exist and we're on allchroms, then
# default to generic complement
if allchroms and len(chroms) == 0:
allchroms = False
if allchroms:
chromReader = GenomicIntervalReader(chroms)
generator = subtract([chromReader, g1])
else:
generator = complement(g1, lens)
out_file = open(out_fname, "w")
try:
for interval in generator:
if type(interval) is GenomicInterval:
out_file.write("%s\n" % "\t".join(interval))
else:
out_file.write("%s\n" % interval)
except ParseError, exc:
out_file.close()
fail("Invalid file format: %s" % str(exc))
def main():
distance = 0
minregions = 2
output = 1
options, args = doc_optparse.parse(__doc__)
try:
chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg(
options.cols1)
if options.distance:
distance = int(options.distance)
if options.overlap:
distance = -1 * int(options.overlap)
if options.output:
output = int(options.output)
if options.minregions:
minregions = int(options.minregions)
in_fname, out_fname = args
except:
doc_optparse.exception()
g1 = NiceReaderWrapper(fileinput.FileInput(in_fname),
chrom_col=chr_col_1,
start_col=start_col_1,
end_col=end_col_1,
strand_col=strand_col_1,
fix_strand=True)
# Get the cluster tree
try:
clusters, extra = find_clusters(g1,
mincols=distance,
minregions=minregions)
except ParseError as exc:
fail("Invalid file format: %s" % str(exc))
f1 = open(in_fname, "r")
out_file = open(out_fname, "w")
# If "merge"
if output == 1:
fields = [
"."
for x in range(max(g1.chrom_col, g1.start_col, g1.end_col) + 1)
]
for chrom, tree in clusters.items():
for start, end, lines in tree.getregions():
fields[g1.chrom_col] = chrom
fields[g1.start_col] = str(start)
fields[g1.end_col] = str(end)
out_file.write("%s\n" % "\t".join(fields))
# If "filtered" we preserve order of file and comments, etc.
if output == 2:
linenums = dict()
for chrom, tree in clusters.items():
for linenum in tree.getlines():
linenums[linenum] = 0
linenum = -1
f1.seek(0)
for line in f1.readlines():
linenum += 1
if linenum in linenums or linenum in extra:
out_file.write("%s\n" % line.rstrip("\n\r"))
# If "clustered" we output original intervals, but near each other (i.e. clustered)
if output == 3:
linenums = list()
f1.seek(0)
fileLines = f1.readlines()
for chrom, tree in clusters.items():
for linenum in tree.getlines():
out_file.write("%s\n" % fileLines[linenum].rstrip("\n\r"))
# If "minimum" we output the smallest interval in each cluster
if output == 4 or output == 5:
linenums = list()
f1.seek(0)
fileLines = f1.readlines()
for chrom, tree in clusters.items():
for start, end, lines in tree.getregions():
outsize = -1
outinterval = None
for line in lines:
# three nested for loops?
# should only execute this code once per line
fileline = fileLines[line].rstrip("\n\r")
try:
cluster_interval = GenomicInterval(
g1, fileline.split("\t"), g1.chrom_col,
g1.start_col, g1.end_col, g1.strand_col,
g1.default_strand, g1.fix_strand)
except Exception as exc:
print(str(exc), file=sys.stderr)
f1.close()
sys.exit()
interval_size = cluster_interval.end - cluster_interval.start
if outsize == -1 or \
( outsize > interval_size and output == 4 ) or \
( outsize < interval_size and output == 5 ):
outinterval = cluster_interval
outsize = interval_size
out_file.write("%s\n" % outinterval)
f1.close()
out_file.close()
if g1.skipped > 0:
print(skipped(g1, filedesc=""))
