if x == 15:
return "XV"
if x == 16:
return "XVI"
if x == 17:
return "XVII"
if x == 18:
return "XVIII"
if x == 19:
return "XIX"
if x == 20:
return "XX"
return None
tabpath = ap.getArg("--in")
if False == os.path.exists(tabpath):
print "\n. I cannot find your TAB file at", tabpath
exit()
gffpath = ap.getOptionalArg("--out")
if gffpath == False or gffpath == None:
gffpath = tabpath + ".gff"
fin = open(tabpath, "r")
fout = open(gffpath, "w")
fout.write("# gff-version 3\n")
fout.write("# This file was auto-generated by the script tab2gff.py\n")
fout.write("# using data from the TAB file " + tabpath + "\n")
fout.write("#\n")
for l in fin.xreadlines():
import os, sys
from argParser import ArgParser
ap = ArgParser(sys.argv)
gffpath = ap.getArg("--gff")
if False == os.path.exists(gffpath):
print "\n. Error. I can't find your GFF at", gffpath
exit()
bdgpath = ap.getArg("--bdg")
if bdgpath != False:
if False == os.path.exists(bdgpath):
print "\n. Error. I can't find your BDG at", bdgpath
exit()
genename = ap.getArg("--genename")
regsize = int( ap.getArg("--regsize") )
chrom = None
start = None
stop = None
strand = None
fin = open(gffpath, "r")
for l in fin.xreadlines():
if l.__len__() > 0 and False == l.startswith("#"):
tokens = l.split()
this_gene = tokens[8].split(";")[0].split("=")[1] # orfName
if this_gene == genename:
chrom = tokens[0]
start = int( tokens[3] )
#
# Create a master table of gene-peak occurances across multiple species and replicate conditions
#
import os, sys, re
from plot_venn import *
from argParser import ArgParser
ap = ArgParser(sys.argv)
runids = ap.getList("--runids") # a list of runid names
runid = ap.getArg("--runid") # the (output) runid for this peak comparison
pillarspath = ap.getArg("--pillars") # a file containing G
orf_names = {}
def splash():
print "============================================"
print " compare_peaks.py"
print " Victor Hanson-Smith, 2014"
print " [email protected]"
print "============================================"
splash()
def get_runid_reps():
print "\n. Reading Replicates..."
runid_reps = {}
for t in runids:
if t not in runid_reps:
runid_reps[t] = []
import os, sys
from argParser import ArgParser
ap = ArgParser(sys.argv)
gffpath = ap.getArg("--gff")
if False == os.path.exists(gffpath):
print "\n. Error. I can't find your GFF at", gffpath
exit()
bdgpath = ap.getArg("--bdg")
if bdgpath != False:
if False == os.path.exists(bdgpath):
print "\n. Error. I can't find your BDG at", bdgpath
exit()
genename = ap.getArg("--genename")
regsize = int(ap.getArg("--regsize"))
chrom = None
start = None
stop = None
strand = None
fin = open(gffpath, "r")
for l in fin.xreadlines():
if l.__len__() > 0 and False == l.startswith("#"):
tokens = l.split()
this_gene = tokens[8].split(";")[0].split("=")[1] # orfName
if this_gene == genename:
chrom = tokens[0]
con = build_db(dbpath=dbpath)
"""--make_testdb is a dev-only option"""
if True == ap.getOptionalToggle("--make_testdb"):
reduce_db_for_test(con)
exit()
"""--reset_files is a dev-only option"""
if True == ap.getOptionalToggle("--reset_files"):
reset_files(con)
exit()
#
# IMPORT
#
pillarspath = ap.getArg("--pillarspath")
if False == ap.getOptionalToggle("--skip_pillars_import") and False == ap.getOptionalToggle("--skip_import"):
con = import_pillars(pillarspath, con)
else:
print "\n. I'm skipping pillars import. I will use the existing pillars in the database."
print_pillarsstats(con)
if False == ap.getOptionalToggle("--skip_gff") and False == ap.getOptionalToggle("--skip_import"):
import_gffs(con)
resolve_aliasids(con)
import_redflagregions(con, ap)
import_intergenic_regions(con)
if False == ap.getOptionalToggle("--skip_import"):
#
# Draw a subsample of reads from a FASTQ file.
#
import sys, os
from argParser import ArgParser
ap = ArgParser(sys.argv)
inpath = ap.getArg("--in")
outpath = ap.getArg("--out")
n = int(ap.getArg("--n"))
fin = open(inpath, "r")
fout = open(outpath, "w")
count_reads = 0
lc = 0
for l in fin.xreadlines():
if lc == 0:
count_reads += 1
if count_reads <= n:
fout.write(l)
else:
break
lc += 1
if lc == 4:
lc = 0
if count_reads % 10 == 0:
sys.stdout.write("\r --> %.1f%%" % (100 * count_reads / float(n)))
title="",
force_square=False,
plot_as_rank=[],
skip_identity=False,
skip_zeros=False,
unit_labels=[],
xlab=None,
ylab=None)
##############################
#
# main
#
motifpath = ap.getArg("--motifpath")
readsdbpath = ap.getArg("--readdbpath")
rcon = lite.connect(readsdbpath, timeout=1)
vizdbpath = ap.getArg("--vizdbpath")
vcon = build_db(dbpath=vizdbpath)
vcon = build_motif_dbtables(vcon)
"""Import motifs"""
vcur = vcon.cursor()
gene_motif = read_motifs(motifpath)
motifname_id = {}
for genename in gene_motif:
sql = "select id from Motifs where name='" + genename + "'"
vcur.execute(sql)
if vcur.fetchone() == None:
"""Regardless of which options are being executed, the DB gets
built, or rebuilt, depending on its status."""
con = build_db(dbpath=dbpath)
"""--make_testdb is a dev-only option"""
if True == ap.getOptionalToggle("--make_testdb"):
reduce_db_for_test(con)
exit()
"""--reset_files is a dev-only option"""
if True == ap.getOptionalToggle("--reset_files"):
reset_files(con)
exit()
#
# IMPORT
#
pillarspath = ap.getArg("--pillarspath")
if False == ap.getOptionalToggle(
"--skip_pillars_import") and False == ap.getOptionalToggle(
"--skip_import"):
con = import_pillars(pillarspath, con)
else:
print "\n. I'm skipping pillars import. I will use the existing pillars in the database."
print_pillarsstats(con)
if False == ap.getOptionalToggle(
"--skip_gff") and False == ap.getOptionalToggle("--skip_import"):
import_gffs(con)
resolve_aliasids(con)
import_redflagregions(con, ap)
#
# Draw a subsample of reads from a FASTQ file.
#
import sys, os
from argParser import ArgParser
ap = ArgParser(sys.argv)
inpath = ap.getArg("--in")
outpath = ap.getArg("--out")
n = int( ap.getArg("--n") )
fin = open(inpath, "r")
fout = open(outpath, "w")
count_reads = 0
lc = 0
for l in fin.xreadlines():
if lc == 0:
count_reads += 1
if count_reads <= n:
fout.write( l )
else:
break
lc += 1
if lc == 4:
lc = 0
if count_reads%10 == 0:
sys.stdout.write("\r --> %.1f%%" % (100*count_reads/float(n)) )
fout.close()
if xvalues.__len__() != yvalues.__len__():
print "ERROR 272: An error occurred while writing the write_peak_motif_table."
exit()
if xvalues.__len__() > 0 and yvalues.__len__() > 0:
scatter_nxm(2, 2, [xvalues,yvalues], ["max motif score","fold-enrichment"], groupname + ".motifs_vs_fe." + motifid_name[ mid ], title="", force_square=False, plot_as_rank = [], skip_identity = False, skip_zeros = False, unit_labels=[], xlab=None, ylab=None)
##############################
#
# main
#
motifpath = ap.getArg("--motifpath")
readsdbpath = ap.getArg("--readdbpath")
rcon = lite.connect(readsdbpath, timeout=1)
vizdbpath = ap.getArg("--vizdbpath")
vcon = build_db(dbpath=vizdbpath)
vcon = build_motif_dbtables(vcon)
"""Import motifs"""
vcur = vcon.cursor()
gene_motif = read_motifs(motifpath)
motifname_id = {}
for genename in gene_motif:
sql = "select id from Motifs where name='" + genename + "'"
vcur.execute(sql)
#
# This script is for generating toy-sized test cases
#
# Subsample a track file, such as BDGs and BEDs
#
import sys, os
from argParser import ArgParser
ap = ArgParser(sys.argv)
bdgpath = ap.getArg("--in")
outpath = ap.getArg("--out") # output path of subsampled BDG
# Lines in the BDG that contain the keyword will be sampled.
# all other lines will be discarded
keyword = ap.getArg("--keyword")
fout = open(outpath, "w")
fin = open(bdgpath, "r")
for l in fin.xreadlines():
if l.__contains__(keyword):
fout.write( l )
fin.close()
fout.close()
#################################################
#
# USAGE:
#
# python compare_asr_dat_files.py [<id> <dat filepath> . . .]
#
import os
import sys
import re
from map_anc_2_anc import *
from argParser import ArgParser
ap = ArgParser(sys.argv)
anc1 = ap.getArg("--anc1")
nick1 = ap.getArg("--nick1")
msa1 = ap.getArg("--msa1")
seed1 = ap.getArg("--seed1")
anc2 = ap.getArg("--anc2")
nick2 = ap.getArg("--nick2")
msa2 = ap.getArg("--msa2")
seed2 = ap.getArg("--seed2")
runid = ap.getOptionalArg("--runid")
if runid == False:
exit()
rsitesa = []
x = ap.getOptionalList("--restrict_sites_1")
if x != None:
import math
import os
import re
import sys
from argParser import ArgParser
argp = ArgParser(sys.argv)
spath = argp.getArg("--input")
fin = open( spath, "r" )
lines = fin.readlines()
fin.close()
output = argp.getArg("--output")
def plot_comb(cat):
cranscript = "plot." + output + "." + cat.__str__() + ".cran"
f = open(cranscript, "w")
y = "y <- c("
x = "x <- c("
for site in site_pps:
y += site_pps[site][cat].__str__() + ","
x += site.__str__() + ","
y = re.sub(",$", "", y)
y += ")"
f.write( y + "\n")
x = re.sub(",$", "", x)
#################################################
#
# USAGE:
#
# python compare_asr_dat_files.py [<id> <dat filepath> . . .]
#
import os
import sys
import re
from map_anc_2_anc import *
from argParser import ArgParser
ap = ArgParser(sys.argv)
anc1 = ap.getArg("--anc1")
nick1 = ap.getArg("--nick1")
msa1 = ap.getArg("--msa1")
seed1 = ap.getArg("--seed1")
anc2 = ap.getArg("--anc2")
nick2 = ap.getArg("--nick2")
msa2 = ap.getArg("--msa2")
seed2 = ap.getArg("--seed2")
runid = ap.getOptionalArg("--runid")
if runid == False:
exit()
rsitesa = []
x = ap.getOptionalList("--restrict_sites_1")
if x != None:
#
# This script is for generating toy-sized test cases
#
# Subsample a track file, such as BDGs and BEDs
#
import sys, os
from argParser import ArgParser
ap = ArgParser(sys.argv)
bdgpath = ap.getArg("--in")
outpath = ap.getArg("--out") # output path of subsampled BDG
# Lines in the BDG that contain the keyword will be sampled.
# all other lines will be discarded
keyword = ap.getArg("--keyword")
fout = open(outpath, "w")
fin = open(bdgpath, "r")
for l in fin.xreadlines():
if l.__contains__(keyword):
fout.write(l)
fin.close()
fout.close()
