def main():
draw_me = False
sum_only = False
MHC = False
regions = pc_toolbox.create_region_list(REGION_LOC)
bfile = BFILE
#ldfolder = LDFOLDER
ldfolder = '/home/jkb4y/ubs/work/results/Intersection_06022014/eurmeta_LD/'
#outfolder = OUTFOLDER
outfolder = '/home/jkb4y/ubs/work/results/Intersection_06022014/CAnalysis_LD/'
assoc_folder = ASSOC_FOLDER
#assoc_folder = '/home/jkb4y/work/results/Intersection_06022014/CAnalysis_eurmeta'
#for r2 in ['0','0.2','0.4','0.6','0.8']:
for r2 in ['0']:
#for r2 in ['0','0.2']:
#for r2 in ['0.2','0.4']:
#for r2 in ['0.8','0.6']:
#r2 = '0.8'
tot_loc = os.path.join(ldfolder,'all_regions_r2_{0}.ld'.format(r2))
with open(tot_loc, mode="w") as total:
ld_title_list = ['CHR_A','BP_A','SNP_A','CHR_B','BP_B','SNP_B','R2']
total.write('\t'.join(ld_title_list)+'\n')
for region in regions:
chrband = region.ID
chromosome = region.chro
subfolder = pc_toolbox.chr_folder(outfolder, chromosome)
assoc_chr_folder = pc_toolbox.chr_folder(assoc_folder, chromosome)
if chrband == '6p21.32' and not MHC:
continue
ld, snp_loc = plink_ld(region, bfile, ldfolder, assoc_chr_folder, r2, sum_only)
copy_to_tot(tot_loc, ld)
lz_ld = ld_for_lz(ld)
main_lz(region, subfolder, assoc_chr_folder, snp_loc,lz_ld, r2, draw_me)
def main(argv):
global out_base, freq_loc, meta_loc, bfile, table_type
global covar_loc, annot, weight_min, build, fix_args
global family
cl_arguments(argv)
#fix_it.main(fix_args)
gene_region_list = pc_toolbox.create_region_list(region_loc)
annot_dict_loc = fix_it.locate_annot_dict(build)
## print annot_dict_loc
annot_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
## print("Annotation Dictionary as Follows:")
## print annot_dict
## gene_list = sorted(key_list,key=lambda gene:gene_region_dict[gene][0])
#head, tail = os.path.split(out_file)
#keep_loc = os.path.join(out_file,'_plink_keep.txt')
keep_loc = out_base+'_plink_keep.txt'
plink_out = out_base+'_sigs_inCC'
#fixed_meta_loc = fix_it.locate_fixed_meta(meta_loc, build)
## print fixed_meta_loc
fixed_meta_loc = meta_loc
index_dict = create_index_dict(fixed_meta_loc,table_type)
z_list, lw_list = find_leastP_SNPs(gene_region_list, fixed_meta_loc, index_dict,
out_base, freq_loc, keep_loc,
weight_min, table_type, annot_dict)
if bfile is not None and covar_loc is not None:
plink_it(keep_loc, bfile, covar_loc, plink_out)
repair_for_zs(z_list, lw_list, fixed_meta_loc, index_dict, build)
def which_one(region_loc, table_loc,chromosome, index_dict, zero_list):
if region_loc is not None:
## determine_table_titles(table_loc)
## region_list = create_region_list(region_loc, region_col_dict)
mb_region_list = pc_toolbox.create_region_list(region_loc)
region_list = list()
for mb_region in mb_region_list:
region = RegInfo(chro = mb_region.chro, start = int(float(mb_region.start) * 1e6),
end = int(float(mb_region.end) *1e6),
band=mb_region.band, sym=mb_region.sym,
ID=mb_region.ID,title=mb_region.title)
region_list.append(region)
print region_list
else:
range_list = macro_ranges(table_loc, chromosome, index_dict)
## print(range_list)
region_list = macro_regions(chromosome, range_list)
## base, ext = os.path.splitext(table_loc)
## noZ_loc = base + '_noZs'+ext
fix_list, zr_list = identify_zerops(region_list, zero_list)
print('''
************************************************************************************
Here are the regions which will be drawn:
''')
for fix in fix_list:
print fix
print('''
The following regions contain zero p-values, and will be adapted:''')
for z in zr_list:
print z
print('''
************************************************************************************''')
sys.stdout.flush()
return fix_list, zr_list
def main():
global out_file, region_loc,assoc_loc, freq_loc
cl_arguments(sys.argv[1:])
gene_region_list = pc_toolbox.create_region_list(region_loc)
#gene_region_dict = create_region_dict(region_loc,position_form)
#key_list = gene_region_dict.keys()
#gene_list = sorted(key_list,key=lambda gene:gene_region_dict[gene][0])
#find_leastP_SNPs(gene_list, gene_region_dict, assoc_loc)
find_leastP_SNPs(gene_region_list, assoc_loc, out_file, freq_loc)
def main(argv):
region_loc = REGION_LOC
build = BUILD
meta_loc = META_LOC
outfolder = OUTFOLDER
region_list = pc_toolbox.create_region_list(region_loc)
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
fixed_meta_loc = fix_it.locate_fixed_meta(meta_loc, build)
for region in region_list:
read_meta(fixed_meta_loc, region, outfolder, build, annot_dict)
def main():
regions = pc_toolbox.create_region_list(REGION_LOC)
ldfolder = '/home/jkb4y/work/results/2012Feb1/hg18/LD/'
outfolder = '/home/jkb4y/work/results/2012Feb1/hg18/CAnalysis_Test/'
for region in regions:
chrband = region.band
chromosome = region.chro
subfolder = pc_toolbox.chr_folder(outfolder, chromosome)
ldfile = chrband + '_r2_0.8_lz.ld'
ld_sub = pc_toolbox.chr_folder(ldfolder, chromosome)
ld = os.path.join(ld_sub,ldfile)
snp_list = '{0}_~leastP_SNPs.txt'.format(chrband)
snp_loc = os.path.join(ld_sub,snp_list)
main_lz(region, subfolder, snp_loc,ld)
def main(argv):
global region_loc, pc_cmdlist
print sys.argv
cl_arguments(argv)
print(pc_cmdlist)
## gene_region_dict = pc_toolbox.create_region_dict(region_loc, POSITION_FORM)
## key_list = gene_region_dict.keys()
## print gene_region_dict
## index_tup = (chrcol,startcol,endcol,genecol)
## region_list = create_region_list(region_loc, index_tup)
region_list = pc_toolbox.create_region_list(region_loc)
for region in region_list:
cmd = write_command(region, pc_cmdlist)
os.system(cmd)
def main():
global out_file, table_loc, assoc, region_loc, build
cl_arguments(sys.argv[1:])
region_list = pc_toolbox.create_region_list(region_loc)
annot_dict_loc = fix_it.locate_annot_dict(build)
purpose = 'LOG'
annot_dict = fix_it.build_annot_dict(purpose,annot_dict_loc)
## annot_dict = None
## print("Annotation Dictionary as Follows:")
## print annot_dict
## if annot is not None:
## annot_dict = meta_toolbox.read_annot(annot)
## elif fix:
## annot_dict = meta_toolbox.read_annot_dict()
snp_list = read_table(table_loc, region_list, assoc, annot_dict)
print("inter_region_yank finds {0} SNPs of significance!".format(len(snp_list)))
write_results(snp_list, out_file, assoc, annot_dict)
def which_one(region_loc, table_loc,chromosome, index_dict, zero_list):
if region_loc is not None:
## determine_table_titles(table_loc)
## region_list = create_region_list(region_loc, region_col_dict)
mb_region_list = pc_toolbox.create_region_list(region_loc)
region_list = []
for mb_region in mb_region_list:
region = RegInfo(chro = mb_region.chro, start = int(float(mb_region.start) * 1e6),
end = int(float(mb_region.end) *1e6), band=mb_region.band, sym=mb_region.sym)
region_list.append(region)
print region_list
else:
range_list = macro_ranges(table_loc, chromosome, index_dict)
## print(range_list)
region_list = macro_regions(chromosome, range_list)
fix_list = remove_zerops(region_list, zero_list)
print('Here are the regions which will be drawn:')
print fix_list
return fix_list
def main(argv):
global region_loc, pc_cmdlist, cluster, cflag
print sys.argv
cl_arguments(argv)
print(pc_cmdlist)
## gene_region_dict = pc_toolbox.create_region_dict(region_loc, POSITION_FORM)
## key_list = gene_region_dict.keys()
## print gene_region_dict
## index_tup = (chrcol,startcol,endcol,genecol)
## region_list = create_region_list(region_loc, index_tup)
region_list = pc_toolbox.create_region_list(region_loc)
for region in region_list:
cmd = write_command(region, pc_cmdlist)
if cluster:
bash_loc = './PBS_scripts/'+region+'_'+cflag+'.sh'
print bash_loc
#write_bash(bash_loc, cmd)
#os.system('qsub {0}.'.format(bash_loc))
else:
os.system(cmd)
def main(argv):
global out_base, freq_loc, table_loc, bfile, table_type
global covar_loc, annot, weight_min, build, region_loc, pop, aa_freq_loc
cl_arguments(argv)
zlist = list()
index_dict, input_title_line = pc_toolbox.create_index_dict(table_loc, table_type)
region_list = pc_toolbox.create_region_list(region_loc)
annot_dict = create_annot_dict(build, 'LOG')
out_file = out_base + '_yank.tbl'
output_title_line = create_output_title_line(table_type, input_title_line)
with open(out_file, mode="w") as out_text:
## title_line = '\t'.join(META_TITLE_LIST)
out_text.write(output_title_line +'\n')
for region in region_list:
print zlist
sig_line, zlist, multicounter = read_table(table_loc, index_dict, region, weight_min, table_type, annot_dict, zlist)
info = document_result(sig_line, region, index_dict, table_type,annot_dict, multicounter)
if table_type == 'assoc':
if pop == 'AA':
for item in AA_ASSOC_ORDER_LIST:
out_text.write(str(info[item]) + '\t')
if pop == 'UK':
for item in ASSOC_ORDER_LIST:
out_text.write(str(info[item]) + '\t')
## if table_type in ['perm']:
## out_list = sig_line.strip().split()
## out_list.append(info['note'])
## out_list.append(info['band'])
## out_list.append(info['ID'])
## out_text.write('\t'.join(out_list))
if table_type in ['meta','family']:
for item in META_ORDER_LIST:
out_text.write(str(info[item]) + '\t')
if table_type =='perm':
for item in PERM_ORDER_LIST:
out_text.write(str(info[item]) + '\t')
out_text.write('\n')
if table_type in ['meta','family']:
repair_meta_for_lz(zlist, table_loc, index_dict, weight_min)