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 main(argv):
global table_loc, build
cl_arguments(argv)
build = 'hg18'
dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('MAP', dict_loc)
tf = fix_joe_map(table_loc,annot_dict,build)
look_up_rs_joe.main()
def main():
global log_folder, summary_name, freq_loc, run_info, build #map_loc #, repair_loc
cl_arguments(sys.argv[1:])
if log_folder is None:
usage()
sys.exit(2)
os.chdir(log_folder)
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
summarize_folder(log_folder,freq_loc, summary_name,run_info, annot_dict)
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(argv):
build = BUILD
#list_file = LIST_FILE
out_file = OUT_FILE
outfolder = '/home/jkb4y/work/data/Joe/HapMapCorrect/'
#map_file = MAP_FILE
intersect_loc = INTERSECT_LOC
assoc_loc = ASSOC_LOC
title_list = ['imchip_name','rs_name','hg18_pos','hg19_pos','hg18_lz','intersect']
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('MAP',annot_dict_loc)
intersect_annot_loc = fix_it.locate_annot_dict('hg19')
intersect_annot_dict = fix_it.build_annot_dict('LOG',intersect_annot_loc)
#im_list = old_read_list(list_file)
intersect_list = read_list(intersect_loc, intersect_annot_dict)
#map_and_key(map_file, out_file, annot_dict, intersect_list)
## index_dict = {'chr':0,'pos':3,'snp':1}
## out = open(out_file, mode="w")
## out.write('\t'.join(title_list)+'\n')
## with open(map_file, mode="r") as mappy:
## for line in mappy:
## line_list = line.strip().split()
## im=line_list[index_dict['snp']]
## info = look_up_snp(im, annot_dict)
## intersect = 'no'
##
## if info is not None:
##
## if info.name in intersect_list:
## intersect = 'yes'
## out.write('\t'.join([im,info.rs, info.hg18_pos, info.hg19_pos,
## info.lz,intersect]) +'\n')
##
## else:
## out.write('\t'.join([im,im,line_list[index_dict['pos']],
## '??','chr16:'+line_list[index_dict['pos']],
## intersect])+'\n')
## out.close()
append_assoc(assoc_loc,outfolder, annot_dict, intersect_list)
def main(argv):
cc_loc = CC_LOC
fam_loc = FAM_LOC
list_loc = LIST_LOC
meta_loc = META_LOC
chr_table = CHR_TABLE
annot_loc = fix_it.locate_annot_dict('hg19')
annot_dict = fix_it.build_annot_dict('LOG',annot_loc)
intersect_list = make_list(cc_loc, fam_loc, BASE_LIST_LOC, annot_dict)
#intersect_list = read_list(list_loc)
filter_table(meta_loc, list_loc,'META')
#intersect_list = read_list(list_loc)
#filter_table(chr_table, list_loc)
filter_table(FAM_TABLE, list_loc,'FAMILY')
def main(argv):
global manifest_loc, table_loc, build
cl_arguments(argv)
if manifest_loc is not None:
print("WRITING MANIFEST DICT!")
write_manifest_dict(manifest_loc)
dict_loc = locate_manifest_dict()
manifest_dict = build_manifest_dict(dict_loc)
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('HAPMAP', annot_dict_loc)
fix_table(table_loc, build, manifest_dict, annot_dict)
key_loc = locate_table_key(table_loc)
create_key(table_loc, manifest_dict, annot_dict, key_loc)
def main():
build = BUILD
#list_file = LIST_FILE
out_file = OUT_FILE
map_file = MAP_FILE
intersect_loc = INTERSECT_LOC
title_list = ['imchip_name','rs_name','hg18_pos','hg19_pos','hg18_lz','intersect']
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('MAP',annot_dict_loc)
intersect_annot_loc = fix_it.locate_annot_dict('hg19')
intersect_annot_dict = fix_it.build_annot_dict('LOG',intersect_annot_loc)
#im_list = old_read_list(list_file)
intersect_list = read_list(intersect_loc, intersect_annot_dict)
index_dict = {'chr':0,'pos':3,'snp':1}
out = open(out_file, mode="w")
out.write('\t'.join(title_list)+'\n')
with open(map_file, mode="r") as mappy:
for line in mappy:
line_list = line.strip().split()
im=line_list[index_dict['snp']]
info = look_up_snp(im, annot_dict)
intersect = 'no'
if info is not None:
if info.name in intersect_list:
intersect = 'yes'
out.write('\t'.join([im,info.rs, info.hg18_pos, info.hg19_pos,
info.lz,intersect]) +'\n')
else:
out.write('\t'.join([im,im,line_list[index_dict['pos']],
'??','chr16:'+line_list[index_dict['pos']],intersect])+'\n')
out.close()
def fix_eur(orig_table, out_table, fix_dict):
line1 = True
out = open(out_table, mode="w")
key_list = fix_dict.keys()
with open(orig_table, mode="r") as orig:
for line in orig:
if line1:
index_dict = pc_toolbox.read_meta_titles(line)
ls = line.strip().split()
ls.append('eurlowP_SNP')
out.write('\t'.join(ls)+'\n')
#out.write(line)
line1 = False
else:
lp_flag = '.'
lsplit = line.strip().split()
snp = lsplit[index_dict['snp']]
if snp in key_list:
lsplit[index_dict['z']]=fix_dict[snp].z
#lsplit[index_dict['p']]=fix_dict[snp].p
lsplit[index_dict['weight']]=fix_dict[snp].w
lsplit[index_dict['a1']]=fix_dict[snp].a1
lsplit[index_dict['a2']]='.'
lsplit[index_dict['direction']]='.'
key_list.remove(snp)
lp_flag = 'yes'
lsplit.append(lp_flag)
out.write('\t'.join(lsplit) + '\n')
if len(key_list) > 0:
print("{0} keys not found.".format(len(key_list)))
annot_dict_loc = fix_it.locate_annot_dict('hg18')
annot_dict = fix_it.build_annot_dict('MAP', annot_dict_loc)
for key in key_list:
#print fix_dict
print(key)
a1 = fix_dict[key].a1
a2 = '.'
weight = fix_dict[key].w
z = fix_dict[key].z
p = '0'
direction = '.'
chro = annot_dict[key].hg18_chr
pos = annot_dict[key].hg18_pos
lp_flag = 'yes'
key_info = [key,a1,a2,weight,z,p,direction,chro,pos,lp_flag]
out.write('\t'.join(key_info)+'\n')
#out.write('\t'.join(fix_dict[key])+'\n')
out.close()
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 main(argv):
global table_loc, region_loc, achilleas_key, build,out_base
weight_min = 0
cl_arguments(argv)
perm = False
if 'perm' in table_loc:
perm = True
achilleas_key_loc = ACHILLEAS_KEY_LOC
achilleas_dict = build_key(achilleas_key_loc, 'IM')
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('MAP',annot_dict_loc)
base, ext = os.path.splitext(table_loc)
multi_loc = base + '_JB'+ext
write_multi_table(table_loc, multi_loc, achilleas_dict,annot_dict)
## region_list = pc_toolbox.create_region_list(region_loc)
## keep_loc = out_base+'_plink_keep.txt'
## plink_out = out_base+'_sigs_eQTL'
index_dict = create_eqtl_index(multi_loc, perm)
log_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
def main(argv):
global manifest_loc, table_loc, build, table_type, purpose
cl_arguments(argv)
#repair_dict = fix_it.DUPLICATE_FIX_DICT
#rs_dup_list = fix_it.RS_KEEP
base, ext = os.path.splitext(table_loc)
im_dup_loc = base + '_imDups.list'
all_dup_loc = base + '_allDups.list'
dup_names_loc = base + '_dupNames.list'
#look up quinlan dictionary, using imchip names as key
annot_dict_loc = fix_it.locate_annot_dict(build)
key_type = table_type
if not table_type == 'HAPMAP':
key_type = 'LOG'
annot_dict = fix_it.build_annot_dict(key_type, annot_dict_loc)
#extract SNP info from table
print("Now gathering info from table....")
snpFo_list = list_info(table_loc, table_type)
#check table for duplicates based on current SNP names
print("Now searching list for duplicate snp names....")
#rs_sort = sorted(snpFo_list, key=attrgetter('snp'))
dup_name_count, dup_name_list = find_dup_names(snpFo_list)
print("FOUND {0} DUPLICATE SNP NAMES!!".format(dup_name_count))
write_snp_list(dup_name_list, dup_names_loc)
#check table for duplicates based on current SNP positions
print("Now sorting list for snp positions....")
sort_fo = sorted(snpFo_list, key=attrgetter('chro', 'pos'))
non_rs_dups, all_dups, rs_dup = find_dups(sort_fo, annot_dict)
write_snp_list(non_rs_dups, im_dup_loc)
#check the duplicate list for the number of rs SNP names
all_count, rs_count = count_dups(all_dups, all_dup_loc)
print("\nTHERE ARE {0} TOTAL DUPLICATES --- {1} ORIGINALLY WITH RS-ID NAMES".format(all_count, rs_count))
#check for specific types of duplicates:
#duplicates
#fix table based on current duplicate data
#repair_dict = pc_toolbox.read_dict(repair_loc)
repair_dict = fix_it.DUPLICATE_FIX_DICT
def main(argv):
meta_yank_loc = '/home/jkb4y/work/results/Intersection/eurmeta_06062012/RegionYank/eurmeta_yank.tbl'
fam_loc = '/home/jkb4y/work/data/2012Feb1/Family_data/eurgdtscan_06062012_lz_hg19_intersect.txt'
out_loc = '/home/jkb4y/work/results/Intersection/family/eurmeta_snp_info.tbl'
yank_out = '/home/jkb4y/work/results/Intersection/family/RegionYank/family'
BFILE = '/home/jkb4y/work/data/2012Feb1/intersect_fam_uk/hg19/intersect'
FREQ = '/home/jkb4y/work/data/2012Feb1/intersect_fam_uk/hg19/intersect_controls.frq'
REGION_LOC = '/home/jkb4y/work/data/Region_Lists/hg19/T1D_regions_hg19_05242012.txt'
COVAR = '/home/jkb4y/work/data/2012Feb1/intersect_fam_uk/hg19/intersect.cov'
build = 'hg19'
##
## table_yank.main(['--family',fam_loc, '--build',build,
## '--bfile',BFILE,'--freq',FREQ,'-r',REGION_LOC,
## '--covar',COVAR, '-o', yank_out])
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
snp_list = get_snp_list(meta_yank_loc)
fixed_table_loc = fam_loc
#fixed_table_loc = fix_it.locate_fixed_table(fam_loc, build)
retrieve_fam_data(snp_list, fixed_table_loc, out_loc, annot_dict)
##
meta_yank.main(['--family',fam_loc, '--build',build,
'--bfile',BFILE,'--freq',FREQ,'-r',REGION_LOC,
'--covar',COVAR, '-o', yank_out])
def create_annot_dict(build, purpose):
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict(purpose,annot_dict_loc)
return annot_dict
def main(argv):
global outfolder, assoc, chromosome,snpstar
global out_flag, user_script_loc
global range_start_bp, range_end_bp, hit_index, hitstring
global region_id, build, single, ldfolder, freq_loc, multi, hit1
cl_arguments(argv)
placeholder = ''
annot_dict_loc = fix_it.locate_annot_dict(build)
annot_dict = fix_it.build_annot_dict('LOG',annot_dict_loc)
snpstar_im = annot_dict[snpstar].name
table_folder = os.path.join(outfolder, 'ResultTables')
summary_folder = os.path.join(outfolder, 'SummaryTables')
str_hit_index = str(hit_index)
if hit_index < 10:
str_hit_index = '0'+str_hit_index
if not os.path.exists(table_folder):
os.makedirs(table_folder)
if not os.path.exists(summary_folder):
os.makedirs(summary_folder)
chr_folder = os.path.join(outfolder, 'chr{0}'.format(chromosome))
if not os.path.exists(chr_folder):
os.makedirs(chr_folder)
reg_folder = os.path.join(chr_folder, region_id)
if multi:
placeholder = '_'+snpstar+'_'+str_hit_index
if not os.path.exists(reg_folder):
os.makedirs(reg_folder)
super_outbase = os.path.join(reg_folder, region_id)
list_loc = super_outbase + '_snps.list'
table_loc = os.path.join(chr_folder, region_id+placeholder+'.tbl')
new_table_loc = os.path.join(table_folder, region_id+placeholder+'.tbl')
summary_table_loc = os.path.join(summary_folder, region_id+placeholder+'.tbl')
print(table_loc)
snplist = make_snp_pos_list(assoc,list_loc)
ld_loc = os.path.join(ldfolder,'chr{0}'.format(chromosome),
'{0}_r2_0.ld'.format(region_id))
table = open(table_loc, mode="w")
table.write('\t'.join(['SNP*','SNP*_pos','SNP*_im','conditional_snp',
'csnp_im','csnp_pos','SNP*_pvalue','OR','ci_lo','ci_hi',
'a1',"r2","csnp_freq","csnp_freq_a1"])+'\n')
table.close()
index = 1
for snp_tuple in snplist:
snp = snp_tuple[0]
snp_pos = snp_tuple[1]
snp_im = annot_dict[snp].name
corrected_snp = snp.replace(':','_')
outbase = super_outbase+'_'+corrected_snp
script_loc = outbase + '.script'
assoc_out = outbase +'.assoc.logistic'
if hit1:
write_script(outbase,script_loc, user_script_loc, snp, single, hitstring)
plink(script_loc)
print('''
**********************************************************************
************************************************************
The data will be conditioned on the following SNP:
%%% {0}
This is snp #{1} in a list of {2}.
******************************************************
**********************************************************************
'''.format(snp,index,len(snplist)))
## if snp == snpstar:
## write_script(outbase,script_loc, user_script_loc, snp, single, hitstring)
## plink(script_loc)
elif not multi:
write_script(outbase,script_loc, user_script_loc, snp, single, snpstar)
plink(script_loc)
print('''
**********************************************************************
************************************************************
The data will be conditioned on the following SNP:
%%% {0}
This is snp #{1} in a list of {2}.
******************************************************
**********************************************************************
'''.format(snp,index,len(snplist)))
info = filter_result(assoc_out,snpstar)
snp_freq = pc_toolbox.retrieve_freq(freq_loc, snp)
r2 = pc_toolbox.retrieve_r2(snpstar,snp,ld_loc)
if r2 is None:
r2 = "???"
index = index + 1
with open(table_loc, mode='a') as table:
table.write('\t'.join([snpstar,info.pos, snpstar_im,
snp,snp_im,snp_pos,str(info.p),
info.OR,info.lo,info.hi,
info.a1,r2,snp_freq[0],snp_freq[1]])+'\n')
shutil.copy(table_loc, new_table_loc)
summarize_table(new_table_loc, summary_table_loc, snpstar)