def genotype_missing(remPercent):
ori_genotype_file_name = "genotype_ori.txt"
geno_title_info, geno_dict = load_raw_data(ori_genotype_file_name)
ori_geno_total = len(geno_dict)
print "ori_geno_total", ori_geno_total
geno_sorted_list = sort_dict_by_key(geno_dict)
if remPercent > 0:
print "remPercent is", remPercent
for i in range(int(remPercent*ori_geno_total)):
if len(geno_sorted_list) > 1:
random_index = random.randrange(0, (len(geno_sorted_list)-1))
position = geno_sorted_list[random_index][0]
if position in geno_dict:
del geno_dict[int(position)]
del geno_sorted_list[random_index]
geno_sorted_list = sort_dict_by_key(geno_dict)
print "new geno total", len(geno_dict)
output_files("genotype.txt", geno_title_info, geno_dict)
os.system("cp genotype.txt genotype_" + str(remPercent) + ".txt")
chr_name = "chr9"
file_name = "haplotype.txt"
hifi_run(file_name, chr_name)
mode = "filterbyrefid"
seed_correction(file_name, chr_name, mode)
hifiAccuCheck("imputed_" + file_name, chr_name)
print "filterbyrefid accuracy"
hifiAccuCheck("non_one.txt", chr_name)
def run(self):
self.load_seed_geno_ref()
#elapse_time = time.time() - start_time
#print "load_seed_geno_ref time is: " + str(format(elapse_time, "0.3f")) + "s"
self.merge_pos()
#elapse_time = time.time() - elapse_time
#print "merge_pos time is: " + str(format(elapse_time, "0.3f")) + "s"
self.hg_merge()
#elapse_time = time.time() - elapse_time
#print "hg_merge time is: " + str(format(elapse_time, "0.3f")) + "s"
self.get_maf()
#elapse_time = time.time() - elapse_time
#print "get_maf time is: " + str(format(elapse_time, "0.3f")) + "s"
maf_num_list = self.maf_dict.keys()
#print maf_num_list
maf_num_list.sort()
maf_num_list.reverse()
print maf_num_list
self.combine_msg(186)
for maf_num in maf_num_list:
# improve add new pos to the current list
#self.combine_msg(maf_num)
if maf_num >= 0 and maf_num != 186:
print "current maf_num:", maf_num
self.pos_to_impute.extend(self.maf_dict[maf_num])
#print len(self.pos_to_impute)
pre_imputed_size = len(self.h_xn_imputed_dict)
#print "pre_imputed_size", pre_imputed_size
self.to_impute_window('X')
self.to_impute_window('N')
print "newly_imputed_size", len(self.h_xn_imputed_dict) - pre_imputed_size
"""
self.combine_msg(180)
#elapse_time = time.time() - elapse_time
#print "combine_msg time is: " + str(format(elapse_time, "0.3f")) + "s"
start_time = time.time()
self.to_impute_window('X')
self.to_impute_window('N')
elapse_time = time.time() - start_time
print "***********************to_impute_window time is: " + str(format(elapse_time, "0.3f")) + "s"
"""
self.output_dict("h_xn_new.txt", self.h_xn_imputed_dict)
seed_std_compare("h_xn_new.txt", self.chr_name)
self.output_dict("h_xn_1.txt", self.h_xn_dict)
seed_std_compare("h_xn_1.txt", self.chr_name)
hifiAccuCheck("h_xn_1.txt", self.chr_name)
def generate_std_seed_run(seed_number, add_range):
chr_name = "chr9"
hap_std_dict = load_seed_data(file_path + "ASW_" + chr_name + "_child_hap_refed.txt")[1]
hap_std_list = sort_dict_by_key(hap_std_dict)
genotype_file = file_path + "genotype_NA10847_" + chr_name + ".txt"
geno_dict = load_raw_data(genotype_file)[1]
seed_homo_dict, seed_hetero_dict = group_seed(hap_std_dict, geno_dict)
seed_hetero_list = sort_dict_by_key(seed_hetero_dict)
selected_seed_dict = {}
if add_range == "begining":
# add seed from begining
for i in range(seed_number - 1):
selected_seed_dict[seed_hetero_list[i][0]] = seed_hetero_list[i][1]
elif add_range == "middle":
# add seed in the middle
hetero_total = len(seed_hetero_list)
middle_point = hetero_total / 2
for i in range(seed_number - 1):
selected_seed_dict[seed_hetero_list[middle_point + i][0]] = seed_hetero_list[middle_point + i][1]
elif add_range == "end":
# add seed from end
seed_hetero_list.reverse()
for i in range(1, seed_number):
selected_seed_dict[seed_hetero_list[i][0]] = seed_hetero_list[i][1]
elif add_range == "random":
# randomly adding seed
i = 0
while i < seed_number - 1:
random_index = random.randrange(0, (len(seed_hetero_list) - 1))
while seed_hetero_list[random_index][0] in selected_seed_dict or seed_hetero_list[random_index][
1].allele_new == "N" \
or seed_hetero_list[random_index][1].allele_new == "X":
#while seed_hetero_list[random_index][0] in selected_seed_dict:
random_index = random.randrange(0, (len(seed_hetero_list) - 1))
selected_seed_dict[seed_hetero_list[random_index][0]] = seed_hetero_list[random_index][1]
i += 1
# always add the last snp into seed, hifi requirement
selected_seed_dict[hap_std_list[-1][0]] = hap_std_list[-1][1]
file_name = "haplotype_std.txt"
output_revised_seed(file_name, selected_seed_dict)
seed_std_compare(file_name, chr_name)
refMerger(file_name, chr_name, 0)
file_name = "haplotype.txt"
hifi_run(file_name, chr_name)
hifiAccuCheck("imputed_" + file_name, chr_name)
def hifi_revise(seed_input_file, chr_name):
start_time = time.time()
hifi_test(seed_input_file)
hifiAccuCheck("imputed_" + seed_input_file, chr_name)
#hifiAccuCheck("imputedhaplotype_1.txt", chr_name)
#analyze_data()
#seed_file_name = "hap_homo.txt"
#output_genohomo(seed_input_file, seed_file_name)
#output_hapstdhomo(seed_input_file, seed_file_name)
elapse_time = time.time() - start_time
print "***********************to_impute_window time is: " + str(format(elapse_time, "0.3f")) + "s"
def hifi_revise(seed_input_file, chr_name):
start_time = time.time()
hifi_test(seed_input_file)
hifiAccuCheck("imputed_" + seed_input_file, chr_name)
#hifiAccuCheck("imputedhaplotype_1.txt", chr_name)
#analyze_data()
#seed_file_name = "hap_homo.txt"
#output_genohomo(seed_input_file, seed_file_name)
#output_hapstdhomo(seed_input_file, seed_file_name)
elapse_time = time.time() - start_time
print "***********************to_impute_window time is: " + str(
format(elapse_time, "0.3f")) + "s"
def depth_cutoff():
for i in range(1, 2):
i = 11
data_path = solid_path + "song_" + str(i) + "/prem_rmsk_indel/"
os.chdir(data_path)
os.system("pwd")
sam_file = "song_" + str(i) + "_prem_" + solid_chr[i] + "_sorted_rmsk_indel.sam"
print "**************** song_" + str(i)
print "sam_file", sam_file
for depth_threshold in range(0, 3):
snpPick(data_path + sam_file, depth_threshold, solid_chr[i])
sam_file_name = "song_" + str(i) + "_prem_" + solid_chr[i] + "_sorted_rmsk_indel_"
seed_std_compare(data_path + sam_file_name + str(depth_threshold) + "_called_seed.txt", solid_chr[i])
combined_seed_file = data_path + sam_file_name + str(depth_threshold) + "_combined_seed.txt"
refMerger(combined_seed_file, solid_chr[i], 0)
hifi_test("haplotype.txt")
hifiAccuCheck(data_path + "imputed_haplotype.txt", solid_chr[i])
def simulation_run():
for depth in dept_list:
depth_path = simulation_path + depth + 'x/'
print "depth_path", depth_path
#os.system("cd " + depth_path)
for error_rate in error_rate_list:
#combined_seed_file = depth_path + "NA12878_hg18ch6_A_" + depth + "x_" + error_rate + "er_indel_0_combined_seed.txt"
#print "combined_seed_file", combined_seed_file
#refMerger(combined_seed_file, chr_name, 0)
#seed_file = depth_path + "NA12878_hg18ch6_A_" + depth + "x_" + error_rate + "er_indel_0_combined_seed.txt"
#print "seed_file", seed_file
#hap_seed_name = "haplotype_" + depth + "x_" + error_rate + "er.txt"
#os.system("cp " + "haplotype.txt" + " " + hap_seed_name)
#hap_seed_name = "haplotype.txt"
#hifi_test(hap_seed_name)
error_path = depth_path + "NA12878_hg18ch6_A_" + depth + "x_" + error_rate + "er/"
#os.system("cd " + error_path)
#os.system("pwd")
hifiAccuCheck(error_path + "imputedhaplotype.txt", chr_name)