diff options
Diffstat (limited to 'wqflask/maintenance')
| -rw-r--r-- | wqflask/maintenance/convert_geno_to_bimbam.py | 21 | ||||
| -rw-r--r-- | wqflask/maintenance/gen_select_dataset.py | 6 | ||||
| -rw-r--r-- | wqflask/maintenance/generate_kinship_from_bimbam.py | 13 | ||||
| -rw-r--r-- | wqflask/maintenance/geno_to_json.py | 3 | ||||
| -rw-r--r-- | wqflask/maintenance/quantile_normalize.py | 3 |
5 files changed, 31 insertions, 15 deletions
diff --git a/wqflask/maintenance/convert_geno_to_bimbam.py b/wqflask/maintenance/convert_geno_to_bimbam.py index 5b2369c9..a1712500 100644 --- a/wqflask/maintenance/convert_geno_to_bimbam.py +++ b/wqflask/maintenance/convert_geno_to_bimbam.py @@ -83,7 +83,8 @@ class ConvertGenoFile: genotypes = row_items[2:] for item_count, genotype in enumerate(genotypes): if genotype.upper().strip() in self.configurations: - this_marker.genotypes.append(self.configurations[genotype.upper().strip()]) + this_marker.genotypes.append( + self.configurations[genotype.upper().strip()]) else: this_marker.genotypes.append("NA") @@ -106,9 +107,11 @@ class ConvertGenoFile: with open(self.output_files[2], "w") as snp_fh: for marker in self.markers: if self.mb_exists: - snp_fh.write(marker['name'] + ", " + str(int(float(marker['Mb']) * 1000000)) + ", " + marker['chr'] + "\n") + snp_fh.write( + marker['name'] + ", " + str(int(float(marker['Mb']) * 1000000)) + ", " + marker['chr'] + "\n") else: - snp_fh.write(marker['name'] + ", " + str(int(float(marker['cM']) * 1000000)) + ", " + marker['chr'] + "\n") + snp_fh.write( + marker['name'] + ", " + str(int(float(marker['cM']) * 1000000)) + ", " + marker['chr'] + "\n") def get_sample_list(self, row_contents): self.sample_list = [] @@ -160,10 +163,14 @@ class ConvertGenoFile: group_name = ".".join(input_file.split('.')[:-1]) if group_name == "HSNIH-Palmer": continue - geno_output_file = os.path.join(new_directory, group_name + "_geno.txt") - pheno_output_file = os.path.join(new_directory, group_name + "_pheno.txt") - snp_output_file = os.path.join(new_directory, group_name + "_snps.txt") - output_files = [geno_output_file, pheno_output_file, snp_output_file] + geno_output_file = os.path.join( + new_directory, group_name + "_geno.txt") + pheno_output_file = os.path.join( + new_directory, group_name + "_pheno.txt") + snp_output_file = os.path.join( + new_directory, group_name + "_snps.txt") + output_files = [geno_output_file, + pheno_output_file, snp_output_file] print("%s -> %s" % ( os.path.join(old_directory, input_file), geno_output_file)) convertob = ConvertGenoFile(input_file, output_files) diff --git a/wqflask/maintenance/gen_select_dataset.py b/wqflask/maintenance/gen_select_dataset.py index 583a06e1..484336a6 100644 --- a/wqflask/maintenance/gen_select_dataset.py +++ b/wqflask/maintenance/gen_select_dataset.py @@ -120,14 +120,16 @@ def get_types(groups): else: if not phenotypes_exist(group_name) and not genotypes_exist(group_name): types[species].pop(group_name, None) - groups[species] = tuple(group for group in groups[species] if group[0] != group_name) + groups[species] = tuple( + group for group in groups[species] if group[0] != group_name) else: # ZS: This whole else statement might be unnecessary, need to check types_list = build_types(species, group_name) if len(types_list) > 0: types[species][group_name] = types_list else: types[species].pop(group_name, None) - groups[species] = tuple(group for group in groups[species] if group[0] != group_name) + groups[species] = tuple( + group for group in groups[species] if group[0] != group_name) return types diff --git a/wqflask/maintenance/generate_kinship_from_bimbam.py b/wqflask/maintenance/generate_kinship_from_bimbam.py index 7cc60c9e..bed634fa 100644 --- a/wqflask/maintenance/generate_kinship_from_bimbam.py +++ b/wqflask/maintenance/generate_kinship_from_bimbam.py @@ -21,7 +21,9 @@ class GenerateKinshipMatrices: self.pheno_file = pheno_file def generate_kinship(self): - gemma_command = "/gnu/store/xhzgjr0jvakxv6h3blj8z496xjig69b0-profile/bin/gemma -g " + self.geno_file + " -p " + self.pheno_file + " -gk 1 -outdir /home/zas1024/genotype_files/genotype/bimbam/ -o " + self.group_name + gemma_command = "/gnu/store/xhzgjr0jvakxv6h3blj8z496xjig69b0-profile/bin/gemma -g " + self.geno_file + \ + " -p " + self.pheno_file + \ + " -gk 1 -outdir /home/zas1024/genotype_files/genotype/bimbam/ -o " + self.group_name print("command:", gemma_command) os.system(gemma_command) @@ -34,9 +36,12 @@ class GenerateKinshipMatrices: group_name = ".".join(input_file.split('.')[:-1]) if group_name == "HSNIH-Palmer": continue - geno_input_file = os.path.join(bimbam_dir, group_name + "_geno.txt") - pheno_input_file = os.path.join(bimbam_dir, group_name + "_pheno.txt") - convertob = GenerateKinshipMatrices(group_name, geno_input_file, pheno_input_file) + geno_input_file = os.path.join( + bimbam_dir, group_name + "_geno.txt") + pheno_input_file = os.path.join( + bimbam_dir, group_name + "_pheno.txt") + convertob = GenerateKinshipMatrices( + group_name, geno_input_file, pheno_input_file) try: convertob.generate_kinship() except EmptyConfigurations as why: diff --git a/wqflask/maintenance/geno_to_json.py b/wqflask/maintenance/geno_to_json.py index ad3f2b72..7bdf2b53 100644 --- a/wqflask/maintenance/geno_to_json.py +++ b/wqflask/maintenance/geno_to_json.py @@ -100,7 +100,8 @@ class ConvertGenoFile: genotypes = row_items[2:] for item_count, genotype in enumerate(genotypes): if genotype.upper() in self.configurations: - this_marker.genotypes.append(self.configurations[genotype.upper()]) + this_marker.genotypes.append( + self.configurations[genotype.upper()]) else: this_marker.genotypes.append("NA") diff --git a/wqflask/maintenance/quantile_normalize.py b/wqflask/maintenance/quantile_normalize.py index 1896bc52..ac7689f5 100644 --- a/wqflask/maintenance/quantile_normalize.py +++ b/wqflask/maintenance/quantile_normalize.py @@ -34,7 +34,8 @@ def create_dataframe(input_file): with open(input_file) as f: ncols = len(f.readline().split("\t")) - input_array = np.loadtxt(open(input_file, "rb"), delimiter="\t", skiprows=1, usecols=list(range(1, ncols))) + input_array = np.loadtxt(open( + input_file, "rb"), delimiter="\t", skiprows=1, usecols=list(range(1, ncols))) return pd.DataFrame(input_array) # This function taken from https://github.com/ShawnLYU/Quantile_Normalize |