diff options
Diffstat (limited to 'wqflask/maintenance')
| -rw-r--r-- | wqflask/maintenance/convert_dryad_to_bimbam.py | 2 | ||||
| -rw-r--r-- | wqflask/maintenance/convert_geno_to_bimbam.py | 4 | ||||
| -rw-r--r-- | wqflask/maintenance/generate_kinship_from_bimbam.py | 8 | ||||
| -rw-r--r-- | wqflask/maintenance/geno_to_json.py | 34 |
4 files changed, 24 insertions, 24 deletions
diff --git a/wqflask/maintenance/convert_dryad_to_bimbam.py b/wqflask/maintenance/convert_dryad_to_bimbam.py index e417c280..18fbb8a1 100644 --- a/wqflask/maintenance/convert_dryad_to_bimbam.py +++ b/wqflask/maintenance/convert_dryad_to_bimbam.py @@ -52,7 +52,7 @@ def read_dryad_file(filename): # this_row.append(line.split(" ")[i+2]) # print("row: " + str(i)) # geno_rows.append(this_row) - # + # # return geno_rows diff --git a/wqflask/maintenance/convert_geno_to_bimbam.py b/wqflask/maintenance/convert_geno_to_bimbam.py index a2ede1f9..c5af1ca6 100644 --- a/wqflask/maintenance/convert_geno_to_bimbam.py +++ b/wqflask/maintenance/convert_geno_to_bimbam.py @@ -91,7 +91,7 @@ class ConvertGenoFile: self.markers.append(this_marker.__dict__) - self.write_to_bimbam() + self.write_to_bimbam() def write_to_bimbam(self): with open(self.output_files[0], "w") as geno_fh: @@ -126,7 +126,7 @@ class ConvertGenoFile: self.sample_list = row_contents[3:] else: self.sample_list = row_contents[2:] - + def process_rows(self): for self.latest_row_pos, row in enumerate(self.input_fh): self.latest_row_value = row diff --git a/wqflask/maintenance/generate_kinship_from_bimbam.py b/wqflask/maintenance/generate_kinship_from_bimbam.py index bed634fa..cd39fceb 100644 --- a/wqflask/maintenance/generate_kinship_from_bimbam.py +++ b/wqflask/maintenance/generate_kinship_from_bimbam.py @@ -19,7 +19,7 @@ class GenerateKinshipMatrices: self.group_name = group_name self.geno_file = geno_file 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 + \ @@ -56,11 +56,11 @@ class GenerateKinshipMatrices: print(" Column is:", convertob.latest_col_value) print(" Row is:", convertob.latest_row_value) break - - + + if __name__ == "__main__": Geno_Directory = """/export/local/home/zas1024/genotype_files/genotype/""" Bimbam_Directory = """/export/local/home/zas1024/genotype_files/genotype/bimbam/""" GenerateKinshipMatrices.process_all(Geno_Directory, Bimbam_Directory) - + # ./gemma -g /home/zas1024/genotype_files/genotype/bimbam/BXD_geno.txt -p /home/zas1024/genotype_files/genotype/bimbam/BXD_pheno.txt -gk 1 -o BXD diff --git a/wqflask/maintenance/geno_to_json.py b/wqflask/maintenance/geno_to_json.py index 76a0fc98..27eb6553 100644 --- a/wqflask/maintenance/geno_to_json.py +++ b/wqflask/maintenance/geno_to_json.py @@ -29,7 +29,7 @@ from pprint import pformat as pf class EmptyConfigurations(Exception): pass - + class Marker: def __init__(self): self.name = None @@ -42,20 +42,20 @@ class Marker: class ConvertGenoFile: def __init__(self, input_file, output_file): - + self.input_file = input_file self.output_file = output_file - + self.mb_exists = False self.cm_exists = False self.markers = [] - + self.latest_row_pos = None self.latest_col_pos = None - + self.latest_row_value = None self.latest_col_value = None - + def convert(self): self.haplotype_notation = { @@ -64,16 +64,16 @@ class ConvertGenoFile: '@het': "0.5", '@unk': "NA" } - + self.configurations = {} #self.skipped_cols = 3 - + # if self.input_file.endswith(".geno.gz"): # print("self.input_file: ", self.input_file) # self.input_fh = gzip.open(self.input_file) # else: self.input_fh = open(self.input_file) - + with open(self.output_file, "w") as self.output_fh: # if self.file_type == "geno": self.process_csv() @@ -105,22 +105,22 @@ class ConvertGenoFile: self.configurations[genotype.upper()]) else: this_marker.genotypes.append("NA") - - #print("this_marker is:", pf(this_marker.__dict__)) + + #print("this_marker is:", pf(this_marker.__dict__)) # if this_marker.chr == "14": self.markers.append(this_marker.__dict__) with open(self.output_file, 'w') as fh: json.dump(self.markers, fh, indent=" ", sort_keys=True) - + # print('configurations:', str(configurations)) #self.latest_col_pos = item_count + self.skipped_cols #self.latest_col_value = item - + # if item_count != 0: # self.output_fh.write(" ") # self.output_fh.write(self.configurations[item.upper()]) - + # self.output_fh.write("\n") def process_rows(self): @@ -176,12 +176,12 @@ class ConvertGenoFile: print(" Column is:", convertob.latest_col_value) print(" Row is:", convertob.latest_row_value) break - + # def process_snps_file(cls, snps_file, new_directory): # output_file = os.path.join(new_directory, "mouse_families.json") # print("%s -> %s" % (snps_file, output_file)) # convertob = ConvertGenoFile(input_file, output_file) - + if __name__ == "__main__": Old_Geno_Directory = """/export/local/home/zas1024/gn2-zach/genotype_files/genotype""" @@ -192,5 +192,5 @@ if __name__ == "__main__": # convertob.convert() ConvertGenoFile.process_all(Old_Geno_Directory, New_Geno_Directory) # ConvertGenoFiles(Geno_Directory) - + #process_csv(Input_File, Output_File) |