def convert_sort(self, sort_gene_origin):
"""
Function creates a sorted and indexed bam file from given bam file
Parameters
----------
sort_gene_origin: str
Bam file's name that created by mapping algorithm
"""
if self.map_type == "Novoalign":
convert_sort = self.get_paths.novoalign + "novosort -m 16g -t . -c " + self.threads + " --removeduplicates --keeptags " + \
sort_gene_origin + " -i -o SortedBAM_" + sort_gene_origin
log_command(convert_sort, "Convert Sort", self.threads, "Mapping")
self.file_list.append("SortedBAM_" + sort_gene_origin)
self.file_list.append("SortedBAM_" + sort_gene_origin + ".bai")
else:
convert_sort = "samtools view -@" + self.threads + " -bS " + sort_gene_origin + " | samtools sort -@" + \
self.threads + " -o SortedBAM_" + sort_gene_origin
log_command(convert_sort, "Convert Sort", self.threads, "Mapping")
self.file_list.append("SortedBAM_" + sort_gene_origin)
indexed = helpers.create_index("SortedBAM_" + sort_gene_origin,
"Create Index", self.threads,
"Mapping")
self.file_list.append(indexed)
def gatk4_applybsqr(self, lastbam, recaltable):
afterbqsrbam = "GATK4_" + lastbam
apply_command = self.get_paths.gatk4_path + " ApplyBQSR -R " + self.bundle_dir + "Homo_sapiens_assembly38.fasta -I " + \
lastbam + " --bqsr-recal-file " + recaltable + " -O " + afterbqsrbam
log_command(apply_command, "ApplyBQSR", self.threads,
"Gatk4PreProcessing")
self.file_list.append(afterbqsrbam)
indexed = helpers.create_index(afterbqsrbam,
"Create Index by GATK_ApplyBSQR",
self.threads, "GatkPreProcess")
self.file_list.append(indexed)
def gatk3_print_reads(self, lastbam, bqsr):
nct = " -nct " + str(self.threads)
aftercalibratorBam = "GATK_PR" + lastbam
bcal = "java -jar " + self.get_paths.gatk_path + nct + " -T PrintReads -R " + self.bundle_dir + \
"/ucsc.hg19.fasta -I " + lastbam + " --BQSR " + bqsr + " -o " + aftercalibratorBam
log_command(bcal, "Print Reads", self.threads, "GatkPreProcessing")
self.file_list.append(aftercalibratorBam)
indexed = helpers.create_index(aftercalibratorBam,
"Create Index by GATK_PrintReads",
self.threads, "GatkPreProcess")
self.file_list.append(indexed)
def convert_sort(self, sort_gene_origin):
"""
Function creates a sorted and indexed bam file from given bam file
Parameters
----------
sort_gene_origin: str
Bam file's name that created by mapping algorithm
"""
convert_sort = "samtools view -@" + self.threads + " -bS " + sort_gene_origin + " | samtools sort -@" + \
self.threads + " -o SortedBAM_" + sort_gene_origin
log_command(convert_sort, "Convert Sort", self.threads, "Mapping")
self.file_list.append("SortedBAM_" + sort_gene_origin)
indexed = helpers.create_index("SortedBAM_" + sort_gene_origin, "Create Index", self.threads, "Mapping")
self.file_list.append(indexed)
def pre_process(self, info_dict, all_bam_files):
if self.split_chr == "After":
merged_file = self.merge_bams(info_dict, all_bam_files)
self.file_list.append(merged_file)
indexed = helpers.create_index(merged_file, "Create Index by Merge", self.threads, "Pre Processing")
self.file_list.append(indexed)
splitted_files = split_bam_by_chr(merged_file)
for splitted_file in splitted_files:
index_start = splitted_file.find("_Chr_")
chr_a = splitted_file[index_start:]
mark_duplicate_file = self.mark_duplicate(splitted_file, chr_a)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(mark_duplicate_file, "Create Index by MarkDuplicate", self.threads,
"Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory, self.file_list, map_type=self.map_type, step="PreProcess",
folder_directory=self.folder_directory)
return_files = [a for a in self.file_list if "MDUP" in a and "bam" in a]
return return_files
elif self.split_chr == "Before":
for bam_file in all_bam_files:
splitted_files = split_bam_by_chr(bam_file)
all_chr_files = get_bam_by_chr()
print("preprocess line 128" )
print( all_chr_files)
for i in all_chr_files:
merged_file = self.merge_bams(info_dict, all_chr_files[i])
self.file_list.append(merged_file)
indexed = helpers.create_index(merged_file, "Create Index by Merge", self.threads, "Pre Processing")
self.file_list.append(indexed)
index_start = all_chr_files[i][0].find("_Chr_")
chr_a = all_chr_files[i][0][index_start:]
mark_duplicate_file = self.mark_duplicate(merged_file, chr_a)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(mark_duplicate_file, "Create Index by MarkDuplicate", self.threads,
"Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory, self.file_list, map_type=self.map_type, step="PreProcess",
folder_directory=self.folder_directory)
return_files = [a for a in self.file_list if "MDUP" in a and "bam" in a]
return return_files
# self.split_chr == "No":
else:
if self.map_type == "Novoalign":
mark_duplicate_file = self.novoalign_sort_markduplicate(info_dict, all_bam_files)
#self.file_list.append(indexed)
helpers.create_folder(self.working_directory, self.file_list, map_type=self.map_type, step="PreProcess",
folder_directory=self.folder_directory)
return mark_duplicate_file
merged_file = self.merge_bams(info_dict, all_bam_files)
indexed = helpers.create_index(merged_file, "Create Index by Merge", self.threads, "Pre Processing")
self.file_list.append(merged_file)
self.file_list.append(indexed)
mark_duplicate_file = self.mark_duplicate(merged_file,"")
print("preprocess mark duplicate file " )
print(mark_duplicate_file)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(mark_duplicate_file, "Create Index by MarkDuplicate", self.threads,
"Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory, self.file_list, map_type=self.map_type, step="PreProcess",
folder_directory=self.folder_directory)
return mark_duplicate_file
# if __name__ == "__main__":
# pre_processing_step = PreProcessing(working_directory="/home/bioinformaticslab/Desktop/GitHub_Repos/Genomics_Pipeline_Test/test_files",
# map_type="Bwa", sample_type="Tumor", library_matching_id="203", thrds="1", issplitchr="Before")
#
# mapping_step = mapping.Mapping(working_directory=pre_processing_step.main_directory,
# map_type="Bwa", sample_type="Tumor", library_matching_id="203", thrds="3")
#
# fastq_list = mapping_step.get_fastq()
# info_dict = mapping_step.get_info(fastq_list)
# os.chdir(pre_processing_step.working_directory)
# bam_files = glob.glob("SortedBAM*.bam")
# mark_duplicate_file = pre_processing_step.pre_process(info_dict, bam_files)
# print(mark_duplicate_file)
def pre_process(self, info_dict, all_bam_files):
if self.split_chr == "After":
merged_file = self.merge_bams(info_dict, all_bam_files)
self.file_list.append(merged_file)
indexed = helpers.create_index(merged_file,
"Create Index by Merge",
self.threads, "Pre Processing")
self.file_list.append(indexed)
splitted_files = split_bam_by_chr(merged_file)
for splitted_file in splitted_files:
index_start = splitted_file.find("_Chr_")
chr_a = splitted_file[index_start:]
mark_duplicate_file = self.mark_duplicate(splitted_file, chr_a)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(
mark_duplicate_file, "Create Index by MarkDuplicate",
self.threads, "Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory,
self.file_list,
map_type=self.map_type,
step="PreProcess",
folder_directory=self.folder_directory)
return_files = [
a for a in self.file_list if "MDUP" in a and "bam" in a
]
return return_files
elif self.split_chr == "Before":
for bam_file in all_bam_files:
splitted_files = split_bam_by_chr(bam_file)
all_chr_files = get_bam_by_chr()
print("preprocess line 128")
print(all_chr_files)
for i in all_chr_files:
merged_file = self.merge_bams(info_dict, all_chr_files[i])
self.file_list.append(merged_file)
indexed = helpers.create_index(merged_file,
"Create Index by Merge",
self.threads, "Pre Processing")
self.file_list.append(indexed)
index_start = all_chr_files[i][0].find("_Chr_")
chr_a = all_chr_files[i][0][index_start:]
mark_duplicate_file = self.mark_duplicate(merged_file, chr_a)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(
mark_duplicate_file, "Create Index by MarkDuplicate",
self.threads, "Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory,
self.file_list,
map_type=self.map_type,
step="PreProcess",
folder_directory=self.folder_directory)
return_files = [
a for a in self.file_list if "MDUP" in a and "bam" in a
]
return return_files
# self.split_chr == "No":
else:
merged_file = self.merge_bams(info_dict, all_bam_files)
indexed = helpers.create_index(merged_file,
"Create Index by Merge",
self.threads, "Pre Processing")
self.file_list.append(merged_file)
self.file_list.append(indexed)
mark_duplicate_file = self.mark_duplicate(merged_file, "")
print("preprocess mark duplicate file ")
print(mark_duplicate_file)
self.file_list.append(mark_duplicate_file)
indexed = helpers.create_index(mark_duplicate_file,
"Create Index by MarkDuplicate",
self.threads, "Pre Processing")
self.file_list.append(indexed)
helpers.create_folder(self.working_directory,
self.file_list,
map_type=self.map_type,
step="PreProcess",
folder_directory=self.folder_directory)
return mark_duplicate_file