def sam_to_index_bam(args):
# input_sam_path = os.path.abspath(input_sam)
# if output_bam == "inputdir":
# output_bam = os.path.dirname(input_sam_path)
# else:
# output_bam = output_bam
r1 = os.path.abspath(args.r1_file)
r2 = os.path.abspath(args.r2_file)
sample = extract_sample(r1, r2)
output_dir = obtain_output_dir(args, "Bam")
sample_name = sample + ".sam"
input_sam_path = os.path.join(output_dir, sample_name)
input_name = (".").join(os.path.basename(input_sam_path).split(".")[:-1])
output_bam_name = input_name + ".bam"
output_bam_path = os.path.join(output_dir, output_bam_name)
output_bg_sorted_name = input_name + ".rg.sorted.bam"
output_bg_sorted_path = os.path.join(output_dir, output_bg_sorted_name)
check_create_dir(output_dir)
"""
#sam to bam: samtools view -Sb $input_file -o $output_dir/$sample.bam
with open(output_bam_path, "w") as outfile:
#map reads and save it in th eoutput file
subprocess.run(["samtools", "view", "-Sb", input_sam_path],
stdout=outfile, stderr=subprocess.PIPE, check=True, universal_newlines=True)
"""
cmd = [
"samtools", "view", "-Sb", input_sam_path, "-o", output_bam_path,
"--threads",
str(args.threads)
]
execute_subprocess(cmd)
check_remove_file(input_sam_path)
add_SG(args, output_bam_path, output_bg_sorted_path)
check_remove_file(output_bam_path)
"""
def picard_markdup(args):
#java -jar picard.jar MarkDuplicates \
# I=input.bam O=marked_duplicates.bam M=marked_dup_metrics.txt
picard_jar = get_picard_path()
input_bam = os.path.abspath(args.input_bam)
in_param = "I=" + input_bam
path_file_name = input_bam.split(".")[0]
file_name = path_file_name.split("/")[-1]
output_markdup = path_file_name + ".rg.markdup.bam"
output_markdup_sorted = path_file_name + ".rg.markdup.sorted.bam"
out_param = "O=" + output_markdup
stat_output_dir = obtain_output_dir(args, "Stats")
stat_output_file = file_name + ".markdup.metrics.txt"
stat_output_full = os.path.join(stat_output_dir, stat_output_file)
stats_param = "M=" + stat_output_full
check_create_dir(stat_output_dir)
cmd_markdup = [
"java", "-jar", picard_jar, "MarkDuplicates", in_param, out_param,
stats_param
]
execute_subprocess(cmd_markdup)
#samtools sort: samtools sort $output_dir/$sample".sorted.bam" -o $output_dir/$sample".sorted.bam"
cmd_sort = [
"samtools", "sort", output_markdup, "-o", output_markdup_sorted
]
execute_subprocess(cmd_sort)
#Handled in Haplotype Caller function
#samtools index: samtools index $output_dir/$sample".sorted.bam"
subprocess.run(["samtools", "index", output_markdup_sorted],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
check=True)
check_remove_file(input_bam)
check_remove_file(output_markdup)
def ivar_trim(input_bam,
primers_file,
sample,
min_length=30,
min_quality=20,
sliding_window_width=4):
"""
Usage: ivar trim -i <input.bam> -b <primers.bed> -p <prefix> [-m <min-length>] [-q <min-quality>] [-s <sliding-window-width>]
Input Options Description
-i (Required) Sorted bam file, with aligned reads, to trim primers and quality
-b (Required) BED file with primer sequences and positions
-m Minimum length of read to retain after trimming (Default: 30)
-q Minimum quality threshold for sliding window to pass (Default: 20)
-s Width of sliding window (Default: 4)
-e Include reads with no primers. By default, reads with no primers are excluded
Output Options Description
-p (Required) Prefix for the output BAM file
"""
input_bam = os.path.abspath(input_bam)
input_bai = input_bam + ".bai"
primers_file = os.path.abspath(primers_file)
prefix = input_bam.split('.')[0] + ".rg.markdup.trimmed"
output_trimmed_bam = prefix + ".bam"
output_trimmed_sorted_bam = input_bam.split(
'.')[0] + ".rg.markdup.trimmed.sorted.bam"
cmd = [
"ivar", "trim", "-i", input_bam, "-b", primers_file, "-p", prefix,
"-m",
str(min_length), "-q",
str(min_quality), "-s",
str(sliding_window_width), "-e"
]
execute_subprocess(cmd)
check_remove_file(input_bam)
cmd_sort = [
"samtools", "sort", output_trimmed_bam, "-o", output_trimmed_sorted_bam
]
execute_subprocess(cmd_sort)
check_remove_file(output_trimmed_bam)
cmd_index = ["samtools", "index", output_trimmed_sorted_bam]
execute_subprocess(cmd_index)
check_remove_file(input_bai)
def sam_to_index_bam(sample, output_dir, r1, threads):
# input_sam_path = os.path.abspath(input_sam)
# if output_bam == "inputdir":
# output_bam = os.path.dirname(input_sam_path)
# else:
# output_bam = output_bam
sample_name = sample + ".sam"
input_sam_path = os.path.join(output_dir, sample_name)
input_name = (".").join(os.path.basename(input_sam_path).split(".")[:-1])
output_bam_name = input_name + ".bam"
output_bam_path = os.path.join(output_dir, output_bam_name)
output_sorted_name = input_name + ".sorted.bam"
output_sorted_path = os.path.join(output_dir, output_sorted_name)
output_bg_sorted_name = input_name + ".rg.sorted.bam"
output_bg_sorted_path = os.path.join(output_dir, output_bg_sorted_name)
cmd_view = [
"samtools",
"view",
"-Sb",
input_sam_path,
"--threads",
str(threads),
"-o",
output_bam_path,
]
execute_subprocess(cmd_view)
check_remove_file(input_sam_path)
cmd_sort = ["samtools", "sort", output_bam_path, "-o", output_sorted_path]
execute_subprocess(cmd_sort)
check_remove_file(output_bam_path)
add_SG(sample, output_sorted_path, output_bg_sorted_path, r1)
check_remove_file(output_sorted_path)
"""
######################################################################
#####################START PIPELINE###################################
######################################################################
output = os.path.abspath(args.output)
group_name = args.input.split("/")[-1].split(".")[0]
out_vcf_dir = os.path.join(args.output, "VCF")
check_create_dir(out_vcf_dir)
output_vcf_file = os.path.abspath(args.input)
base_input = os.path.basename(args.input)
linked_file = os.path.join(out_vcf_dir, base_input)
check_remove_file(linked_file)
os.symlink(output_vcf_file, linked_file)
print("\n\n" + BLUE + BOLD +
"STARTING COHORT GVCF TO SPLIT SAMPLE VCF IN GROUP: " + group_name +
END_FORMATTING)
#SELECT VARIANTS 2/2 FOR HARD FILTERING AND RECALIBRATION
#########################################################
out_vcfsnp_name = group_name + ".cohort.snp.vcf"
output_vcfsnp_file = os.path.join(out_vcf_dir, out_vcfsnp_name)
if os.path.isfile(output_vcfsnp_file):
print(YELLOW + DIM + output_vcfsnp_file +
" EXIST\nOmmiting Variant Selection (Group) for group " +