def fastqc_run(input_files, args, end_type):
if end_type == "single":
input_file = input_files[0]
fastqc_command = Command("fastqc")
fastqc_params = {
"-o": os.path.join(args.output, "reports"),
"-t": args.thread,
"-k": "7",
"": input_file
}
elif end_type == "pair":
input_file_1, input_file_2 = input_files
fastqc_command = Command("fastqc")
fastqc_params = {
"-o": os.path.join(args.output, "reports"),
"-t": args.thread,
"-k": "7",
input_file_1 + " " + input_file_2: ""
}
else:
raise ValueError("Unknown end type")
timer_run(fastqc_command, fastqc_params)
def test_pipeline(args):
'''
salmon及びhisat2+salmonを使ったパイプラインを実行する
'''
all_files = [
file for file in os.listdir(args.input)
if file.endswith(args.fastq_type)
]
files_1 = sorted([
file for file in os.listdir(args.input)
if file.endswith("_1" + args.fastq_type)
])
files_2 = sorted([
file for file in os.listdir(args.input)
if file.endswith("_2" + args.fastq_type)
])
single_files = list(set(all_files) - set(files_1) - set(files_2))
# single
print_single_logo()
if len(single_files) == 0:
print("#" * 20, "No single files!", "#" * 20)
print()
else:
for in_file in single_files:
salmon_pipeline([in_file], args, end_type="single")
# pair
print_pair_logo()
if len(files_1) != len(files_2):
raise ValueError("There are not complete pairs")
elif len(files_1) == 0:
print("#" * 20, "No pair files!", "#" * 20)
print()
else:
for in_file_1, in_file_2 in zip(files_1, files_2):
salmon_pipeline([in_file_1, in_file_2], args, end_type="pair")
# multiqc and delete other reports
multiqc_command = Command("multiqc")
multiqc_params = {args.output: "", "-o": args.output}
timer_run(multiqc_command, multiqc_params, deco="+")
shutil.rmtree(os.path.join(args.output, "reports"))
# tximport
tximport_command = Command("Rscript quant2tsv.R")
tximport_params = {args.output: "", args.method: ""}
timer_run(tximport_command, tximport_params, deco="*")
def salmon_aln_run(bam_file, basename, args):
if args.salmon_ref is None:
ref_path = "/local_volume/salmon_ref_index"
else:
ref_path = args.salmon_ref
salmon_output = os.path.join(args.output, basename + "_exp")
os.makedirs(salmon_output, exist_ok=True)
salmon_command = Command("salmon quant")
salmon_params = {
"-t": ref_path,
"-l": "A",
"-a": bam_file,
"-o": salmon_output
}
timer_run(salmon_command, salmon_params)
def hisat2_run(trim_files, basename, args, end_type):
if args.hisat2_ref is None:
ref_path = "/local_volume/hisat2_ref_index"
else:
ref_path = args.hisat2_ref
os.makedir(os.path.join(args.input, "bam_files"), exit_ok=True)
bam_file_name = basename + ".bam"
bam_file = os.path.join(args.input, "bam_files", bam_file_name)
hisat2_command = Command("hisat2")
if end_type == "single":
trim_file = trim_files[0]
hisat2_params = {
"-x": ref_path,
"-U": trim_file,
"-p": args.thread,
"|": "",
"samtools": "sort",
"-@": args.thread,
"-O": "BAM",
"- >": bam_file,
"&&": "",
"samtools": "index",
"-@": args.thread,
bam_file: "",
}
else:
trim_file_1, trim_file_2 = trim_files
hisat2_params = {
"-x": ref_path,
"-1": trim_file_1,
"-2": trim_file_2,
"-p": args.thread,
"|": "",
"samtools": "sort",
"-@": args.thread,
"-O": "BAM",
"- >": bam_file,
"&&": "",
"samtools": "index",
"-@": args.thread,
bam_file: "",
}
timer_run(hisat2_command, hisat2_params)
return bam_file
def make_salmon_index(args):
print("salmon ref index is not detected, now creating...")
os.makedirs("/local_volume/tmp_fa/", exist_ok=True)
subprocess.run([
"wget", "--quite", "--quota=0", "-O",
"/local_volume/tmp_fa/salmon_ref.fa.gz", args.salmon_ref_dl
])
subprocess.run(["gunzip", "/local_volume/tmp_fa/salmon_ref.fa.gz"])
salmon_index_cmd = Command("salmon index")
salmon_index_cmd_params = {
"-t": "/local_volume/tmp_fa/salmon_ref.fa",
"-i": "/local_volume/salmon_ref_index"
}
salmon_index_cmd.parse_params_dict(salmon_index_cmd_params)
salmon_index_cmd.run()
shutil.rmtree("/local_volume/tmp_fa")
def fastp_run(input_files, trim_files, basenames, args, end_type):
fastp_command = Command("fastp")
if end_type == "single":
input_file = input_files[0]
trim_file = trim_files[0]
basename = basenames[0]
fastp_params = {
"-i": input_file,
"-o": trim_file,
"-w": args.thread,
"-h": os.path.join(args.output, "reports",
basename + "_fastp.html"),
"-j": os.path.join(args.output, "reports",
basename + "_fastp.json")
}
elif end_type == "pair":
input_file_1, input_file_2 = input_files
trim_file_1, trim_file_2 = trim_files
basename_1, basename_2 = basenames
fastp_params = {
"-i": input_file_1,
"-I": input_file_2,
"-o": trim_file_1,
"-O": trim_file_2,
"-w": args.thread,
"-h": os.path.join(args.output, "reports",
basename + "_fastp.html"),
"-j": os.path.join(args.output, "reports",
basename + "_fastp.json")
}
else:
raise ValueError("Unknown end type")
if args.fastp is not None:
fastp_params = update_params(fastp_params, args.fastp)
timer_run(fastp_command, fastp_params)
def salmon_map_run(trim_files, basename, args, end_type):
if args.salmon_ref is None:
ref_path = "/local_volume/salmon_ref_index"
else:
ref_path = args.salmon_ref
salmon_output = os.path.join(args.output, basename + "_exp")
os.makedirs(salmon_output, exist_ok=True)
salmon_command = Command("salmon quant")
if end_type == "single":
trim_file = trim_files[0]
salmon_params = {
"-i": ref_path,
"-p": args.thread,
"-l": "A",
"-r": trim_file,
"-o": salmon_output,
"--gcBias": "",
"--validateMappings": "",
}
elif end_type == "pair":
trim_file_1, trim_file_2 = trim_files
salmon_params = {
"-i": ref_path,
"-p": args.thread,
"-l": "A",
"-1": trim_file_1,
"-2": trim_file_2,
"-o": salmon_output,
"--gcBexias": "",
"--validateMappings": "",
}
timer_run(salmon_command, salmon_params)
from function import Command, update_params
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--fastqc", nargs="*")
args = parser.parse_args()
fastqc_dict = {"-o": "test", "-t": "2", "-k": "7", "": "FILENAME"}
fastqc_command = Command("fastqc")
fastqc_command.parse_params_dict(fastqc_dict)
print(fastqc_command)
update_fastqc_params = args.fastqc
updated_dict = update_params(fastqc_dict, update_fastqc_params)
fastqc_command.parse_params_dict(updated_dict)
print(updated_dict)