def control_func(preprocess=preprocess, key=key):
control_bamfile = preprocess.control_bamfile_list[key]
processed_bam = control_bamfile #control_bamfile.dirname + "/" + control_bamfile.samplename#+"_preprocessed.bam"
if control_bamfile.isexist(
): #and control_bamfile.ln(processed_bam, control_bamfile.samplename):
control_bamfile = BamFile(processed_bam,
control_bamfile.samplename, cfg)
#control_bamfile.index(cfg["samtools"])
preprocess.control_bamfile_list[key] = control_bamfile
def convert2bam(self, out_bam):
config_dict = self.config_dict
samtools = config_dict["samtools"]
info("Running samtools to convert %s SAM File to %s Bam file." %
(self.path, out_bam))
cmd = "%s view -bS %s -o %s" % (samtools, self.path, out_bam)
out_bam = BamFile(out_bam, self.samplename, config_dict)
if out_bam.isexist():
savecmd(cmd, self.samplename)
return (out_bam)
elif self.isexist():
if not out_bam.isexist():
runcmd(cmd)
savecmd(cmd, self.samplename)
return (out_bam)
else:
info(self.path +
" is not exists, cannot conduct the convert2bam step!")
def pre_process(options):
"""
pre_process:Be imported in rnaseq.py, conduct the genome index, fastq mapping, several of bam file preprocess step.
"""
cfg = get_config(options.config)
preprocess = PreProcessor(options)
try:
genome_process = options.genome_index #Genomeindex be set in rnaseq.py mode parameter
except:
genome_process = 0
try:
fastq_mapping = options.fastq_mapping #fastq_mapping be set in rnaseq.py mode parameter
except:
fastq_mapping = 0
add_read_group = options.bamprocess[0] # -d --bamprocess 0111
contig_reorder = options.bamprocess[1] # 0 or 1
mark_duplicates = options.bamprocess[2]
split_ntrim = options.bamprocess[3]
realigner_target_creator = options.bamprocess[4]
indel_realigner = options.bamprocess[5]
recalibration = options.bamprocess[6]
print_reads = options.bamprocess[7]
############# Value equal 0 not to be run, and equal 1 will be run ##########
if genome_process != "0":
status = preprocess.genome_pre_process()
if options.mode == "genomeindex":
return (status)
if fastq_mapping != "0":
preprocess.fastq_mapping()
#Bam process
if add_read_group != "0":
preprocess.add_read_group()
if contig_reorder != "0":
preprocess.contig_reorder()
if mark_duplicates != "0":
preprocess.mark_duplicates()
if split_ntrim != "0":
preprocess.split_ntrim()
if realigner_target_creator != "0":
preprocess.realigner_target_creator()
if indel_realigner != "0":
preprocess.indel_realigner()
if recalibration != "0":
preprocess.recalibration()
if print_reads != "0":
preprocess.print_reads()
#Get copy and rename
for key in preprocess.bamfile_list.keys():
bamfile = preprocess.bamfile_list[key]
processed_bam = bamfile #.dirname + "/" + bamfile.samplename+"_preprocessed.bam"
if bamfile.isexist(
): #and bamfile.ln(processed_bam, bamfile.samplename):
bamfile = BamFile(processed_bam, bamfile.samplename, cfg)
#bamfile.index(cfg["samtools"])
preprocess.bamfile_list[key] = bamfile
return (preprocess.bamfile_list)
def __init__(self, options):
FundementalPreprocess.__init__(self, options)
if options.mode != "genomeindex":
self.case_bamfile_list = {
"Bwa":
BamFile(options.case_in_bam, self.samplename + "A", self.cfg)
}
self.control_bamfile_list = {
"Bwa":
BamFile(options.control_in_bam, self.samplename + "C",
self.cfg)
}
self.caseoptions = copy.deepcopy(options)
self.caseoptions.fastq1 = self.options.case_fastq1
self.caseoptions.fastq2 = self.options.case_fastq2
self.caseoptions.samplename = options.samplename + "A"
self.controloptions = copy.deepcopy(options)
self.controloptions.fastq1 = options.control_fastq1
self.controloptions.fastq2 = options.control_fastq2
self.controloptions.samplename = options.samplename + "C"
def pre_process_self(options):
"""
pre_process_self:Be useed, when run the module of self, using options.dataprocess to control the step be runned.
"""
cfg = get_config(options.config)
preprocess = PreProcessor(options)
genome_process = options.dataprocess[0]
fastq_mapping = options.dataprocess[1]
add_read_group = options.dataprocess[2]
contig_reorder = options.dataprocess[3]
mark_duplicates = options.dataprocess[4]
split_ntrim = options.dataprocess[5]
realigner_target_creator = options.dataprocess[6]
indel_realigner = options.dataprocess[7]
recalibration = options.dataprocess[8]
print_reads = options.dataprocess[9]
if genome_process != "0":
status = preprocess.genome_pre_process()
if options.mode == "genomeindex":
return (status)
if fastq_mapping != "0":
preprocess.fastq_mapping()
if add_read_group != "0":
preprocess.add_read_group()
if contig_reorder != "0":
preprocess.contig_reorder()
if mark_duplicates != "0":
preprocess.mark_duplicates()
if split_ntrim != "0":
preprocess.split_ntrim()
if realigner_target_creator != "0":
preprocess.realigner_target_creator()
if indel_realigner != "0":
preprocess.indel_realigner()
if recalibration != "0":
preprocess.recalibration()
if print_reads != "0":
preprocess.print_reads()
for key in preprocess.bamfile_list.keys():
bamfile = preprocess.bamfile_list[key]
processed_bam = bamfile #bamfile.dirname + "/" + bamfile.samplename#+"_preprocessed.bam"
if bamfile.isexist(
): #and bamfile.ln(processed_bam, bamfile.samplename):
bamfile = BamFile(processed_bam, bamfile.samplename, cfg)
#bamfile.index(cfg["samtools"])
preprocess.bamfile_list[key] = bamfile
else:
info("Not found avaliable bam file in input!")
return (False)
return (preprocess.bamfile_list)
def __init__(self, options):
FundementalPreprocess.__init__(self, options)
if options.mode != "genomeindex":
self.bamfile_list = {
"Default": BamFile(options.in_bam, self.samplename, self.cfg)
}