def step3_QC(conf_dict, logfile):
'''
start RseQC
mapping stat
single cell level QC
'''
# start
# create section for
Log('Step3: bulk and individual cell QC', logfile)
### preparing mapping state dict
Log('calculate mapping state', logfile)
conf_dict['Mapping_stat'] = {}
conf_dict['Mapping_stat']['umi_gene'] = 0
conf_dict['Mapping_stat']['cdsN'] = 0
conf_dict['Mapping_stat']['utr3N'] = 0
conf_dict['Mapping_stat']['utr5N'] = 0
conf_dict['Mapping_stat']['intronN'] = 0
conf_dict['Mapping_stat']['intergenicN'] = 0
### calculate mapping state based on QC matrix
inf = open(conf_dict['Step2_ExpMat']['qcmatfull'])
for line in inf:
if line.startswith('cellname'):
continue
ll = line.split()
conf_dict['Mapping_stat']['umi_gene'] += int(ll[2])
conf_dict['Mapping_stat']['cdsN'] += int(ll[3])
conf_dict['Mapping_stat']['utr3N'] += int(ll[4])
conf_dict['Mapping_stat']['utr5N'] += int(ll[5])
conf_dict['Mapping_stat']['intronN'] += int(ll[6])
conf_dict['Mapping_stat']['intergenicN'] += int(ll[7])
inf.close()
conf_dict['Mapping_stat']['totalreads'] = int(
Get('wc -l %s' %
(conf_dict['General']['barcode_reform']))[0].split()[0])
conf_dict['Mapping_stat']['q30reads'] = int(
Get('wc -l %s' % (conf_dict['General']['bed']))[0].split()[0])
### create QC dir and conduct QC
Log(
'generate reads QC measurement with own script, based on sample down reads',
logfile)
qcdir = conf_dict['General']['outputdirectory'] + 'QC/'
CreateDirectory(qcdir)
os.chdir(qcdir)
conf_dict['QCplots'] = {}
conf_dict['QCplots']['map_summary'] = qcdir + conf_dict['General'][
'outname'] + '_map_summary.txt'
mapsummary_doc = """genomic region(Category)\treads number
total reads\t%s
mappble reads\t%s
total UMI count\t%s
CDS exon UMI count\t%s
3'UTR UMI count\t%s
5'UTR UMI count\t%s
intron UMI count\t%s
intergenic UMI count\t%s
""" % (str(conf_dict['Mapping_stat']['totalreads']),
str(conf_dict['Mapping_stat']['q30reads']),
str(conf_dict['Mapping_stat']['umi_gene']),
str(conf_dict['Mapping_stat']['cdsN']),
str(conf_dict['Mapping_stat']['utr3N']),
str(conf_dict['Mapping_stat']['utr5N']),
str(conf_dict['Mapping_stat']['intronN']),
str(conf_dict['Mapping_stat']['intergenicN']))
outf = open(conf_dict['QCplots']['map_summary'], 'w')
outf.write(mapsummary_doc)
outf.close()
## reads quality
t = time.time()
readsqc(conf_dict['General']['sampledownsam'],
conf_dict['General']['outname'])
Log(
'generate bulk cell QC measurement with own script, based on sample down reads',
logfile)
cmd = "bedtools intersect -a %s -b %s -c > %s" % (
conf_dict['General']['outputdirectory'] + 'annotation/' +
conf_dict['General']['outname'] + '_gene_anno_binexon.bed',
conf_dict['General']['sampledownbed'],
conf_dict['General']['outname'] + '_sampledown_on_gbbin.bed')
LogCommand(cmd, logfile)
GBcover(conf_dict['General']['outname'] + '_sampledown_on_gbbin.bed',
conf_dict['General']['outname'])
cmd = "%s %s %s" % ('Rscript',
conf_dict['rscript'] + 'DrSeq_readsbulk_QC.r',
conf_dict['General']['outname'])
LogCommand(cmd, logfile)
# cmd = "%s -i %s -o %s"%(conf_dict['Step3_QC']['read_qul'],conf_dict['General']['sam'],conf_dict['General']['outname'])
# LogCommand(cmd,logfile)
# ## reads nucleotide composition
# cmd = "%s -i %s -o %s"%(conf_dict['Step3_QC']['read_nvc'],conf_dict['General']['sam'],conf_dict['General']['outname'])
# LogCommand(cmd,logfile)
# ## reads GC content
# cmd = "%s -i %s -o %s"%(conf_dict['Step3_QC']['read_gc'],conf_dict['General']['sam'],conf_dict['General']['outname'])
# LogCommand(cmd,logfile)
# readsqctime = time.time() -t
# Log("time for readsqc: %s"%(readsqctime),logfile)
# ## reads genebody coverage
# t= time.time()
#
# cmd = "%s -i %s -o %s -r %s"%(conf_dict['Step3_QC']['gb_cover'],conf_dict['General']['sam'],conf_dict['General']['outname'],conf_dict['General']['outputdirectory'] + 'annotation/'+conf_dict['General']['outname']+'_gene_anno_fullbed.bed')
# LogCommand(cmd,logfile)
# bulkqctime = time.time() -t
# Log("time for bulkqc: %s"%(bulkqctime),logfile)
# mvcmd1 = "mv %s %s"%(qcdir + conf_dict['General']['outname'] + '.qual.heatmap.pdf',qcdir + conf_dict['General']['outname'] + '_quality_heatmap.pdf')
# mvcmd2 = "mv %s %s"%(qcdir + conf_dict['General']['outname'] + '.NVC_plot.pdf',qcdir + conf_dict['General']['outname'] + '_NVC.pdf')
# mvcmd3 = "mv %s %s"%(qcdir + conf_dict['General']['outname'] + '.GC_plot.pdf',qcdir + conf_dict['General']['outname'] + '_GC.pdf')
# mvcmd4 = "mv %s %s"%(qcdir + conf_dict['General']['outname'] + '.geneBodyCoverage.pdf',qcdir + conf_dict['General']['outname'] + '_GBcover.pdf')
# LogCommand(mvcmd1,logfile)
# LogCommand(mvcmd2,logfile)
# LogCommand(mvcmd3,logfile)
# LogCommand(mvcmd4,logfile)
#
conf_dict['QCplots']['read_qul'] = qcdir + conf_dict['General'][
'outname'] + '_Figure1_quality_heatmap.pdf'
conf_dict['QCplots']['read_nvc'] = qcdir + conf_dict['General'][
'outname'] + '_Figure2_NVC.pdf'
conf_dict['QCplots']['read_gc'] = qcdir + conf_dict['General'][
'outname'] + '_Figure3_GC.pdf'
conf_dict['QCplots']['gb_cover'] = qcdir + conf_dict['General'][
'outname'] + '_Figure4_GBcover.pdf'
bulkqctime = time.time() - t
Log("time for bulkqc: %s" % (bulkqctime), logfile)
### individual cell QC
Log('generate individual cell QC measurement', logfile)
t = time.time()
conf_dict['QCplots']['duprate'] = qcdir + conf_dict['General'][
'outname'] + '_Figure5_duprate.pdf'
conf_dict['QCplots']['covergn'] = qcdir + conf_dict['General'][
'outname'] + '_Figure8_coverGN.pdf'
conf_dict['QCplots']['intronrate'] = qcdir + conf_dict['General'][
'outname'] + '_Figure9_intronrate.pdf'
if conf_dict['General']['png_for_dot'] == 1:
conf_dict['QCplots']['umicovergn'] = qcdir + conf_dict['General'][
'outname'] + '_Figure7_umi_coverGN.png'
conf_dict['QCplots']['cumumiduprate'] = qcdir + conf_dict['General'][
'outname'] + '_Figure6_cumUMI_duprate.png'
else:
conf_dict['QCplots']['umicovergn'] = qcdir + conf_dict['General'][
'outname'] + '_Figure7_umi_coverGN.pdf'
conf_dict['QCplots']['cumumiduprate'] = qcdir + conf_dict['General'][
'outname'] + '_Figure6_cumUMI_duprate.pdf'
conf_dict['Step2_ExpMat']['qcmatcc'] = qcdir + conf_dict['General'][
'outname'] + "_qcmat_clustercell.txt"
conf_dict['Step2_ExpMat']['expmatcc'] = qcdir + conf_dict['General'][
'outname'] + "_expmat_clustercell.txt"
conf_dict['results']['expmatcc'] = qcdir + conf_dict['General'][
'outname'] + "_expmat_clustercell.txt"
if int(conf_dict['Step3_QC']['select_cell_measure']) == 1:
use_cutoff = conf_dict['Step3_QC']['covergncluster']
elif int(conf_dict['Step3_QC']['select_cell_measure']) == 2:
use_cutoff = conf_dict['Step3_QC']['topumicellnumber']
else:
LogError(
'select_cell_measure value can only be 1 or 2, current value is %s'
% (conf_dict['Step4_Analysis']['select_cell_measure']), logfile)
cmd = "%s %s %s %s %s %s %s %s %s %s %s %s %s" % (
'Rscript', conf_dict['rscript'] + 'DrSeq_individual_QC.r',
conf_dict['Step2_ExpMat']['qcmat'],
conf_dict['Step2_ExpMat']['expmat'], conf_dict['General']['outname'],
conf_dict['Step3_QC']['select_cell_measure'], use_cutoff,
conf_dict['Step3_QC']['remove_low_dup_cell'],
conf_dict['Step3_QC']['non_dup_cutoff'],
conf_dict['Mapping_stat']['umi_gene'],
conf_dict['Step2_ExpMat']['qcmatcc'],
conf_dict['Step2_ExpMat']['expmatcc'],
conf_dict['General']['png_for_dot'])
LogCommand(cmd, logfile)
individualqctime = time.time() - t
Log("time for individualqc: %s" % (individualqctime), logfile)
Log("Step3 bulk and individual cell QC DONE", logfile)
return conf_dict
def step1_generate_matrix(conf_dict, logfile):
'''
generate expression matrix file
main data processing step, including mapping, generate expression matrix and QC matrix which is used in next step
for fastq format :
STAR/bowtie2 mapping
q30 filter,
for sam format:
q30 filter
'''
Log("Step1: alignment", logfile)
t = time.time()
### create mapping dir
mapping_dir = conf_dict['General']['outputdirectory'] + 'mapping/'
CreateDirectory(mapping_dir)
### check reads file format , start mapping step if format is fastq
if conf_dict['General']['format'] == 'sam':
Log('reads file format is sam, skip mapping step', logfile)
conf_dict['General']['sam'] = conf_dict['General']['reads_file']
else:
Log(
'Now start mapping in %s , all mapping result will be here' %
(mapping_dir), logfile)
os.chdir(mapping_dir)
## choose mapping tool from STAR and bowtie2 according to config file
if conf_dict['Step1_Mapping']['mapping_software_main'] == "STAR":
Log('user choose STAR as alignment software', logfile)
if Get('which STAR')[0].strip() == "":
LogError(
'STAR is not detected in default PATH, make sure you installed STAR and export it into default PATH',
logfile)
mapping_cmd = 'STAR --genomeDir %s --readFilesIn %s --runThreadN %s' % (
conf_dict['Step1_Mapping']['mapindex'],
conf_dict['General']['reads_file'],
conf_dict['Step1_Mapping']['mapping_p'])
mapping_cmd2 = 'mv Aligned.out.sam %s.sam' % (
conf_dict['General']['outname'])
LogCommand(mapping_cmd, logfile)
LogCommand(mapping_cmd2, logfile)
elif conf_dict['Step1_Mapping']['mapping_software_main'] == "bowtie2":
Log('user choose bowtie2 as alignment software', logfile)
if Get('which bowtie2')[0].strip() == "":
LogError(
'bowtie2 is not detected in default PATH, make sure you installed bowtie2 and export it into default PATH',
logfile)
mapping_cmd = 'bowtie2 -p %s -x %s -U %s -S %s.sam 2>&1 >>/dev/null |tee -a %s.bowtieout' % (
conf_dict['Step1_Mapping']['mapping_p'],
conf_dict['Step1_Mapping']['mapindex'],
conf_dict['General']['reads_file'],
conf_dict['General']['outname'],
conf_dict['General']['outname'])
LogCommand(mapping_cmd, logfile)
elif conf_dict["Step1_Mapping"]["mapping_software_main"] == "HISAT2":
Log('user choose HISAT2 as alignment software', logfile)
if Get('which hisat2')[0].strip() == "":
LogError(
'hisat2 is not detected in default PATH, make sure you installed hisat2 and export it into default PATH',
logfile)
mapping_cmd = 'hisat2 -p %s -x %s -U %s -S %s.sam 2>&1 >>/dev/null |tee -a %s.hisat2out' % (
conf_dict['Step1_Mapping']['mapping_p'],
conf_dict['Step1_Mapping']['mapindex'],
conf_dict['General']['reads_file'],
conf_dict['General']['outname'],
conf_dict['General']['outname'])
LogCommand(mapping_cmd, logfile)
else:
LogError("alignment tools can only be HISAT2, STAR or bowtie2",
logfile)
conf_dict['General'][
'sam'] = mapping_dir + conf_dict['General']['outname'] + '.sam'
### transform to bed file, awk helps to conduct q30 filtering
Log("transfer sam file to aligned bed file with own script", logfile)
conf_dict['General'][
'bed'] = mapping_dir + conf_dict['General']['outname'] + '.bed'
conf_dict['General']['sampledownsam'] = mapping_dir + conf_dict['General'][
'outname'] + '_sampledown.sam'
conf_dict['General']['sampledownbed'] = mapping_dir + conf_dict['General'][
'outname'] + '_sampledown.bed'
if int(conf_dict['Step1_Mapping']['q30filter']) == 1:
Log("q30 filter is turned on", logfile)
else:
Log("q30 filter is turned off", logfile)
### use own script to transform sam to bed, and random sampling 5M mappable reads
SampleDownTransformSam(conf_dict['General']['sam'],
conf_dict['General']['bed'],
conf_dict['General']['sampledownsam'],
conf_dict['General']['sampledownbed'], 5000000,
int(conf_dict['Step1_Mapping']['q30filter']))
# q30cmd = """samtools view -q 30 -XS %s | awk '{FS="\t";OFS="\t";if (substr($3,1,3) == "chr") {if (substr($2,1,1) == "r") print $3,$4-1,$4-1+length($11),$1,255,"-";else print $3,$4-1,$4-1+length($11),$1,255,"+";}}' > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# q30cmd = """awk '/^[^@]/{FS="\t";OFS="\t";if (substr($3,1,3) == "chr" && $5 > 30) {if ($2 == 16) print $3,$4-1,$4-1+length($11),$1,255,"-";else print $3,$4-1,$4-1+length($11),$1,255,"+";}}' %s > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# q30cmd = """awk '/^[^@]/{FS="\t";OFS="\t";if (substr($3,1,3) == "chr" && $5 > 30) {if ($2 == 16) print $3,$4-1,$4,$1,255,"-";else print $3,$4-1,$4,$1,255,"+";}}' %s > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# LogCommand(q30cmd,logfile,conf_dict['General']['dryrun'])
# q30cmd = """samtools view -XS %s | awk '{FS="\t";OFS="\t";if (substr($3,1,3) == "chr") {if (substr($2,1,1) == "r") print $3,$4-1,$4-1+length($11),$1,255,"-";else print $3,$4-1,$4-1+length($11),$1,255,"+";}}' > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# q30cmd = """awk '/^[^@]/{FS="\t";OFS="\t";if (substr($3,1,3) == "chr") {if ($2 == 16) print $3,$4-1,$4-1+length($11),$1,255,"-";else print $3,$4-1,$4-1+length($11),$1,255,"+";}}' %s > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# q30cmd = """awk '/^[^@]/{FS="\t";OFS="\t";if (substr($3,1,3) == "chr") {if ($2 == 16) print $3,$4-1,$4+length($11),$1,255,"-";else print $3,$4-1,$4,$1,255,"+";}}' %s > %s"""%(conf_dict['General']['sam'],conf_dict['General']['bed'])
# LogCommand(q30cmd,logfile,conf_dict['General']['dryrun'])
if not os.path.isfile(conf_dict['General']['bed']) or os.path.getsize(
conf_dict['General']['bed']) == 0:
LogError(
'Alignment step / q30 filtering step failed, check your alignment parameter and samfile',
logfile)
s1time = time.time() - t
Log("time for alignment: %s" % (s1time), logfile)
Log("Step1: alignment DONE", logfile)
### create annotation dir and generate related annotation file
t = time.time()
Log("Step2: transform expression matrix", logfile)
Log('generate related annotation file with own script', logfile)
annotation_dir = conf_dict['General']['outputdirectory'] + 'annotation/'
CreateDirectory(annotation_dir)
os.chdir(annotation_dir)
GeneAnnotation(conf_dict['General']['gene_annotation'],
conf_dict['Step2_ExpMat']['ttsdistance'],
conf_dict['General']['outname'])
### create expression matrix dir and generate matrix
Log(
'generate expression matrix and individual cell qc matrix with own script',
logfile)
expdir = conf_dict['General']['outputdirectory'] + 'expmatrix/'
CreateDirectory(expdir)
os.chdir(expdir)
### use bedtools(intersect function) to assign exon/intron/intergenic/overlapping gene information to all reads
### sort according to name
Log('add gene annotation on aligned bed file', logfile)
cmd1 = "bedtools intersect -a %s -b %s -wo | sort -k 4,4 --parallel=6 -T . -S 8%% - > %s" % (
conf_dict['General']['bed'], annotation_dir +
conf_dict['General']['outname'] + '_gene_anno_symbol.bed',
conf_dict['General']['outname'] + '_on_symbol.bed')
cmd2 = "bedtools intersect -a %s -b %s -c | sort -k 4,4 --parallel=6 -T . -S 8%% - > %s" % (
conf_dict['General']['bed'], annotation_dir +
conf_dict['General']['outname'] + '_gene_anno_cds.bed',
conf_dict['General']['outname'] + '_on_cds.bed')
cmd3 = "bedtools intersect -a %s -b %s -c | sort -k 4,4 --parallel=6 -T . -S 8%% - > %s" % (
conf_dict['General']['bed'], annotation_dir +
conf_dict['General']['outname'] + '_gene_anno_3utr.bed',
conf_dict['General']['outname'] + '_on_3utr.bed')
cmd4 = "bedtools intersect -a %s -b %s -c | sort -k 4,4 --parallel=6 -T . -S 8%% - > %s" % (
conf_dict['General']['bed'], annotation_dir +
conf_dict['General']['outname'] + '_gene_anno_5utr.bed',
conf_dict['General']['outname'] + '_on_5utr.bed')
cmd5 = "bedtools intersect -a %s -b %s -c | sort -k 4,4 --parallel=6 -T . -S 8%% - > %s" % (
conf_dict['General']['bed'], annotation_dir +
conf_dict['General']['outname'] + '_gene_anno_TTSdis.bed',
conf_dict['General']['outname'] + '_on_TTSdis.bed')
LogCommand(cmd1, logfile)
LogCommand(cmd2, logfile)
LogCommand(cmd3, logfile)
LogCommand(cmd4, logfile)
LogCommand(cmd5, logfile)
### transform barcode fastq to 3column txt file [name,cell_barcode,umi]
if conf_dict['General']['format1'] == 'txt':
Log('barcode files is reformed txt format, skip reform step', logfile)
conf_dict['General']['barcode_reform'] = conf_dict['General'][
'barcode_file']
else:
Log('reform barcode files with own script', logfile)
conf_dict['General']['barcode_reform'] = expdir + conf_dict['General'][
'outname'] + '_barcode_reform.txt'
ReformBarcodeFastq(conf_dict['General']['barcode_file'],
conf_dict['General']['barcode_reform'],
conf_dict['General']['cell_barcode_range'],
conf_dict['General']['umi_range'])
### sort according name
cmdsort = 'sort -k 1,1 --parallel=6 -T . -S 8%% %s > %s' % (
conf_dict['General']['barcode_reform'],
expdir + conf_dict['General']['outname'] + '_barcode_reform_sort.txt')
LogCommand(cmdsort, logfile)
conf_dict['General']['barcode_reform'] = expdir + conf_dict['General'][
'outname'] + '_barcode_reform_sort.txt'
### combine gene annotation, reads, barcode together
Log('combine annotation and barcode on reads with own script', logfile)
CombineReads(conf_dict['General']['barcode_reform'],
conf_dict['General']['outname'] + '_on_cds.bed',
conf_dict['General']['outname'] + '_on_3utr.bed',
conf_dict['General']['outname'] + '_on_5utr.bed',
conf_dict['General']['outname'] + '_on_symbol.bed',
conf_dict['General']['outname'] + '_on_TTSdis.bed',
conf_dict['General']['outname'] + '_combined.bed',
conf_dict['Step2_ExpMat']['duplicate_measure'])
### sort combined file by umi+loci, for following duplicate detection
cmd6 = "sort -k 7,7 -k 5,5 --parallel=6 -T . -S 8%% %s > %s" % (
conf_dict['General']['outname'] + '_combined.bed',
conf_dict['General']['outname'] + '_combined_sort.bed')
LogCommand(cmd6, logfile)
### generate expression and QC matrix based on combined file
Log('generate expression matrix and QC matrix with own script', logfile)
### qcmatfull contains all cell_barcodes, while qcmat,expmat only contain cell_barcodes >= covergncutoff(100, default)
conf_dict['Step2_ExpMat']['qcmatfull'] = expdir + conf_dict['General'][
'outname'] + "_qcmatfull.txt"
conf_dict['Step2_ExpMat'][
'qcmat'] = expdir + conf_dict['General']['outname'] + "_qcmat.txt"
conf_dict['Step2_ExpMat'][
'expmat'] = expdir + conf_dict['General']['outname'] + "_expmat.txt"
GenerateMatrix(conf_dict['General']['gene_annotation'],
conf_dict['General']['outname'] + '_combined_sort.bed',
conf_dict['Step2_ExpMat']['filterttsdistance'],
conf_dict['Step2_ExpMat']['qcmatfull'],
conf_dict['Step2_ExpMat']['qcmat'],
conf_dict['Step2_ExpMat']['expmat'],
conf_dict['Step2_ExpMat']['covergncutoff'],
conf_dict['Step2_ExpMat']['umidis1'])
Log("Step2 transform expression matrix DONE", logfile)
s2time = time.time() - t
Log("time for transform expmat: %s" % (s2time), logfile)
conf_dict['results'] = {}
#conf_dict['results']['expmat'] = conf_dict['Step2_ExpMat']['expmat']
#conf_dict['results']['qcmat'] = conf_dict['Step2_ExpMat']['qcmat']
return conf_dict
def Step0IntegrateData(conf_dict, logfile):
'''
step0 integrate data
check and complement parameter
'''
Log("Start ATAC", logfile)
Log("Step0: Data integrate", logfile)
### check output name
if "/" in conf_dict['General']['outname']:
LogError(
"outname is the name of all your output result, cannot contain " /
", current outname is %s" % (conf_dict['General']['outname']),
logfile)
### check data path , format ,
if "~" in conf_dict['General']['fastq_1']:
LogError(
'require absolute path for fastq_1 file, cannot contain "~", current fastq_1 file is %s'
% (conf_dict['General']['fastq_1']), logfile)
if "~" in conf_dict['General']['fastq_2']:
LogError(
'require absolute path for fastq_2 file, cannot contain "~", current fastq_2 file is %s'
% (conf_dict['General']['fastq_2']), logfile)
if "~" in conf_dict['General']['barcode_file']:
LogError(
'require absolute path for barcode file, cannot contain "~", current barcode file is %s'
% (conf_dict['General']['barcode']), logfile)
if not conf_dict['General']['fastq_1'].startswith('/'):
conf_dict['General']['fastq_1'] = conf_dict['General'][
'startdir'] + conf_dict['General']['fastq_1']
if not conf_dict['General']['fastq_2'].startswith('/'):
conf_dict['General']['fastq_2'] = conf_dict['General'][
'startdir'] + conf_dict['General']['fastq_2']
if not conf_dict['General']['barcode_file'].startswith('/'):
conf_dict['General']['barcode_file'] = conf_dict['General'][
'startdir'] + conf_dict['General']['barcode_file']
if not os.path.isfile(conf_dict['General']['fastq_1']):
LogError(
"fastq_1 file %s not found" % (conf_dict['General']['fastq_1']),
logfile)
if not os.path.isfile(conf_dict['General']['fastq_2']):
LogError(
"fastq_2 file %s not found" % (conf_dict['General']['fastq_2']),
logfile)
if not os.path.isfile(conf_dict['General']['barcode_file']):
LogError(
"barcode_file file %s not found" %
(conf_dict['General']['barcode_file']), logfile)
if not (conf_dict['General']['fastq_1'].endswith('.fastq')
and conf_dict['General']['fastq_2'].endswith('.fastq')):
LogError("input files should be fastq files.", logfile)
else:
Log('Detected input file format is fastq', logfile)
conf_dict['General']['format'] = 'fastq'
### check gene annotation file
if conf_dict['General']['gene_annotation'] == "":
LogError("gene annotation file cannot be empty", logfile)
if not "/" in conf_dict['General']['gene_annotation']:
LogError("absolute path for gene annotation file required", logfile)
if not os.path.isfile(conf_dict['General']['gene_annotation']):
LogError(
"cannot find gene annotation file : %s" %
(conf_dict['General']['gene_annotation']), logfile)
### mapping index
if conf_dict['General']['format'] == 'fastq':
if conf_dict['Step1_Mapping']['mapping_software'] == "bowtie2":
Log('use bowtie2 as alignment tools', logfile)
# conf_dict['Step1_Mapping']['mapindex'] = indexdir + conf_dict['General']['genome_version']
indexfile1 = conf_dict['Step1_Mapping']['mapindex'] + '.1.bt2'
if not os.path.isfile(indexfile1):
LogError("cannot find bowtie2 index file : %s " % (indexfile1),
logfile)
else:
LogError("alignment tools can only be bowtie2 by now", logfile)
### check options
Log('option setting: ', logfile)
try:
Log(
'mapping thread is %s' %
(str(int(conf_dict['Step1_Mapping']['p']))), logfile)
except:
LogError(
'p should be int, current value is %s' %
(conf_dict['Step1_Mapping']['p']), logfile)
if not int(conf_dict['Step1_Mapping']['q30filter']) in [0, 1]:
LogError(
'q30filter measurement can only be 0/1, current value is %s' %
(conf_dict['Step1_Mapping']['q30filter']), logfile)
if not int(conf_dict['Step1_Mapping']['filter_reads_length']) in [0, 1]:
LogError(
'filter_reads_length measurement can only be 0/1, current value is %s'
% (conf_dict['Step1_Mapping']['filter_reads_length']), logfile)
### check Rscript
if not 'Usage' in GetError('Rscript')[1] and not 'version' in GetError(
'Rscript')[1]:
LogError('require Rscript', logfile)
### check pdflatex
if Get('pdflatex --help')[0] == "":
Log(
'pdflatex was not installed, ATAC is still processing but no summary QC report generated',
logfile)
conf_dict['General']['latex'] = 0
else:
conf_dict['General']['latex'] = 1
Log('Step0 Data integrate DONE', logfile)
return conf_dict