def call_after_mapping(working_dir, prefix, bam_or_fastq, sample_dict,
ped_type):
os.chdir(working_dir)
print 'hello'
##variant calling
make_list_of_bams(sample_dict, final_bam_suffix, bamlist)
variant_calling_freebayes(bamlist, prefix)
variant_calling_gatk_hc_no_gvcf(bamlist, prefix)
intesect_two_vcf_files(prefix + '.gatkHC.vcf.gz',
prefix + '.freebayes.vcf.gz',
prefix + '.intersected_vcfs')
##coverage
calculate_exome_coverage(sample_dict, final_bam_suffix,
exome_bed_for_coverage, prefix)
##plink for sex and relatedness -- work in progress
plink_relatadness_check(prefix + '.intersected_vcfs/0002.vcf', prefix)
##delete unwanted files
delete_unwated_files([
'*.r1.fastq', '*.r2.fastq', '*.bwa.bam', '*.bwa_sort.bam', '*.metrics',
'*.bwa_religned.bam', '*.bwa_religned.bai', '*.recal_data.table',
'*temp*', '*bwa_mkdup.bai', '*bwa_mkdup.bam'
])
##run gemini
dobyns_gemini_pipeline_cybertron_v8.standard_gemini_protocol(
working_dir, prefix, ped_type)
def call_all_exome_methods_inc_gemini(working_dir, prefix, bam_or_fastq,
sample_dict, ped_type):
os.chdir(working_dir)
##covert bam to fastq and then process
# '''
if bam_or_fastq == 'bam':
for sample in sample_dict:
read1_fastq = sample + '.r1.fastq'
read2_fastq = sample + '.r2.fastq'
# convert_bam_fastq_bedtools(sample_dict[sample], read1_fastq, read2_fastq)
convert_bam_fastq_picard(sample_dict[sample], read1_fastq,
read2_fastq)
align_with_bwa_one_at_time(sample, read1_fastq, read2_fastq)
elif bam_or_fastq == 'messy_bam':
for sample in sample_dict:
read1_fastq = sample + '.r1.fastq'
read2_fastq = sample + '.r2.fastq'
convert_bam_fastq_bedtools(sample_dict[sample], read1_fastq,
read2_fastq)
align_with_bwa_one_at_time(sample, read1_fastq, read2_fastq)
elif bam_or_fastq == 'fastq':
for sample in sample_dict:
read1_fastq = sample_dict[sample][0]
read2_fastq = sample_dict[sample][1]
align_with_bwa_one_at_time(sample, read1_fastq, read2_fastq)
##single fq
# align_with_bwa_one_at_time_single_end(sample,sample_dict[sample])
else:
print 'must specify if starting with fastq or bam file'
# '''
##variant calling
make_list_of_bams(sample_dict, final_bam_suffix, bamlist)
variant_calling_freebayes(bamlist, prefix)
variant_calling_gatk_hc_no_gvcf(bamlist, prefix)
intesect_two_vcf_files(prefix + '.gatkHC.vcf.gz',
prefix + '.freebayes.vcf.gz',
prefix + '.intersected_vcfs')
##coverage
calculate_exome_coverage(sample_dict, final_bam_suffix,
exome_bed_for_coverage, prefix)
##plink for sex and relatedness -- work in progress
plink_relatadness_check(prefix + '.intersected_vcfs/0002.vcf', prefix)
##delete unwanted files
delete_unwated_files([
'*.r1.fastq', '*.r2.fastq', '*.bwa.bam', '*.bwa_sort.bam', '*.metrics',
'*.bwa_religned.bam', '*.bwa_religned.bai', '*.recal_data.table',
'*temp*', '*bwa_mkdup.bai', '*bwa_mkdup.bam'
])
##run gemini
dobyns_gemini_pipeline_cybertron_v8.standard_gemini_protocol(
working_dir, prefix, ped_type)
def intersect_vcfs_and_gemini(working_dir, prefix, bam_or_fastq, sample_dict,
ped_type):
os.chdir(working_dir)
intesect_two_vcf_files(prefix + '.gatkHC.vcf.gz',
prefix + '.freebayes.vcf.gz',
prefix + '.intersected_vcfs')
##coverage
# calculate_exome_coverage(sample_dict, final_bam_suffix, exome_bed_for_coverage, prefix)
##plink for sex and relatedness -- work in progress
plink_relatadness_check(prefix + '.intersected_vcfs/0002.vcf', prefix)
##delete unwanted files
# delete_unwated_files(['*.r1.fastq', '*.r2.fastq', '*.bwa.bam', '*.bwa_sort.bam', '*.metrics', '*.bwa_religned.bam', '*.bwa_religned.bai', '*.recal_data.table', '*temp*', '*bwa_mkdup.bai', '*bwa_mkdup.bam'])
##run gemini
dobyns_gemini_pipeline_cybertron_v8.standard_gemini_protocol(
working_dir, prefix, ped_type)
def call_just_gemini(working_dir, prefix, bam_or_fastq, sample_dict, ped_type):
os.chdir(working_dir)
print 'hello'
##run gemini
dobyns_gemini_pipeline_cybertron_v8.standard_gemini_protocol(
working_dir, prefix, ped_type)