zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated input to accept BAM list, and output to emit proper sample name. 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@5991 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
hanna 2011-06-14 00:15:01 +00:00
parent 1b1aefc385
commit 1fec811a47
1 changed files with 14 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
python/generate_per_sample_metrics.py
View File

@ -1,8 +1,6 @@
from java.lang import * from java.lang import *
from java.io import File,FileReader from java.io import File,FileReader
from net.sf.picard.metrics import MetricsFile from net.sf.picard.metrics import MetricsFile
from org.broadinstitute.sting.datasources.pipeline import Pipeline
from org.broadinstitute.sting.utils.yaml import YamlUtils
import os,string,sys import os,string,sys
@ -25,13 +23,12 @@ if len(sys.argv) != 2:
print 'USAGE: %s <pipeline_file.yaml>' print 'USAGE: %s <pipeline_file.yaml>'
sys.exit(1) sys.exit(1)
if not os.path.exists(sys.argv[1]): if not os.path.exists(sys.argv[1]):
print 'Pipeline file %s not found' % sys.argv[1] print 'BAM list %s not found' % sys.argv[1]
sys.exit(1) sys.exit(1)
pipeline_file = sys.argv[1] bam_list_filename = sys.argv[1]
pipeline = YamlUtils.load(Pipeline,File(pipeline_file))
header = ['SAMPLE','HAPLOTYPES_CONFIDENTLY_MATCHING.MIN','HAPLOTYPES_CONFIDENTLY_MATCHING.MAX','HAPLOTYPES_CONFIDENTLY_MATCHING.MEDIAN', header = ['sample','HAPLOTYPES_CONFIDENTLY_MATCHING.MIN','HAPLOTYPES_CONFIDENTLY_MATCHING.MAX','HAPLOTYPES_CONFIDENTLY_MATCHING.MEDIAN',
'BAIT_SET','GENOME_SIZE','PCT_SELECTED_BASES','MEAN_TARGET_COVERAGE','ZERO_CVG_TARGETS_PCT','FOLD_80_BASE_PENALTY','HS_LIBRARY_SIZE', 'BAIT_SET','GENOME_SIZE','PCT_SELECTED_BASES','MEAN_TARGET_COVERAGE','ZERO_CVG_TARGETS_PCT','FOLD_80_BASE_PENALTY','HS_LIBRARY_SIZE',
'PCT_PF_READS_ALIGNED','PF_HQ_ERROR_RATE','MEAN_READ_LENGTH','BAD_CYCLES','STRAND_BALANCE','PCT_CHIMERAS','PCT_ADAPTER','MEDIAN_INSERT_SIZE', 'PCT_PF_READS_ALIGNED','PF_HQ_ERROR_RATE','MEAN_READ_LENGTH','BAD_CYCLES','STRAND_BALANCE','PCT_CHIMERAS','PCT_ADAPTER','MEDIAN_INSERT_SIZE',
'TOTAL_SNPS'] 'TOTAL_SNPS']
@ -40,13 +37,20 @@ data = ['%s'] * len(header)
print string.join(header,'\t') print string.join(header,'\t')
# get a representative BAM file for each sample, to use as a base path. Note that this assumes every sample corresponds to the same base path. # get a representative BAM file for each sample, to use as a base path. Note that this assumes every sample corresponds to the same base path.
bam_list = open(bam_list_filename,'r')
samples = dict() samples = dict()
for sample in pipeline.getSamples():
if sample.getBamFiles().size() > 0: for bam_filename in bam_list:
samples[sample.getId()] = sample.getBamFiles().values().iterator().next() bam_filename = bam_filename.strip()
if bam_filename == '':
continue
bam_filename_tokens = bam_filename.split('/')
sample_id = bam_filename_tokens[len(bam_filename_tokens)-3]
samples[sample_id] = bam_filename
bam_list.close()
for sample_id,filename in samples.items(): for sample_id,filename in samples.items():
basepath = filename.getAbsolutePath()[0:filename.getAbsolutePath().rindex('.bam')] basepath = filename[:filename.rindex('.bam')]
fingerprinting_summary_metrics = get_metrics('%s.%s' % (basepath,'fingerprinting_summary_metrics')) fingerprinting_summary_metrics = get_metrics('%s.%s' % (basepath,'fingerprinting_summary_metrics'))