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

Checkpointing some bugfixes with zero-length version directories and missing 

Picard metrics files before the push back into svn.

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@6069 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
droazen 2011-06-22 22:56:01 +00:00
parent 171e20a111
commit d92055d1f9
3 changed files with 11 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
R/exomePreQC.R
View File

@ -3,8 +3,8 @@ onCMDLine = ! is.na(args[1])
if ( onCMDLine ) {
reference_dataset = '/Users/mhanna/metrics.perSample.formatted.table'
inputTSV = args[2]
outputPDF = args[3]
inputTSV = args[1]
outputPDF = args[2]
} else {
reference_dataset = '/Users/mhanna/metrics.perSample.formatted.table'
inputTSV = 'GoT2D_exomes_batch_005.tsv'
@ -13,7 +13,6 @@ if ( onCMDLine ) {
require('ggplot2')
inputTSV = "GoT2D_exomes_batch_005.tsv"
data <- read.table(inputTSV,header=T)
complete <- read.table(reference_dataset,header=T)

14
python/generate_per_sample_metrics.py
View File

@ -90,19 +90,17 @@ for sample_id,filename in samples.items():
if fingerprinting_summary_metrics != None:
haplotypes_confidently_matching = [str(metric.HAPLOTYPES_CONFIDENTLY_MATCHING) for metric in fingerprinting_summary_metrics]
fingerprint_lods = [str(metric.LOD_EXPECTED_SAMPLE) for metric in fingerprinting_summary_metrics]
# min_haplotypes_confidently_matching = str(min(haplotypes_confidently_matching))
# max_haplotypes_confidently_matching = str(max(haplotypes_confidently_matching))
# median_haplotypes_confidently_matching = str(median(haplotypes_confidently_matching))
else:
haplotypes_confidently_matching = []
fingerprint_lods = []
# min_haplotypes_confidently_matching = 'NA'
# max_haplotypes_confidently_matching = 'NA'
# median_haplotypes_confidently_matching = 'NA'
data = [sample_id,'c('+string.join(fingerprint_lods,',')+')','c('+string.join(haplotypes_confidently_matching,',')+')']
for metrics_type,metrics_extension in sample_summary_metrics_types:
metrics = get_sample_summary_metrics('%s.%s' % (basepath,metrics_extension))
data.extend([getattr(metrics, metrics_field_name) for metrics_field_name in get_sample_summary_metrics_fields(metrics_type)])
metrics_pathname = '%s.%s' % (basepath,metrics_extension)
if os.path.exists(metrics_pathname):
metrics = get_sample_summary_metrics(metrics_pathname)
data.extend([getattr(metrics, metrics_field_name) for metrics_field_name in get_sample_summary_metrics_fields(metrics_type)])
else:
data.extend(['NA' for metrics_field_name in get_sample_summary_metrics_fields(metrics_type)])
print string.join(['%s']*len(header),'\t')%tuple(data)

4
python/parse_pm_input.py
View File

@ -50,7 +50,7 @@ def create_reader(filename):
extension = os.path.splitext(filename)[1]
if extension == '.xls' or extension == '.xlsx':
return excel_reader(filename)
elif extensions == '.tsv' or extension == '.txt':
elif extension == '.tsv' or extension == '.txt':
return tsv_reader(filename)
else:
print 'Unrecognized file extension',extension
@ -73,6 +73,8 @@ for project,sample in create_reader(input_filename):
print 'Hit a path name that cannot be parsed: ',version_path
sys.exit(1)
versions.append(int(version_path[1:]))
if len(versions) == 0:
continue
versions = sorted(versions)
bam_file = '%s/v%d/%s.bam' % (sample_path,versions[-1],sample)
if not os.path.exists(bam_file):