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

Add a column summing the fingerprint LOD scores. 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@6041 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
droazen 2011-06-22 22:54:09 +00:00
parent 4f7a64a798
commit e0d203434f
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
python/generate_per_sample_metrics.py
View File

@ -64,7 +64,7 @@ sample_summary_metrics_types = [ (HsMetrics,'hybrid_selection_metrics'),
(InsertSizeMetrics, 'insert_size_metrics'), (InsertSizeMetrics, 'insert_size_metrics'),
(DbSnpMatchMetrics, 'dbsnp_matches') ] (DbSnpMatchMetrics, 'dbsnp_matches') ]
header = ['sample','HAPLOTYPES_CONFIDENTLY_MATCHING.MIN','HAPLOTYPES_CONFIDENTLY_MATCHING.MAX','HAPLOTYPES_CONFIDENTLY_MATCHING.MEDIAN'] header = ['sample','SUM_OF_FINGERPRINT_LODS','HAPLOTYPES_CONFIDENTLY_MATCHING.MIN','HAPLOTYPES_CONFIDENTLY_MATCHING.MAX','HAPLOTYPES_CONFIDENTLY_MATCHING.MEDIAN']
for metric_type in sample_summary_metrics_types: for metric_type in sample_summary_metrics_types:
header.extend(get_sample_summary_metrics_fields(metric_type[0])) header.extend(get_sample_summary_metrics_fields(metric_type[0]))
print string.join(header,'\t') print string.join(header,'\t')
@ -89,15 +89,17 @@ for sample_id,filename in samples.items():
if fingerprinting_summary_metrics != None: if fingerprinting_summary_metrics != None:
haplotypes_confidently_matching = [metric.HAPLOTYPES_CONFIDENTLY_MATCHING for metric in fingerprinting_summary_metrics] haplotypes_confidently_matching = [metric.HAPLOTYPES_CONFIDENTLY_MATCHING for metric in fingerprinting_summary_metrics]
sum_of_fingerprint_lods = str(sum([metric.LOD_EXPECTED_SAMPLE for metric in fingerprinting_summary_metrics]))
min_haplotypes_confidently_matching = str(min(haplotypes_confidently_matching)) min_haplotypes_confidently_matching = str(min(haplotypes_confidently_matching))
max_haplotypes_confidently_matching = str(max(haplotypes_confidently_matching)) max_haplotypes_confidently_matching = str(max(haplotypes_confidently_matching))
median_haplotypes_confidently_matching = str(median(haplotypes_confidently_matching)) median_haplotypes_confidently_matching = str(median(haplotypes_confidently_matching))
else: else:
sum_of_fingerprint_lods = 'NA'
min_haplotypes_confidently_matching = 'NA' min_haplotypes_confidently_matching = 'NA'
max_haplotypes_confidently_matching = 'NA' max_haplotypes_confidently_matching = 'NA'
median_haplotypes_confidently_matching = 'NA' median_haplotypes_confidently_matching = 'NA'
data = [sample_id,min_haplotypes_confidently_matching,max_haplotypes_confidently_matching,median_haplotypes_confidently_matching] data = [sample_id,sum_of_fingerprint_lods,min_haplotypes_confidently_matching,max_haplotypes_confidently_matching,median_haplotypes_confidently_matching]
for metrics_type,metrics_extension in sample_summary_metrics_types: for metrics_type,metrics_extension in sample_summary_metrics_types:
metrics = get_sample_summary_metrics('%s.%s' % (basepath,metrics_extension)) metrics = get_sample_summary_metrics('%s.%s' % (basepath,metrics_extension))