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

This script produces information for a firehose job-finished email 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@3804 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
corin 2010-07-16 14:44:52 +00:00
parent ec94cfdf05
commit 917469ef43
1 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
python/firehose_out_email.py 100755
View File

@ -0,0 +1,35 @@
#this script produces the output to go in emails
import os
import re
import sample_lister
class SampSet(sample_lister.SampleSet)
def __init__(self, sampset, pathname):
self.sampset=sampset
self.pathname=pathname
sample_lister.SampleSet.__init__(self, sampset, pathname)
def evalout(self):
'''This produced the output that needs to go in the emails'''
filename = "/humgen/gsa-firehose/firehose/firehose_output/trunk/Sample_Set/" + self.sampset +"/UnifiedGenotyper/"+ self.sampset+".filtered.eval"
evalfile = open(filename, "r").read()
annotations= ["all", "novel", "known", "snp_at_known_non_snps", "filtered"]
variant=dict(zip(annotations, ('','','','','')))
ratio=dict(zip(annotations, ('','','','','')))
bpre=re.compile("all,summary,variant_counts +n bases covered +(\d+)")
size=repr(bpre.search(evalfile).group(1))
for a in annotations:
anregexv = re.compile(a + ",summary,variant_counts +variants +(\d+)")
variant[a] = repr(anregexv.search(evalfile).group(1))
anregexr = re.compile(a + ",summary,transitions_transversions +ratio +(\d+.\d+)")
print (anregexr.search(evalfile))
ratio[a] = repr(anregexr.search(evalfile).group(1))
print (a)
print (ratio[a])
print("Samples processed:\n\n Target size: \t" +size+" bp \n\n\t\t\t\t\t Variants \t\t Ti/TV \n (true positives)\t All \t\t " +variant["all"]+ " \t\t " + ratio["all"] +" \n \t\t\t Known \t\t " +variant["known"]+ " \t\t " + ratio['known']+" \n \t\t\t Novel \t\t " +variant["novel"]+" \t\t " + ratio['novel']+ " \n*************************************************************************\n (false \tSNPS at known indels \t " +variant["snp_at_known_non_snps"]+"\t\t\t " + ratio['snp_at_known_non_snps']+ " \n positives) \t\t filtered \t " +variant["filtered"]+" \t\t " + ratio['filtered'] )
#EOMI=SampSet("EOMI_Kathiresan_NHGRI", "test")
#EOMI.evalout() <-this and the line above are examples
#TODO: make this send the email when run
#TODO: make this find the list of bams, bed files, and annotated vcfs.