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

Now accepts command line args and prints paths to vcf, bams and beds 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@3846 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
corin 2010-07-21 15:04:58 +00:00
parent f7957bc7f2
commit 1209b165bf
1 changed files with 40 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
python/firehose_out_email.py
View File

@ -1,13 +1,33 @@
#this script produces the output to go in emails #this script produces the output to go in emails
import subprocess
import os import os
import re import re
import sys
import getopt
import sample_lister import sample_lister
try:
opts, args = getopt.getopt(sys.argv[1:], "dp:s:")
except getopt.GetoptError, err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
opts=dict(opts)
givenname=opts['-s']
projname=opts['-p']
if '-d' in opts:
dirname=opts['-d']
else:
dirname=""
class SampSet(sample_lister.SampleSet): class SampSet(sample_lister.SampleSet):
def __init__(self, sampset, pathname): def __init__(self, projectname, sampset, pathname):
self.sampset=sampset self.sampset=sampset
self.pathname=pathname self.pathname=pathname
sample_lister.SampleSet.__init__(self, sampset, pathname) self.projectname=projectname
sample_lister.SampleSet.__init__(self, projectname, sampset, pathname)
def evalout(self): def evalout(self):
'''This produced the output that needs to go in the emails''' '''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" filename = "/humgen/gsa-firehose/firehose/firehose_output/trunk/Sample_Set/" + self.sampset +"/UnifiedGenotyper/"+ self.sampset+".filtered.eval"
@ -17,16 +37,27 @@ class SampSet(sample_lister.SampleSet):
ratio=dict(zip(annotations, ('','','','',''))) ratio=dict(zip(annotations, ('','','','','')))
bpre=re.compile("all,summary,variant_counts +n bases covered +(\d+)") bpre=re.compile("all,summary,variant_counts +n bases covered +(\d+)")
size=repr(bpre.search(evalfile).group(1)) size=repr(bpre.search(evalfile).group(1))
bamsearch="find /humgen/gsa-firehose/firehose/firehose_output/trunk/Sample_Set/"+self.sampset+"/* -name \*.bam"
bams = subprocess.Popen([bamsearch], shell=True, stdout=subprocess.PIPE).communicate()[0]
sampno=bams.count("bam")
bedsearch="find /humgen/gsa-firehose/firehose/firehose_output/trunk/Sample_Set/"+self.sampset+"/* -name \*filtered_indels.bed"
beds = subprocess.Popen([bedsearch], shell=True, stdout=subprocess.PIPE).communicate()[0]
vcf="/humgen/gsa-firehose/firehose/firehose_output/trunk/Sample_Set/"+self.sampset+"/UnifiedGenotyper/"+self.sampset+'.maf.annotated.vcf'
for a in annotations: for a in annotations:
anregexv = re.compile(a + ",summary,variant_counts +variants +(\d+)") anregexv = re.compile(a + ",summary,variant_counts +variants +(\d+)")
variant[a] = repr(anregexv.search(evalfile).group(1)) variant[a] = repr(anregexv.search(evalfile).group(1))
anregexr = re.compile(a + ",summary,transitions_transversions +ratio +(\d+.\d+)") anregexr = re.compile(a + ",summary,transitions_transversions +ratio +(\d+.\d+)")
ratio[a] = repr(anregexr.search(evalfile).group(1) ratio[a] = repr(anregexr.search(evalfile).group(1))
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'] ) out1="Samples processed:"+repr(sampno)+"\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']
out2="\n\n\nSNP calls:"+vcf+"\n\nIndel-realigned Bam files:\n"+bams+"\nIndel calls:\n"+beds
if self.pathname == '':
print(out1+out2)
else:
filename=self.pathname+self.sampset+".emailtxt"
putthere=open(filename, "w")
putthere.write(out1+out2)
target=SampSet(projname,givenname,dirname)
#EOMI=SampSet("EOMI_Kathiresan_NHGRI", "test") target.evalout()
#EOMI.evalout() <-this and the line above are examples #TODO: make this send the email when run
#TODO: make this send the email when run with a setname as input
#TODO: make this find the list of bams, bed files, and annotated vcfs. #TODO: make this find the list of bams, bed files, and annotated vcfs.