-T IndelRealigner\
-R %s \
-targetIntervals %s.intervals \
-I %s \
-D %s \
-U \
-o %s" % (gatkbase,
gatkref,
args.infilename.replace(args.insuffix,''),
args.infilename.replace(args.insuffix,'.dupsmarked.bam'),
gatkdbsnp,
args.infilename.replace(args.insuffix,'.processed.bam')
)],shell=True)
subparser=subparsers.add_parser(
"exomePostProcess",
help="Postprocess a single lane of exome data, including duplicate marking and quality recalibration. No indel realignment is done as BAQ is expected downstream")
subparser.add_argument(
"infilename",
help="The input filename")
subparser.add_argument(
"-o","--out-suffix",dest="outsuffix",default=".processed.bam",
help="The output suffix name, to be appended after stripping in-suffix from the input filename [default: .processed.bam]")
subparser.add_argument(
"-i","--in-suffix",dest='insuffix',default=".bam",
help="The input file suffix, to be stripped before appending the outsuffix, [default: .bam]")
subparser.add_argument(
"-j","--javaDir",dest="javadir",default="/data/sedavis/usr/local/jars/",
help="base directory for java jar files")
subparser.add_argument(
"-c","--configfile",dest="configfile",default="ngs.conf",
print(
"java -jar /data/sedavis/usr/local/jars/picard/MergeSamFiles.jar ASSUME_SORTED=true OUTPUT=%s %s"
% (
"'" + k + ".bam'",
" ".join(["INPUT='" + x["Lane"] + "_" + x["Flowcell"] + args.suffix + "'" for x in v]),
)
)
else:
print(
"ln -s %s %s"
% (" ".join(["'" + x["Lane"] + "_" + x["Flowcell"] + args.suffix + "'" for x in v]), "'" + k + ".bam'")
)
subparser = subparsers.add_parser(
"makeMergeCmd", help="Use this to merge lanes of data into a single file, based on source_name in samplesheet"
)
subparser.add_argument("samplesheet", help="The samplesheet for the project")
subparser.add_argument(
"-s",
"--suffix",
dest="suffix",
default=".bam",
help="Suffix to append to the standard lane_flowcell nomenclature for the input bam files (eg., 'recal.sorted.bam' or '.bam')",
)
subparser.add_argument(
"-t",
"--sampleType",
dest="sampletype",
help="Limit the type of sample to deal with (Genomic DNA, mRNA, etc.) from the 'sample_type' column in the samplesheet",
)
row[read]=row[read].replace('_1,2_','_2_')
fnameremote=row[read]
if(fnameremote=="None"):
logger.info('Empty sequence file %s found for row:\n%s' % (read,row))
if(args.altsuffix):
fnameremote=fnameremote.replace('.tgz',args.altsuffix)
fnamelocal=fnameremote # default same name
if((int(row['index_read'])>0) & (read=='r2sequence')):
logger.info("Found a lane with indexing, so transferring the third read and renaming to read 2")
fnameremote=fnameremote.replace('_2_','_3_')
_doRsync(args.fromloc,args.toloc,fnameremote,fnamelocal)
subparser = subparsers.add_parser(
'getsequence',
help="Given a sample sheet in standard form, rsync the files from one location to another")
subparser.add_argument(
"-f","--from-location",required=True,dest='fromloc',
help="A uri (without filename) as recognized by rsync, such as [email protected]:/path/to/sequencefiles")
subparser.add_argument(
"-t","--to-location",dest="toloc",default='.',
help="A uri (without filename) as recognized by rsync, such as [email protected]:/path/to/sequencefiles or '.' [default '.']")
subparser.add_argument(
"-a","--alternative-suffix",dest="altsuffix",default='.',
help="The sequence files have a suffix '.tgz' that could be replaced with another suffix, for example '.fq.gz' to get the fastq files. Specify the alternate suffix here.")
subparser.add_argument(
"samplesheet",
help="The name of the samplesheet file from which to pull the sequence names")
subparser.set_defaults(func=func)
r2 = row['r2sequence'].replace('.tgz','.fq.gz')
r2 = r2.replace('_1,2_','_2_')
if(r2=='None'):
print("ngtools doAlign -1 %s --rg_id '%s' --rg_lb '%s' --rg_sm '%s' %d %s %s %s" %
(r1,row['Lane']+"_"+row['Flowcell'],
row['library_name'],row['source_name'],
8,'/data/sedavis/public/novoalign/hg18.index',
'/data/sedavis/public/sequence/ucsc/hg18/genome.fa.fai',
row['Lane']+"_"+row['Flowcell']))
else:
print("ngtools doAlign -1 %s -2 %s --rg_id '%s' --rg_lb '%s' --rg_sm '%s' %d %s %s %s" %
(r1,r2,row['Lane']+"_"+row['Flowcell'],
row['library_name'],row['source_name'],
8,'/data/sedavis/public/novoalign/hg18.index',
'/data/sedavis/public/sequence/ucsc/hg18/genome.fa.fai',
row['Lane']+"_"+row['Flowcell']))
subparser=subparsers.add_parser(
"makeAlignCmd",
help="generate a .cmd file for swarm submission. Output is simply to stdout.")
subparser.add_argument(
"samplesheet")
subparser.add_argument(
'faifile')
subparser.add_argument(
'novoindex')
subparser.set_defaults(func=func)
from ngs.main import subparsers
import ngs.solexadb.model
def func(args):
sdb = ngs.solexadb.model.SolexaDB(args.uri)
res = sdb.getSampleSheetByStudyID(args.study_id)
print "\t".join([str(x) for x in res['keys']])
for row in res['rows']:
print "\t".join([str(x) for x in row])
subparser = subparsers.add_parser(
'makeSampleSheet',
help="Generate a standard sample sheet for a given study id")
subparser.add_argument(
"-u","--uri",dest='uri',
help="Database uri, like 'mysql://*****:*****@localhost/solexa'")
subparser.add_argument(
"-s","--study-id",dest='study_id',type=int,
help="Study ID from the solexa database")
subparser.set_defaults(func=func)
if(args.rg_id is not None):
samtag+="\tID:%s" % (args.rg_id)
if(args.rg_sm is not None):
samtag+="\tSM:%s" % (args.rg_id)
if(args.rg_lb is not None):
samtag+="\tLB:%s" % (args.rg_id)
if(args.read2 is None):
x=subprocess.call(["novoalign -k -a -H -o SAM '%s' -c %d -d %s -f %s | samtools import %s - - | samtools sort - %s" % (samtag,args.nproc, args.novoidx, args.read1, args.faifile, args.prefix + ".tmp")],shell=True)
# paired end
else:
x=subprocess.call(["novoalign -k -a -H -o SAM '%s' -c %d -d %s -f %s %s | samtools import %s - - | samtools sort - %s" % (samtag,args.nproc, args.novoidx, args.read1, args.read2, args.faifile, args.prefix + ".tmp")],shell=True)
if(x==0):
os.rename(args.prefix+".tmp"+".bam",args.prefix+".bam")
subparser = subparsers.add_parser(
'doAlign',
help="do the alignment given a set of inputs")
subparser.add_argument(
"nproc",type=int,default=1,
help="The number of cores to use")
subparser.add_argument(
"novoidx",
help="The novoalign index to use")
subparser.add_argument(
"faifile",
help="The .fai file to use")
subparser.add_argument(
'-1',"--read1",
help="read1 filename")
subparser.add_argument(
'-2',"--read2",
