def gdv_create(self,ex):
from bbcflib import gdv
project = gdv.get_project(mail=self.globals['gdv']['email'],
key=self.globals['gdv']['key'],
project_key=self.job.options['gdv_key'])
if 'error' in project:
self.log_write("Creating GDV project.")
project = gdv.new_project( self.globals['gdv']['email'],
self.globals['gdv']['key'],
self.job.description,
self.job.assembly.id,
self.globals['gdv']['url'] )
self.debug_write("\nGDV project: "+json.dumps(project))
add_pickle( ex, project, description=set_file_descr("gdv_json",step='gdv',type='py',view='admin') )
self.job.options['gdv_project'] = project
return True
def demultiplex_workflow(ex, job, gl, file_path="../", via='lsf',
logfile=sys.stdout, debugfile=sys.stderr):
script_path=gl['script_path']
file_names = {}
job_groups=job.groups
resFiles={}
for gid, group in job_groups.iteritems():
file_names[gid] = {}
primersFilename = 'group_' + group['name'] + "_barcode_file.fa"
primersFile = os.path.join(file_path,primersFilename)
ex.add(primersFile,description=set_file_descr(primersFilename,groupId=gid,step="init",type="fa"))
paramsFilename = 'group_' + group['name'] + "_param_file.txt"
paramsFile = os.path.join(file_path,paramsFilename)
ex.add(paramsFile,description=set_file_descr(paramsFilename,groupId=gid,step="init",type="txt"))
params = load_paramsFile(paramsFile)
infiles = []
tot_counts = 0
allSubFiles = []
for rid,run in group['runs'].iteritems():
infiles.append(run)
n=count_lines(ex,run)
tot_counts += n/4
if n>10000000:
allSubFiles.extend(split_file(ex,run,n_lines=8000000))
else:
allSubFiles.append(run)
(resExonerate, tot_ambiguous, tot_discarded) = parallel_exonerate( ex, allSubFiles, primersFile,
(gid, group['name']), via=via, **params )
gzipfile(ex,run)
ex.add(run+".gz",description=set_file_descr(group['name']+"_full_fastq.gz",
groupId=gid,step='exonerate',view='debug',type="fastq"))
logfile.write("Will get sequences to filter\n");logfile.flush()
seqToFilter = getSeqToFilter(ex,primersFile)
logfile.write("Will filter the sequences\n")
filteredFastq = filterSeq(ex,resExonerate,seqToFilter,gid,group['name'],via=via)
logfile.write("After filterSeq, filteredFastq=%s\n" %filteredFastq);logfile.flush()
counts_primers = {}
counts_primers_filtered = {}
if len(filteredFastq):
archive = unique_filename_in()
tgz = tarfile.open(archive, "w:gz")
for k,f in resExonerate.iteritems():
counts_primers[k] = count_lines(ex,f)/4
if k in filteredFastq:
file_names[gid][k] = group['name']+"_"+k+"_filtered"
ex.add(filteredFastq[k],description=set_file_descr(file_names[gid][k]+".fastq",
groupId=gid,step="final",
type="fastq"))
counts_primers_filtered[k] = count_lines(ex,filteredFastq[k])/4
tgz.add( f, arcname=group['name']+"_"+k+".fastq" )
else:
file_names[gid][k] = group['name']+"_"+k
ex.add(f,description=set_file_descr(file_names[gid][k]+".fastq",
groupId=gid,step="final",
type="fastq"))
counts_primers_filtered[k] = 0
if len(filteredFastq):
tgz.close()
ex.add(archive,description=set_file_descr(group['name']+"_unfiltered_fastq.tgz",
groupId=gid,step="exonerate",
type="tar"))
# Prepare report per group of runs
report_ok,reportFile = prepareReport(ex,group['name'],
tot_counts, counts_primers,counts_primers_filtered,
tot_ambiguous, tot_discarded)
ex.add(reportFile,description = set_file_descr(
group['name']+"_report_demultiplexing.txt",
groupId=gid,step="final",type="txt",view="admin"))
if report_ok:
reportFile_pdf = unique_filename_in()
createReport(ex,reportFile,reportFile_pdf,script_path)
ex.add(reportFile_pdf,description=set_file_descr(
group['name']+"_report_demultiplexing.pdf",
groupId=gid,step="final",type="pdf"))
else:
logfile.write("*** Probable ambiguous classification: total_reads < sum(reads_by_primers) ***\n");logfile.flush()
add_pickle( ex, file_names,
set_file_descr('file_names',step="final",type='py',view='admin') )
return resFiles
def demultiplex_workflow(ex,
job,
gl,
file_path="../",
via='lsf',
logfile=sys.stdout,
debugfile=sys.stderr):
script_path = gl['script_path']
file_names = {}
job_groups = job.groups
resFiles = {}
for gid, group in job_groups.iteritems():
file_names[gid] = {}
primersFilename = 'group_' + group['name'] + "_barcode_file.fa"
primersFile = group.get("primersfile",
os.path.join(file_path, primersFilename))
ex.add(primersFile,
description=set_file_descr(primersFilename,
groupId=gid,
step="init",
type="fa"))
paramsFilename = 'group_' + group['name'] + "_param_file.txt"
paramsFile = group.get("paramsfile",
os.path.join(file_path, paramsFilename))
ex.add(paramsFile,
description=set_file_descr(paramsFilename,
groupId=gid,
step="init",
type="txt"))
params = load_paramsFile(paramsFile)
infiles = []
tot_counts = 0
allSubFiles = []
for rid, run in group['runs'].iteritems():
infiles.append(run)
n = count_lines(ex, run)
tot_counts += n / 4
if n > 10000000:
allSubFiles.extend(split_file(ex, run, n_lines=8000000))
else:
allSubFiles.append(run)
(resExonerate, tot_ambiguous,
tot_discarded) = parallel_exonerate(ex,
allSubFiles,
primersFile, (gid, group['name']),
via=via,
**params)
gzipfile(ex, cat(infiles))
ex.add(run + ".gz",
description=set_file_descr(group['name'] + "_full_fastq.gz",
groupId=gid,
step='exonerate',
view='debug',
type="fastq"))
logfile.write("Will get sequences to filter\n")
logfile.flush()
seqToFilter = getSeqToFilter(ex, primersFile)
logfile.write("Will filter the sequences\n")
filteredFastq = filterSeq(ex,
resExonerate,
seqToFilter,
gid,
group['name'],
via=via)
logfile.write("After filterSeq, filteredFastq=%s\n" % filteredFastq)
logfile.flush()
counts_primers = {}
counts_primers_filtered = {}
global bcDelimiter
if len(filteredFastq):
archive = unique_filename_in()
tgz = tarfile.open(archive, "w:gz")
for k, f in resExonerate.iteritems():
counts_primers[k] = count_lines(ex, f) / 4
if k in filteredFastq:
k2 = k.replace(bcDelimiter, "_")
file_names[gid][k2] = group['name'] + "_" + k2 + "_filtered"
ex.add(filteredFastq[k],
description=set_file_descr(file_names[gid][k2] +
".fastq",
groupId=gid,
step="final",
type="fastq"))
counts_primers_filtered[k] = count_lines(ex,
filteredFastq[k]) / 4
tgz.add(f,
arcname=group['name'] + "_" +
k.replace(bcDelimiter, "_") + ".fastq")
else:
k2 = k.replace(bcDelimiter, "_")
file_names[gid][k2] = group['name'] + "_" + k2
ex.add(f,
description=set_file_descr(file_names[gid][k2] +
".fastq",
groupId=gid,
step="final",
type="fastq"))
counts_primers_filtered[k] = 0
if len(filteredFastq):
tgz.close()
ex.add(archive,
description=set_file_descr(group['name'] +
"_unfiltered_fastq.tgz",
groupId=gid,
step="exonerate",
type="tar"))
# Prepare report per group of runs
report_ok, reportFile = prepareReport(ex, group['name'], tot_counts,
counts_primers,
counts_primers_filtered,
tot_ambiguous, tot_discarded)
ex.add(reportFile,
description=set_file_descr(group['name'] +
"_report_demultiplexing.txt",
groupId=gid,
step="final",
type="txt",
view="admin"))
if report_ok:
reportFile_pdf = unique_filename_in()
createReport(ex, reportFile, reportFile_pdf, script_path)
ex.add(reportFile_pdf,
description=set_file_descr(group['name'] +
"_report_demultiplexing.pdf",
groupId=gid,
step="final",
type="pdf"))
else:
logfile.write(
"*** Probable ambiguous classification: total_reads < sum(reads_by_primers) ***\n"
)
logfile.flush()
add_pickle(
ex, file_names,
set_file_descr('file_names', step="final", type='py', view='admin'))
return resFiles
def main(argv = None):
via = "lsf"
limspath = None
hts_key = ''
working_dir = None
config_file = None
if argv is None:
argv = sys.argv
try:
try:
opts,args = getopt.getopt(sys.argv[1:],"hu:k:d:w:c:",
["help","via=","key=","minilims=",
"working-directory=","config="])
except getopt.error, msg:
raise Usage(msg)
for o, a in opts:
if o in ("-h", "--help"):
print __doc__
print usage
return 0
elif o in ("-u", "--via"):
if a=="local":
via = "local"
elif a=="lsf":
via = "lsf"
else:
raise Usage("Via (-u) can only be \"local\" or \"lsf\", got %s." % (a,))
elif o in ("-w", "--working-directory"):
if os.path.exists(a):
os.chdir(a)
working_dir = a
else:
raise Usage("Working directory '%s' does not exist." % a)
elif o in ("-d", "--minilims"):
limspath = a
elif o in ("-k", "--key"):
hts_key = a
elif o in ("-c", "--config"):
config_file = a
else:
raise Usage("Unhandled option: " + o)
if not(limspath and os.path.exists(limspath)
and (hts_key != None or (config_file and os.path.exists(config_file)))):
raise Usage("Need a minilims and a job key or a configuration file")
M = MiniLIMS( limspath )
if len(hts_key)>1:
gl = use_pickle(M, "global variables")
htss = frontend.Frontend( url=gl['hts_mapseq']['url'] )
job = htss.job( hts_key )
[M.delete_execution(x) for x in M.search_executions(with_description=hts_key,fails=True)]
elif os.path.exists(config_file):
(job,gl) = frontend.parseConfig( config_file )
hts_key = job.description
else:
raise ValueError("Need either a job key (-k) or a configuration file (-c).")
g_rep = genrep.GenRep( url=gl["genrep_url"], root=gl["bwt_root"],
intype=job.options.get('input_type_id') or 0 )
assembly = g_rep.assembly( job.assembly_id )
if 'lims' in gl:
dafl = dict((loc,daflims.DAFLIMS( username=gl['lims']['user'], password=pwd ))
for loc,pwd in gl['lims']['passwd'].iteritems())
else:
dafl = None
if not('compute_densities' in job.options):
job.options['compute_densities'] = True
elif isinstance(job.options['compute_densities'],str):
job.options['compute_densities'] = job.options['compute_densities'].lower() in ['1','true','t']
if not('ucsc_bigwig' in job.options):
job.options['ucsc_bigwig'] = True
elif isinstance(job.options['ucsc_bigwig'],str):
job.options['ucsc_bigwig'] = job.options['ucsc_bigwig'].lower() in ['1','true','t']
job.options['ucsc_bigwig'] = job.options['ucsc_bigwig'] and job.options['compute_densities']
if not('create_gdv_project' in job.options):
job.options['create_gdv_project'] = False
elif isinstance(job.options['create_gdv_project'],str):
job.options['create_gdv_project'] = job.options['create_gdv_project'].lower() in ['1','true','t']
if job.options.get('read_extension'):
job.options['read_extension'] = int(job.options['read_extension'])
if job.options.get('merge_strands'):
job.options['merge_strands'] = int(job.options['merge_strands'])
logfile = open(hts_key+".log",'w')
with execution( M, description=hts_key, remote_working_directory=working_dir ) as ex:
logfile.write("Enter execution, fetch fastq files.\n");logfile.flush()
job = get_fastq_files( job, ex.working_directory, dafl )
logfile.write("Map reads.\n");logfile.flush()
mapped_files = map_groups( ex, job, ex.working_directory, assembly, {'via': via} )
logfile.write("Make stats:\n");logfile.flush()
for k,v in job.groups.iteritems():
logfile.write(str(k)+str(v['name'])+"\t");logfile.flush()
pdf = add_pdf_stats( ex, mapped_files,
{k:v['name']},
gl.get('script_path') or '',
description=set_file_descr(v['name']+"_mapping_report.pdf",groupId=k,step='stats',type='pdf') )
if job.options['compute_densities']:
logfile.write("computing densities.\n");logfile.flush()
if not(job.options.get('read_extension')>0):
job.options['read_extension'] = mapped_files.values()[0].values()[0]['stats']['read_length']
density_files = densities_groups( ex, job, mapped_files, assembly.chromosomes, via=via )
logfile.write("Finished computing densities.\n");logfile.flush()
if job.options['create_gdv_project']:
logfile.write("Creating GDV project.\n");logfile.flush()
gdv_project = gdv.create_gdv_project( gl['gdv']['key'], gl['gdv']['email'],
job.description,
assembly.nr_assembly_id,
gdv_url=gl['gdv']['url'], public=True )
logfile.write("GDV project: "+str(gdv_project['project_id']+"\n"));logfile.flush()
add_pickle( ex, gdv_project, description=set_file_descr("gdv_json",step='gdv',type='py',view='admin') )
allfiles = get_files( ex.id, M )
if 'ucsc_bigwig' and g_rep.intype == 0:
ucscfiles = get_files( ex.id, M, select_param={'ucsc':'1'} )
with open(hts_key+".bed",'w') as ucscbed:
for ftype,fset in ucscfiles.iteritems():
for ffile,descr in fset.iteritems():
if re.search(r' \(.*\)',descr): continue
ucscbed.write(track_header(descr,ftype,gl['hts_mapseq']['download'],ffile))
if job.options['create_gdv_project']:
allfiles['url'] = {gdv_project['public_url']: 'GDV view'}
download_url = gl['hts_mapseq']['download']
[gdv.add_gdv_track( gl['gdv']['key'], gl['gdv']['email'],
gdv_project['project_id'],
url=download_url+str(k),
name = re.sub('\.sql','',str(f)),
gdv_url=gl['gdv']['url'] )
for k,f in allfiles['sql'].iteritems()]
logfile.close()
print json.dumps(allfiles)
with open(hts_key+".done",'w') as done:
json.dump(allfiles,done)
if 'email' in gl:
r = email.EmailReport( sender=gl['email']['sender'],
to=str(job.email),
subject="Mapseq job "+str(job.description),
smtp_server=gl['email']['smtp'] )
r.appendBody('''
Your mapseq job has finished.
The description was:
'''+str(job.description)+'''
and its unique key is '''+hts_key+'''.
You can now retrieve the results at this url:
'''+gl['hts_mapseq']['url']+"jobs/"+hts_key+"/get_results")
r.send()
return 0
