def query(*args, **kwargs):
facility = args[0]
if kwargs['user'] and kwargs['password']:
dafl = daflims.DAFLIMS(username=kwargs['user'],
password=kwargs['password'])
else:
params = use_pickle(MiniLIMS(kwargs['minilims']),
"global variables")['lims']
dafl = dict(
(loc, daflims.DAFLIMS(username=params['user'], password=pwd))
for loc, pwd in params['passwd'].iteritems())[facility]
try:
info = dafl._lanedesc(*args)
print json.dumps(info, ensure_ascii=False)
except ValueError as e:
if len(args) > 4:
msg = "Access not granted to data [%s: %s-%i/%i/%s]" % args
else:
msg = "Access not granted to data [%s: %s-%i/%i]" % args
print msg
return 1
try:
if len(args) > 4:
libname = args[4]
else:
libname = None
url = dafl._symlinkname(*args[:4], libname=libname)
urlok = []
for k in sorted(url.keys()):
_ = urlopen(url[k])
urlok.append(url[k])
print "\n".join(urlok)
except (ValueError, URLError) as e:
print "File not accessible", e
return 2
if kwargs.get('output'):
try:
filename = dafl._fetch_symlink(url, kwargs['output'])
print filename
except Exception as e:
print "Problem with downloading %s: %s" % (url, e)
return 3
return 0
def main(argv=None):
parser = None
try:
parser = optparse.OptionParser(usage=usage, description=description)
for opt in opts:
parser.add_option(opt[0],opt[1],help=opt[2],**opt[3])
(options, args) = parser.parse_args()
if options.minilims in module_list:
M = MiniLIMS(os.path.join(options.basepath,options.minilims+"_minilims"))
elif os.path.exists(options.minilims):
M = MiniLIMS(options.minilims)
else:
raise Usage("Minilims not found, please specify a path or a module with -m.")
tags = options.tag
if tags:
tags = tags.split(",")
if tags[0].count("="):
tags = dict(x.split("=") for x in tags)
elif tags[0].count(":"):
tags = dict(x.split(":") for x in tags)
if options.gdv:
if tags: tags['type'] = 'sql'
else: tags = {'type': 'sql'}
if options.programs:
if isinstance(options.execution, basestring):
exlist = M.search_executions(with_description=options.execution)
if len(exlist) == 0:
exlist = M.search_executions(with_text=options.execution)
if len(exlist) == 0:
raise Usage("Execution with key %s not found in %s." %(options.execution,options.minilims))
exid = max(exlist)
else:
exid = int(options.execution or 0)
exec_data = M.fetch_execution(exid)['programs']
outfile = options.output and open(options.output,"w") or sys.stdout
for prog in exec_data:
pargs = prog['arguments']
if tags and all([t not in x for x in pargs for t in tags]):
continue
stout = prog['stdout'].encode('ascii','ignore')
sterr = prog['stderr'].encode('ascii','ignore')
if pargs[0] == 'bsub': pargs = str(pargs[-1])
else: pargs = str(" ".join(pargs))
outfile.write("\n".join([pargs,stout,'',sterr,'','-'*40,'']))
outfile.close()
return 0
files = get_files(options.execution,M,select_param=tags)
fprefix = ''
if options.list:
if options.output and os.path.isdir(options.output):
options.output = os.path.join(options.output,options.execution+".txt")
outfile = options.output and open(options.output,"w") or sys.stdout
outfile.write("\t".join(["type","group","name","path","comment"])+"\n")
else:
if not(options.output): options.output = "./"
if not(os.path.isdir(options.output)):
options.output, fprefix = os.path.split(options.output)
if options.gdv:
gdvpaths = []
gdvnames = []
for t in sorted(files.keys()):
for k,v in files[t].iteritems():
fpath = os.path.join(M.file_path,k)
vv = v.split("[")
fname = fprefix+vv.pop(0)
comment = ''
par_dict = {}
if vv:
vv = vv[0].split("]")
par_dict = dict(x.split(":") for x in vv.pop(0).split(","))
if vv: comment = vv[0].strip().strip("()")
if not(options.admin) and par_dict.get('view') == 'admin': continue
if options.list: outfile.write("\t".join([t,par_dict.get('groupId',''),fname,fpath,comment])+"\n")
if options.copy: shutil.copy(fpath, os.path.join(options.output,fname))
if options.symlink: os.symlink(fpath, os.path.join(options.output,fname))
if options.gdv:
gdvpaths.append(fpath)
gdvnames.append(re.sub('\.sql.*','',str(fname)))
if options.list and options.output: outfile.close()
if options.gdv:
from bbcflib import gdv
gdvurl = options.gdvurl or gdv.default_url
gdvproject = gdv.get_project(mail=options.email, key=options.key,
project_key=options.gdv)
if gdvproject.get('project',{}).get('id',0)>0:
try:
tr = gdv.multiple_tracks( mail=options.email, key=options.key,
project_id=gdvproject['project']['id'],
urls=gdvpaths, names=gdvnames, extensions=['sql']*len(gdvpaths),
force=True, serv_url=gdvurl )
except Exception, err:
raise Usage("GDV Tracks Failed: %s\n" %err)
print """
*********** GDV project at: ***********
%s/public/project?k=%s&id=%s
***************************************
""" %(gdvurl,gdvproject['project']['download_key'],gdvproject['project']['id'])
return 0
def __call__(self,opts):
self.opts = opts
if os.path.exists(self.opts.wdir):
os.chdir(self.opts.wdir)
else:
raise Usage("Working directory '%s' does not exist." %self.opts.wdir)
##### Connect to Minilims, recover global variables, fetch job info
self.minilims = os.path.join(self.opts.basepath,self.name+"_minilims")
M = MiniLIMS(self.minilims)
if not((self.opts.key != None or (self.opts.config and os.path.exists(self.opts.config)))):
raise Usage("Need a job key or a configuration file")
if self.opts.key:
self.globals = use_pickle(M, "global variables")
htss = frontend.Frontend( url=self.globals['hts_mapseq']['url'] )
self.job = htss.job( self.opts.key )
[M.delete_execution(x) for x in \
M.search_executions(with_description=self.opts.key,fails=True)]
if self.job.options.get("config_file"):
if os.path.exists(self.job.options["config_file"]):
self.opts.config = os.path.abspath(self.job.options["config_file"])
elif os.path.exists("config.txt"):
self.opts.config = os.path.abspath("config.txt")
if self.opts.config and os.path.exists(self.opts.config):
(self.job,self.globals) = frontend.parseConfig( self.opts.config, self.job, self.globals )
elif os.path.exists(self.opts.config):
(self.job,self.globals) = frontend.parseConfig( self.opts.config )
self.opts.key = self.job.description
else:
raise Usage("Need either a job key (-k) or a configuration file (-c).")
##### Genrep instance
if 'fasta_file' in self.job.options:
if os.path.exists(self.job.options['fasta_file']):
self.job.options['fasta_file'] = os.path.abspath(self.job.options['fasta_path'])
else:
for ext in (".fa",".fa.gz",".tar.gz"):
if os.path.exists("ref_sequence"+ext):
self.job.options['fasta_file'] = os.path.abspath("ref_sequence"+ext)
if not os.path.exists(self.job.options['fasta_file']):
raise Usage("Don't know where to find fasta file %s." %self.job.options["fasta_file"])
g_rep = genrep.GenRep( url=self.globals.get("genrep_url"),
root=self.globals.get("bwt_root") )
##### Configure facility LIMS
if 'lims' in self.globals:
from bbcflib import daflims
self.job.dafl = dict((loc,daflims.DAFLIMS( username=self.globals['lims']['user'],
password=pwd ))
for loc,pwd in self.globals['lims']['passwd'].iteritems())
########################################################################
########################## EXECUTION #################################
########################################################################
##### Logging
logfile_name = os.path.abspath(self.opts.key+".log")
debugfile_name = os.path.abspath(self.opts.key+".debug")
self.logfile = open(logfile_name,'w')
self.debugfile = open(debugfile_name,'w')
self.debug_write(json.dumps(self.globals)+"\n")
with execution( M, description=self.opts.key,
remote_working_directory=self.opts.wdir ) as ex:
self.log_write("Enter execution. Current working directory: %s" %ex.working_directory)
self.job.assembly = genrep.Assembly( assembly=self.job.assembly_id,
genrep=g_rep,
fasta=self.job.options.get('fasta_file'),
annot=self.job.options.get('annot_file'),
intype=self.job.options.get('input_type_id',0),
ex=ex, via=self.opts.via,
bowtie2=self.job.options.get("bowtie2",True) )
##### Check all the options
if not self.check_options():
raise Usage("Problem with options %s" %self.opts)
self.debug_write(json.dumps(self.job.options))
self.init_files( ex )
##### Run workflow
self.log_write("Starting workflow.")
self.main_func(ex,**self.main_args)
##### Add logs to the LIMS in admin mode
self.logfile.flush()
self.debugfile.flush()
log_desc = set_file_descr('logfile.txt', step='log', type='txt', view="admin")
debug_desc = set_file_descr('debug.txt', step='log', type='txt', view="admin")
ex.add(os.path.join(logfile_name), description=log_desc)
ex.add(os.path.join(debugfile_name), description=debug_desc)
##### Create GDV project
if self.job.options['create_gdv_project']: self.gdv_create(ex)
########################################################################
######################## POSTPROCESSING ##############################
########################################################################
allfiles = get_files( ex.id, M )
if self.job.options['create_gdv_project'] and \
self.job.options['gdv_project'].get('project',{}).get('id',0)>0:
allfiles['url'] = self.gdv_upload(allfiles.get('sql',{}))
self.logfile.close()
self.debugfile.close()
print json.dumps(allfiles)
with open(self.opts.key+".done",'w') as done: json.dump(allfiles,done)
self.send_email()
return 0
def main():
map_args = None # {'bwt_args':["-n",str(3),"-p",str(4),"-d",str(50),"--chunkmbs",str(1024),"-m",str(5)]}
opts = (("-v", "--via", "Run executions using method 'via' (can be 'local' or 'lsf')", {'default': "lsf"}),
("-k", "--key", "Alphanumeric key of the new RNA-seq job", {'default': None}),
("-d", "--minilims", "MiniLIMS where RNAseq executions and files will be stored.", {'default': None}),
("-m", "--mapseq-minilims", "MiniLIMS where a previous Mapseq execution and files has been stored. \
Set it to None to align de novo from read files.",
{'default': "/data/htsstation/mapseq/mapseq_minilims", 'dest':"ms_limspath"}),
("-w", "--working-directory", "Create execution working directories in wdir",
{'default': os.getcwd(), 'dest':"wdir"}),
("-c", "--config", "Config file", {'default': None}),
("-p", "--pileup_level", "Target features, inside of quotes, separated by commas.\
E.g. 'genes,exons,transcripts'",{'default': "genes,exons,transcripts"}))
try:
usage = "run_rnaseq.py [OPTIONS]"
desc = """A High-throughput RNA-seq analysis workflow. It returns a file containing
a column of transcript counts for each given BAM file, normalized using DESeq's
size factors. """
parser = optparse.OptionParser(usage=usage, description=desc)
for opt in opts:
parser.add_option(opt[0],opt[1],help=opt[2],**opt[3])
(opt, args) = parser.parse_args()
if os.path.exists(opt.wdir): os.chdir(opt.wdir)
else: parser.error("Working directory '%s' does not exist." % opt.wdir)
if not opt.minilims: parser.error("Must specify a MiniLIMS to attach to")
# Rna-seq job configuration
M = MiniLIMS(opt.minilims)
if opt.key:
gl = use_pickle( M, "global variables" )
htss = frontend.Frontend( url=gl['hts_rnaseq']['url'] )
job = htss.job(opt.key) # new *RNA-seq* job instance
#h_pileup_level = {'0':'genes', '1':'exons', '2':'transcripts'}
#pileup_level = [h_pileup_level[e] for e in job.options.get('pileup_level').split(',')]
[M.delete_execution(x) for x in M.search_executions(with_description=opt.key,fails=True)]
description = "Job run with mapseq key %s" % opt.key
elif os.path.exists(opt.config):
pileup_level = opt.pileup_level.split(',')
(job,gl) = frontend.parseConfig(opt.config)
description = "Job run with config file %s" % opt.config
else: raise ValueError("Need either a job key (-k) or a configuration file (-c).")
job.options['ucsc_bigwig'] = job.options.get('ucsc_bigwig') or True
job.options['gdv_project'] = job.options.get('gdv_project') or False
job.options['discard_pcr_duplicates'] = job.options.get('discard_pcr_duplicates') or False
assembly_id = job.assembly_id
g_rep = genrep.GenRep( gl['genrep_url'], gl.get('bwt_root'), intype=1 )
#intype is for mapping on the genome (intype=0), exons (intype=1) or transcriptome (intype=2)
assembly = g_rep.assembly(assembly_id)
# Retrieve mapseq output
mapseq_url = None
if 'hts_mapseq' in gl: mapseq_url = gl['hts_mapseq']['url']
# Program body #
with execution(M, description=description, remote_working_directory=opt.wdir ) as ex:
if opt.ms_limspath == "None":
print "Alignment..."
job = mapseq.get_fastq_files( job, ex.working_directory)
fastq_root = os.path.abspath(ex.working_directory)
bam_files = mapseq.map_groups(ex, job, fastq_root, assembly_or_dict=assembly, map_args=map_args)
print "Reads aligned."
else:
print "Loading BAM files..."
(bam_files, job) = mapseq.get_bam_wig_files(ex, job, minilims=opt.ms_limspath, hts_url=mapseq_url,
script_path=gl.get('script_path') or '', via=opt.via )
print "Loaded."
assert bam_files, "Bam files not found."
print "Current working directory:", ex.working_directory
rnaseq.rnaseq_workflow(ex, job, assembly, bam_files, pileup_level=pileup_level, via=opt.via)
# End of program body #
# GDV
allfiles = common.get_files(ex.id, M)
if 'gdv_project' in job.options and 'sql' in allfiles:
allfiles['url'] = {job.options['gdv_project']['public_url']: 'GDV view'}
download_url = gl['hts_rnapseq']['download']
[gdv.add_gdv_track( gl['gdv']['key'], gl['gdv']['email'],
job.options['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()]
print json.dumps(allfiles)
# E-mail
if 'email' in gl:
r = email.EmailReport( sender=gl['email']['sender'],
to=str(job.email),
subject="RNA-seq job "+str(job.description),
smtp_server=gl['email']['smtp'] )
r.appendBody('''Your RNA-seq job is finished.
\n The description was: '''+str(job.description)+''' and its unique key is '''+opt.key+'''.
\n You can retrieve the results at this url: '''+gl['hts_rnaseq']['url']+"jobs/"+opt.key+"/get_results" )
r.send()
sys.exit(0)
except Usage, err:
print >>sys.stderr, err.msg
print >>sys.stderr, usage
return 2
