def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Some specific settings
psv['nthreads'] = 8
psv['map_thresh'] = 10
psv['sample_size'] = 15000000
psv['read_length'] = args.read_length
psv['pe_or_se'] = "pe"
for ltr in sorted(psv['reps'].keys()):
rep = psv['reps'][ltr]
if not rep['paired_end']:
psv['pe_or_se'] = "se"
if rep['paired_end'] and 'barcode' in rep and rep[
'barcode'] == "undetected":
del rep['barcode']
if args.umi:
psv['umi'] = "yes"
psv['upper_limit'] = 0
# Crawford fastqs require trimming
psv["trim_len"] = 0
if not self.template and not psv['paired_end'] and "crawford" in psv[
'lab']:
print "Detected that fastqs will be trimmed to 20"
psv["trim_len"] = 20
self.multi_rep = True # For DNase, a single tech_rep moves on to merge/filter.
self.combined_reps = True
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Some specific settings
psv['nthreads'] = 8
psv['map_thresh'] = 10
psv['sample_size'] = 15000000
psv['read_length'] = args.read_length
psv['pe_or_se'] = "pe"
for ltr in sorted( psv['reps'].keys() ):
rep = psv['reps'][ltr]
if not rep['paired_end']:
psv['pe_or_se'] = "se"
if rep['paired_end'] and 'barcode' in rep and rep['barcode'] == "undetected":
del rep['barcode']
if args.umi:
psv['umi'] = "yes"
psv['upper_limit'] = 0
# Crawford fastqs require trimming
psv["trim_len"] = 0
if not self.template and not psv['paired_end'] and "crawford" in psv['lab']:
print "Detected that fastqs will be trimmed to 20"
psv["trim_len"] = 20
self.multi_rep = True # For DNase, a single tech_rep moves on to merge/filter.
self.combined_reps = True
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
#args.pe = True # This is necessary to ensure templating does what it must.
psv = Launch.pipeline_specific_vars(self, args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv[
'annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome'] + " has no " + psv[
'annotation'] + " annotation."
sys.exit(1)
# Some specific settings
psv['assay_type'] = "rampage"
if self.exp["assay_term_name"] == "CAGE":
psv['assay_type'] = "cage"
psv['nthreads'] = 8
if not self.template:
psv['control'] = args.control
if psv['paired_end'] and psv['assay_type'] == "cage":
print "ERROR: CAGE is always expected to be single-end but mapping says otherwise."
sys.exit(1)
elif not psv['paired_end'] and psv['assay_type'] == "rampage":
print "Rampage is always expected to be paired-end but mapping says otherwise."
sys.exit(1)
if not psv["stranded"]:
print "Detected unstranded library"
# run will either be for combined or single rep.
if not self.combined_reps:
run = psv['reps'][
'a'] # If not combined then run will be for the first (only) replicate
else:
run = psv
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
if self.exp["assay_term_name"] == "CAGE":
psv['name'] = psv['assay_type'] + psv['name'][4:]
psv['title'] = "CAGE" + psv['title'][7:]
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['rnd_seed'] = 12345
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
self.no_tophat = args.no_tophat
if not self.no_tophat:
self.PRUNE_STEPS = []
# Must override results location because of annotation
psv['resultsLoc'] = dxencode.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc'] + psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['rnd_seed'] = 12345
# If paired-end then read_strand might vary TruSeq or ScriptSeq, but only for quant-rsem
psv["read_strand"] = "unstranded" # SE experiments are all unstranded
if psv["paired_end"]:
psv["read_strand"] = "reverse" # Usual ENCODE LRNA experiments are rd1-/rd2+ (AKA reverse)
if not psv["stranded"]:
psv["read_strand"] = "unstranded" # "ScriptSeq" experiments are rd1+/rd2- (AKA forward)
print "Detected unstranded library"
elif psv.get('ScriptSeq', False): # file.replicate.library.document contains "/documents/F17c31e10-1542-42c6-8b4c-3afff95564cf%2F"
psv["read_strand"] = "ScriptSeq" # "ScriptSeq" experiments are rd1+/rd2- (AKA forward)
print "Detected ScriptSeq"
else: # SE
if psv["stranded"]:
psv["read_strand"] = psv.get("strand_direction", "unstranded")
else:
psv["read_strand"] = "unstranded"
if psv["stranded"]:
print "Strand orientation is '%s'" % (psv["read_strand"])
# print "Detected special cases"
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
self.no_tophat = True
if args.tophat_also:
self.no_tophat = False
self.PRUNE_STEPS = [] # This blocks pruning... keeping tophat
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder, self.FOLDER_DEFAULT, self.proj_name,
psv['exp_type'], psv['genome'], psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Now add pipline specific variables and tests
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv[
'annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome'] + " has no " + psv[
'annotation'] + " annotation."
sys.exit(1)
# Paired ends?
if psv['paired_end']:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
#print json.dumps(psv,indent=4,sort_keys=True)
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
# By replicate:
for ltr in psv['reps'].keys():
if len(ltr) != 1: # only simple reps
continue
rep = psv['reps'][ltr]
rep["clipping_model"] = "ENCODE3" # Default
if "a_tailing" in rep:
rep["clipping_model"] = "A_Tailing_" + rep["a_tailing"]
print "%s detected for %s" % (rep["clipping_model"],
rep["rep_tech"])
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
# Must override results location because of annotation
genome = psv['genome']
if self.no_refs: # (no_refs is only True when templating)
genome = None # If templating with no refs then this will hide genome and annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
if not psv['paired_end']:
print "Rampage is always expected to be paired-end but mapping says otherwise."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['control'] = args.control
# run will either be for combined or single rep.
if not psv['combined']:
run = psv['reps']['a'] # If not combined then run will be for the first (only) replicate
else:
run = psv
# workflow labeling
psv['description'] = "The ENCODE Rampage RNA pipeline for long RNAs"
run['name'] = "rampage_"+psv['genome']
if psv['genome'] == 'mm10':
run['name'] += psv['annotation']
if psv['gender'] == 'female':
run['name'] += "XX"
else:
run['name'] += "XY"
run['title'] = "Rampage RNA " + psv['experiment'] + " - " + run['rep_tech']
run['name'] += "_"+psv['experiment']+"_" + run['rep_tech']
if not psv['combined']:
run['title'] += " [library '"+run['library_id']+"']"
run['title'] += " on " + psv['genome']+" - "+psv['gender']
# Must override results location because of annotation
psv['resultsLoc'] = dxencode.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc'] + psv['experiment'] + '/'
psv['reps']['a']['resultsFolder'] = psv['resultsLoc'] + psv['experiment'] + '/' + \
psv['reps']['a']['rep_tech'] + '/'
if psv['combined']:
psv['reps']['b']['resultsFolder'] = psv['resultsLoc'] + psv['experiment'] + '/' + \
psv['reps']['b']['rep_tech'] + '/'
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
#args.pe = True # This is necessary to ensure templating does what it must.
psv = Launch.pipeline_specific_vars(self,args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Some specific settings
psv['assay_type'] = "rampage"
if self.exp["assay_term_name"] == "CAGE":
psv['assay_type'] = "cage"
psv['nthreads'] = 8
if not self.template:
psv['control'] = args.control
if psv['paired_end'] and psv['assay_type'] == "cage":
print "ERROR: CAGE is always expected to be single-end but mapping says otherwise."
sys.exit(1)
elif not psv['paired_end'] and psv['assay_type'] == "rampage":
print "Rampage is always expected to be paired-end but mapping says otherwise."
sys.exit(1)
# run will either be for combined or single rep.
if not self.combined_reps:
run = psv['reps']['a'] # If not combined then run will be for the first (only) replicate
else:
run = psv
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
if self.exp["assay_term_name"] == "CAGE":
psv['name'] = psv['assay_type'] + psv['name'][4:]
psv['title'] = "CAGE" + psv['title'][7:]
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Now add pipline specific variables and tests
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Paired ends?
if psv['paired_end']:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
#print json.dumps(psv,indent=4,sort_keys=True)
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
# By replicate:
for ltr in psv['reps'].keys():
if len(ltr) != 1: # only simple reps
continue
rep = psv['reps'][ltr]
rep["clipping_model"] = "ENCODE3" # Default
if "a_tailing" in rep:
rep["clipping_model"] = "A_Tailing_" + rep["a_tailing"]
print "%s detected for %s" % (rep["clipping_model"],rep["rep_tech"])
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
# Must override results location because of annotation
genome = psv['genome']
if self.no_refs: # (no_refs is only True when templating)
genome = None # If templating with no refs then this will hide genome and annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv[
'annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome'] + " has no " + psv[
'annotation'] + " annotation."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['rnd_seed'] = 12345
# Override paired-end with TruSeq or ScriptSeq, but only for quant-rsem
psv["paired_type"] = "true"
if not psv["paired_end"]:
psv["paired_type"] = "false"
else:
if psv.get(
'ScriptSeq', False
): # file.replicate.library.document contains "/documents/F17c31e10-1542-42c6-8b4c-3afff95564cf%2F"
psv["paired_type"] = "ScriptSeq"
print "Detected ScriptSeq"
else:
psv["paired_type"] = "TruSeq"
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
self.no_tophat = args.no_tophat
if not self.no_tophat:
self.PRUNE_STEPS = []
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Some specific settings
psv['nthreads'] = 8
psv['min_insert'] = 0
psv['max_insert'] = 500
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Some specific settings
psv['nthreads'] = 8
psv['min_insert'] = 0
psv['max_insert'] = 500
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['rnd_seed'] = 12345
# If paired-end then read_strand might vary TruSeq or ScriptSeq, but only for quant-rsem
psv["read_strand"] = "unstranded" # SE experiments are all unstranded
if psv["paired_end"]:
psv["read_strand"] = "reverse" # Usual ENCODE LRNA experiments are rd1-/rd2+ (AKA reverse)
if not psv["stranded"]:
psv["read_strand"] = "unstranded" # "ScriptSeq" experiments are rd1+/rd2- (AKA forward)
print "Detected unstranded library"
elif psv.get('ScriptSeq', False): # file.replicate.library.document contains "/documents/F17c31e10-1542-42c6-8b4c-3afff95564cf%2F"
psv["read_strand"] = "ScriptSeq" # "ScriptSeq" experiments are rd1+/rd2- (AKA forward)
print "Detected ScriptSeq"
# print "Detected special cases"
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
self.no_tophat = True
if args.tophat_also:
self.no_tophat = False
self.PRUNE_STEPS = [] # This blocks pruning... keeping tophat
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder, self.FOLDER_DEFAULT, self.proj_name,
psv['exp_type'], psv['genome'], psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
"""Adds pipeline specific variables to a dict, for use building the workflow."""
psv = Launch.pipeline_specific_vars(self, args)
# Now add pipline specific variables and tests
# Could be multiple annotations supported per genome
psv["annotation"] = args.annotation
if psv["genome"] != self.GENOME_DEFAULT and psv["annotation"] == self.ANNO_DEFAULT:
psv["annotation"] = self.ANNO_DEFAULTS[psv["genome"]]
if psv["annotation"] not in self.ANNO_ALLOWED[psv["genome"]]:
print psv["genome"] + " has no " + psv["annotation"] + " annotation."
sys.exit(1)
# Paired ends?
if psv["paired_end"]:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
# print json.dumps(psv,indent=4,sort_keys=True)
sys.exit(1)
# Some specific settings
psv["nthreads"] = 8
# If annotation is not default, then add it to title
if psv["annotation"] != self.ANNO_DEFAULTS[psv["genome"]]:
psv["title"] += ", " + psv["annotation"]
psv["name"] += "_" + psv["annotation"]
# Must override results location because of annotation
genome = psv["genome"]
if self.no_refs: # (no_refs is only True when templating)
genome = None # If templating with no refs then this will hide genome and annotation
psv["resultsLoc"] = self.umbrella_folder(
args.folder, self.FOLDER_DEFAULT, self.proj_name, psv["exp_type"], psv["genome"], psv["annotation"]
)
psv["resultsFolder"] = psv["resultsLoc"]
if not self.template:
psv["resultsFolder"] += psv["experiment"] + "/"
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self, args, verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self, args)
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv[
'annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome'] + " has no " + psv[
'annotation'] + " annotation."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
psv['rnd_seed'] = 12345
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
self.no_tophat = args.no_tophat
if not self.no_tophat:
self.PRUNE_STEPS = []
# Must override results location because of annotation
psv['resultsLoc'] = self.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc']
if not self.template:
psv['resultsFolder'] += psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv, indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Now add pipline specific variables and tests
# Could be multiple annotations supported per genome
psv['annotation'] = args.annotation
if psv['genome'] != self.GENOME_DEFAULT and psv['annotation'] == self.ANNO_DEFAULT:
psv['annotation'] = self.ANNO_DEFAULTS[psv['genome']]
if psv['annotation'] not in self.ANNO_ALLOWED[psv['genome']]:
print psv['genome']+" has no "+psv['annotation']+" annotation."
sys.exit(1)
# Paired ends?
if psv['paired_end']:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
#print json.dumps(psv,indent=4,sort_keys=True)
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
# If annotation is not default, then add it to title
if psv['annotation'] != self.ANNO_DEFAULTS[psv['genome']]:
psv['title'] += ', ' + psv['annotation']
psv['name'] += '_' + psv['annotation']
# Must override results location because of annotation
psv['resultsLoc'] = dxencode.umbrella_folder(args.folder,self.FOLDER_DEFAULT,self.proj_name,psv['exp_type'], \
psv['genome'],psv['annotation'])
psv['resultsFolder'] = psv['resultsLoc'] + psv['experiment'] + '/'
self.update_rep_result_folders(psv)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Now add pipline specific variables and tests
# Paired ends?
if psv['paired_end']:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
#print json.dumps(psv,indent=4,sort_keys=True)
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
# run will either be for combined or single rep.
if self.combined_reps:
print "Small-RNA-seq pipeline currently does not support combined-replicate processing."
sys.exit(1)
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
def pipeline_specific_vars(self,args,verbose=False):
'''Adds pipeline specific variables to a dict, for use building the workflow.'''
psv = Launch.pipeline_specific_vars(self,args)
# Now add pipline specific variables and tests
# Paired ends?
if psv['paired_end']:
print "Small-RNA is always expected to be single-end but mapping says otherwise."
sys.exit(1)
# Some specific settings
psv['nthreads'] = 8
# run will either be for combined or single rep.
if not psv['combined']:
run = psv['reps']['a'] # If not combined then run will be for the first (only) replicate
else:
run = psv
print "Small-RNA-seq pipeline currently does not support combined-replicate processing."
sys.exit(1)
# workflow labeling
psv['description'] = "The ENCODE RNA Seq pipeline for short RNA"
genderToken = "XY"
if psv['gender'] == 'female':
genderToken = "XX"
run['title'] = "short RNA-seq " + psv['experiment'] + " - "+run['rep_tech'] + \
" (library '"+run['library_id']+"') on " + psv['genome'] + \
" - "+psv['gender']
run['name'] = "srna_"+psv['genome']+genderToken+"_"+psv['experiment'] + "_"+run['rep_tech']
if verbose:
print "Pipeline Specific Vars:"
print json.dumps(psv,indent=4)
return psv
