ref_id , fasta_file = rnaseq_util.get_fa_from_genome(logger,ws_client,self.urls,params['ws_id'],hisat2_dir,params['genome_id'])
### Build Index for the fasta file
hisat2base = os.path.basename(fasta_file)
#hisat2base =os.path.join(hisat2_dir,handler_util.get_file_with_suffix(hisat2_dir,".fa"))
hisat2base_cmd = '{0} {1}'.format(fasta_file,hisat2base)
try:
logger.info("Building Index for Hisat2 {0}".format(hisat2base_cmd))
cmdline_output = script_util.runProgram(logger,"hisat2-build",hisat2base_cmd,None,hisat2_dir)
except Exception,e:
raise Exception("Failed to run command {0}".format(hisat2base_cmd))
### Check if GTF object exists in the workspace pull the gtf
ws_gtf = params['genome_id']+"_GTF"
gtf_file = script_util.check_and_download_existing_handle_obj(logger,ws_client,self.urls,params['ws_id'],ws_gtf,"KBaseRNASeq.GFFAnnotation",hisat2_dir,token)
if gtf_file is None:
rnaseq_util.create_gtf_annotation_from_genome(logger,ws_client,hs,self.urls,params['ws_id'],ref_id,params['genome_id'],hisat2_dir,token)
# Determine the num_threads provided by the user otherwise default the number of threads to 2
logger.info(" Number of threads used by each process {0}".format(self.num_threads))
task_param = {'job_id' : params['sampleset_id'],
'label' : r_label,
'ws_id' : params['ws_id'],
'reads_type' : sample_type,
'hisat2_dir' : self.directory,
'annotation_id': ref_id,
'sampleset_id' : None
}
self.task_list.append(task_param)
def collect(self) :
# do with
except Exception, e:
raise Exception(
"Failed to run command {0}".format(bowtie2base_cmd))
### Check if GTF object exists in the workspace pull the gtf
ref_id = bowtie_index['data']['genome_id']
genome_name = ws_client.get_object_info_new(
{"objects": [{
'ref': ref_id
}]})[0][1]
ws_gtf = genome_name + "_GTF"
gtf_file = script_util.check_and_download_existing_handle_obj(
logger, ws_client, self.urls, params['ws_id'], ws_gtf,
"KBaseRNASeq.GFFAnnotation", bowtie2_dir, token)
if gtf_file is None:
rnaseq_util.create_gtf_annotation_from_genome(
logger, ws_client, hs, self.urls, params['ws_id'], ref_id,
genome_name, bowtie2_dir, token)
count = 0
logger.info(" Number of threads used by each process {0}".format(
self.num_threads))
for i in reads:
try:
label = r_label[count]
task_param = {
'job_id': i,
'label': r_label[count],
'ws_id': params['ws_id'],
'bowtie2_dir': self.directory,
'annotation_id':
ref_id, # Changed annotation_id to ref_id for genome object
ws_gtf = annotation_gtf+"_GTF_Annotation"
ret = script_util.if_obj_exists(None,ws_client,params['ws_id'],"KBaseRNASeq.GFFAnnotation",[ws_gtf])
if not ret is None:
logger.info("GFF Annotation Exist for Genome Annotation {0}.... Skipping step ".format(annotation_gtf))
annot_name,annot_id = ret[0]
gtf_obj=ws_client.get_objects([{'ref' : annot_id}])[0]
gtf_id=gtf_obj['data']['handle']['id']
gtf_name=gtf_obj['data']['handle']['file_name']
try:
script_util.download_file_from_shock(logger, shock_service_url=self.urls['shock_service_url'], shock_id=gtf_id,filename=gtf_name, directory=tophat_dir,token=token)
gtf_file = os.path.join(tophat_dir,gtf_name)
except Exception,e:
logger.exception(e)
raise Exception( "Unable to download shock file, {0}".format(gtf_name))
else:
gtf_file =rnaseq_util.create_gtf_annotation_from_genome(logger,ws_client,hs,self.urls,params['ws_id'],genome_id,annotation_gtf,tophat_dir,token)
# Determine the num_threads provided by the user otherwise default the number of threads to 2
self.num_jobs = 1
logger.info(" Number of threads used by each process {0}".format(self.num_threads))
task_param = {'job_id' : params['sampleset_id'],
'label' : 'Single-Sample',
'ws_id' : params['ws_id'],
'reads_type' : sample_type,
'tophat_dir' : self.directory,
'gtf_file': gtf_file,
'annotation_id': genome_id,
'sampleset_id' : None
}
self.task_list.append(task_param)
class StringTieSampleSet(StringTie):
def __init__(self, logger, directory, urls, max_cores):
pprint(self.__class__)
super(self.__class__, self).__init__(logger, directory, urls,
max_cores)
#super(StringtTieSampleSet, self).__init__(logger, directory, urls)
# user defined shared variables across methods
#self.sample_info = None
self.alignmentset_info = None
self.num_threads = 1
def prepare(self):
# for quick testing, we recover parameters here
ws_client = self.common_params['ws_client']
hs = self.common_params['hs_client']
params = self.method_params
logger = self.logger
token = self.common_params['user_token']
stringtie_dir = self.directory
try:
a_sampleset = ws_client.get_objects([{
'name':
params['alignmentset_id'],
'workspace':
params['ws_id']
}])[0]
a_sampleset_info = ws_client.get_object_info_new({
"objects": [{
'name': params['alignmentset_id'],
'workspace': params['ws_id']
}]
})[0]
self.alignmentset_info = a_sampleset_info
a_sampleset_id = str(a_sampleset_info[6]) + '/' + str(
a_sampleset_info[0]) + '/' + str(a_sampleset_info[4])
alignmentset_id = a_sampleset_id
except Exception, e:
logger.exception("".join(traceback.format_exc()))
raise Exception("Error Downloading objects from the workspace ")
#read_sample_id']
### Check if the gtf file exists in the workspace. if exists download the file from that
genome_id = a_sampleset['data']['genome_id']
genome_name = ws_client.get_object_info([{
"ref": genome_id
}],
includeMetadata=None)[0][1]
ws_gtf = genome_name + "_GTF_Annotation"
gtf_file = script_util.check_and_download_existing_handle_obj(
logger, ws_client, self.urls, params['ws_id'], ws_gtf,
"KBaseRNASeq.GFFAnnotation", stringtie_dir, token)
if gtf_file is None:
rnaseq_util.create_gtf_annotation_from_genome(
logger, ws_client, hs, self.urls, params['ws_id'], genome_id,
genome_name, stringtie_dir, token)
gtf_info = ws_client.get_object_info_new(
{"objects": [{
'name': ws_gtf,
'workspace': params['ws_id']
}]})[0]
gtf_id = str(gtf_info[6]) + '/' + str(gtf_info[0]) + '/' + str(
gtf_info[4])
self.tool_opts = {
k: str(v)
for k, v in params.iteritems()
if not k in ('ws_id', 'alignmentset_id',
'num_threads') and v is not None
}
alignment_ids = a_sampleset['data']['sample_alignments']
m_alignment_names = a_sampleset['data']['mapped_rnaseq_alignments']
self.sampleset_id = a_sampleset['data']['sampleset_id']
### Get List of Alignments Names
self.align_names = []
for d_align in m_alignment_names:
for i, j in d_align.items():
self.align_names.append(j)
m_alignment_ids = a_sampleset['data']['mapped_alignments_ids']
self.num_jobs = len(alignment_ids)
if self.num_jobs < 2:
raise ValueError(
"Please ensure you have atleast 2 alignments to run Stringtie in Set mode"
)
logger.info(" Number of threads used by each process {0}".format(
self.num_threads))
count = 0
for i in m_alignment_ids:
for sample_name, alignment_id in i.items():
task_param = {
'job_id': alignment_id,
'gtf_file': gtf_file,
'ws_id': params['ws_id'],
'genome_id': genome_id,
'stringtie_dir': self.directory,
'annotation_id': gtf_id,
'sample_id': sample_name,
'alignmentset_id': alignmentset_id
}
self.task_list.append(task_param)
count = count + 1
script_util.move_files(logger,mv_dir,tophat_dir)
except Exception, e:
logger.error("".join(traceback.format_exc()))
raise Exception("Unzip indexfile error")
fasta_file =os.path.join(tophat_dir,(handler_util.get_file_with_suffix(tophat_dir,".fa")+".fa"))
bowtie2base =os.path.join(tophat_dir,handler_util.get_file_with_suffix(tophat_dir,".rev.1.bt2"))
### Check if GTF annotation object exist or skip this step
### Check if the gtf object exists in the workspace
### Only run create_gtf_annotation if object doesnt exist
ws_gtf = annotation_gtf+"_GTF_Annotation"
genome_name = script_util.ws_get_obj_name( logger, ws_client, params['ws_id'], genome_id )
gtf_file = script_util.check_and_download_existing_handle_obj(logger,ws_client,self.urls,params['ws_id'],ws_gtf,"KBaseRNASeq.GFFAnnotation",tophat_dir,token)
if gtf_file is None:
gtf_file = rnaseq_util.create_gtf_annotation_from_genome(logger,ws_client,hs,self.urls,params['ws_id'],genome_id,genome_name,tophat_dir,token)
#ret = script_util.if_obj_exists(None,ws_client,params['ws_id'],"KBaseRNASeq.GFFAnnotation",[ws_gtf]) # this line should be safe from reference
#if not ret is None:
# logger.info("GFF Annotation Exist for Genome Annotation {0}.... Skipping step ".format(annotation_gtf))
# annot_name,annot_id = ret[0]
# gtf_obj=ws_client.get_objects([{'ref' : annot_id}])[0]
# gtf_id=gtf_obj['data']['handle']['id']
# gtf_name=gtf_obj['data']['handle']['file_name']
# try:
# script_util.download_file_from_shock(logger, shock_service_url=self.urls['shock_service_url'], shock_id=gtf_id,filename=gtf_name, directory=tophat_dir,token=token)
# gtf_file = os.path.join(tophat_dir,gtf_name)
# except Exception,e:
# logger.exception(e)
# raise Exception( "Unable to download shock file, {0}".format(gtf_name))
#else:
# gtf_file =rnaseq_util.create_gtf_annotation_from_genome(logger,ws_client,hs,self.urls,params['ws_id'],genome_id,annotation_gtf,tophat_dir,token)
class StringTieSample(StringTie):
def __init__(self, logger, directory, urls, max_cores):
super(self.__class__, self).__init__(logger, directory, urls,
max_cores)
# user defined shared variables across methods
self.alignment_info = None
#self.sampleset_info = None
self.num_threads = 1
def prepare(self):
# for quick testing, we recover parameters here
ws_client = self.common_params['ws_client']
hs = self.common_params['hs_client']
params = self.method_params
logger = self.logger
token = self.common_params['user_token']
stringtie_dir = self.directory
try:
a_sample = ws_client.get_objects([{
'name': params['alignmentset_id'],
'workspace': params['ws_id']
}])[0]
a_alignment_info = ws_client.get_object_info_new({
"objects": [{
'name': params['alignmentset_id'],
'workspace': params['ws_id']
}]
})[0]
self.alignment_info = a_alignment_info
s_alignment_id = str(a_alignment_info[6]) + '/' + str(
a_alignment_info[0]) + '/' + str(a_alignment_info[4])
except Exception, e:
logger.exception("".join(traceback.format_exc()))
raise Exception("Error Downloading objects from the workspace ")
read_sample_id = a_sample['data']['read_sample_id']
### Check if the gtf file exists in the workspace. if exists download the file from that
genome_id = a_sample['data']['genome_id']
genome_name = ws_client.get_object_info([{
"ref": genome_id
}],
includeMetadata=None)[0][1]
ws_gtf = genome_name + "_GTF_Annotation"
gtf_file = script_util.check_and_download_existing_handle_obj(
logger, ws_client, self.urls, params['ws_id'], ws_gtf,
"KBaseRNASeq.GFFAnnotation", stringtie_dir, token)
if gtf_file is None:
rnaseq_util.create_gtf_annotation_from_genome(
logger, ws_client, hs, self.urls, params['ws_id'], genome_id,
genome_name, stringtie_dir, token)
gtf_info = ws_client.get_object_info_new(
{"objects": [{
'name': ws_gtf,
'workspace': params['ws_id']
}]})[0]
gtf_id = str(gtf_info[6]) + '/' + str(gtf_info[0]) + '/' + str(
gtf_info[4])
self.tool_opts = {
k: str(v)
for k, v in params.iteritems()
if not k in ('ws_id', 'alignmentset_id',
'num_threads') and v is not None
}
self.num_jobs = 1
logger.info(" Number of threads used by each process {0}".format(
self.num_threads))
task_param = {
'job_id': s_alignment_id,
'gtf_file': gtf_file,
'ws_id': params['ws_id'],
'genome_id': genome_id,
'stringtie_dir': self.directory,
'annotation_id': gtf_id,
'sample_id': read_sample_id,
'alignmentset_id': None
}
self.task_list.append(task_param)
