gtf_name = gtf_obj['data']['handle']['file_name']
try:
script_util.download_file_from_shock(
logger,
shock_service_url=services['shock_service_url'],
shock_id=gtf_id,
filename=gtf_name,
directory=hisat2_dir,
token=token)
gtf_file = os.path.join(hisat2_dir, gtf_name)
except Exception, e:
raise Exception(
"Unable to download shock file, {0}".format(gtf_name))
else:
script_util.create_gtf_annotation(logger, ws_client, hs, services,
params['ws_id'], annotation_id,
params['genome_id'], fasta_file,
hisat2_dir, token)
# Determine the num_threads provided by the user otherwise default the number of threads to 2
if ('num_threads' in params and params['num_threads'] is not None):
num_threads = int(params['num_threads'])
else:
num_threads = 2
num_cores = mp.cpu_count()
logger.info("Number of available cores : {0}".format(num_cores))
b_tasks = []
if sample_type == 'KBaseRNASeq.RNASeqSampleSet':
reads = sample['data']['sample_ids']
reads_type = sample['data']['Library_type']
r_label = sample['data']['condition']
num_samples = len(reads)
if num_cores != 1:
"Unable to download shock file, {0}".format(gtf_name))
else:
fasta_file = script_util.generate_fasta(logger, services, token,
annotation_id, diffexp_dir,
annotation_name)
logger.info("Sanitizing the fasta file to correct id names {}".format(
datetime.datetime.utcnow()))
mapping_filename = c_mapping.create_sanitized_contig_ids(fasta_file)
c_mapping.replace_fasta_contig_ids(fasta_file,
mapping_filename,
to_modified=True)
logger.info("Generating FASTA file completed successfully : {}".format(
datetime.datetime.utcnow()))
gtf_file = script_util.create_gtf_annotation(logger, ws_client, hs,
services, params['ws_id'],
annotation_id,
gtf_obj_name, fasta_file,
diffexp_dir, token)
m_expr_ids = e_sample['data']['mapped_expression_ids']
m_align_exp = []
labels = []
expressions = []
counter = 0
assembly_file = os.path.join(diffexp_dir, ASSEMBLY_GTF_FN)
list_file = open(assembly_file, 'w')
for i in m_expr_ids:
for a_id, e_id in i.items():
#print a_id + ":" + e_id
files = {}
a_obj, e_obj = ws_client.get_objects([{
'ref': a_id
gtf_info = ws_client.get_object_info_new({"objects": [{'name': gtf_obj_name, 'workspace': params['ws_id']}]})[0]
gtf_annotation_id = str(gtf_info[6]) + '/' + str(gtf_info[0]) + '/' + str(gtf_info[4])
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=services['shock_service_url'], shock_id=gtf_id,filename=gtf_name, directory=diffexp_dir,token=token)
gtf_file = os.path.join(diffexp_dir,gtf_name)
except Exception,e:
raise Exception( "Unable to download shock file, {0}".format(gtf_name))
else:
fasta_file= script_util.generate_fasta(logger,services,token,annotation_id,diffexp_dir,annotation_name)
logger.info("Sanitizing the fasta file to correct id names {}".format(datetime.datetime.utcnow()))
mapping_filename = c_mapping.create_sanitized_contig_ids(fasta_file)
c_mapping.replace_fasta_contig_ids(fasta_file, mapping_filename, to_modified=True)
logger.info("Generating FASTA file completed successfully : {}".format(datetime.datetime.utcnow()))
gtf_file = script_util.create_gtf_annotation(logger,ws_client,hs,services,params['ws_id'],annotation_id,gtf_obj_name,fasta_file,diffexp_dir,token)
m_expr_ids = e_sample['data']['mapped_expression_ids']
m_align_exp = []
labels = []
expressions = []
counter = 0
assembly_file = os.path.join(diffexp_dir,ASSEMBLY_GTF_FN)
list_file = open(assembly_file,'w')
for i in m_expr_ids:
for a_id ,e_id in i.items():
#print a_id + ":" + e_id
files = {}
a_obj,e_obj = ws_client.get_objects(
[{'ref' : a_id},{'ref': e_id}])
### Get the condition name, replicate_id , shock_id and shock_filename
condition = a_obj['data']['condition']
ws_gtf = params['genome_id']+"_GTF"
ret = script_util.if_obj_exists(None,ws_client,params['ws_id'],"KBaseRNASeq.GFFAnnotation",[ws_gtf])
print ret
if not ret is None:
logger.info("GFF Annotation Exist for Genome Annotation {0}.... Skipping step ".format(params['genome_id']))
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=services['shock_service_url'], shock_id=gtf_id,filename=gtf_name, directory=hisat2_dir,token=token)
gtf_file = os.path.join(hisat2_dir,gtf_name)
except Exception,e:
raise Exception( "Unable to download shock file, {0}".format(gtf_name))
else:
script_util.create_gtf_annotation(logger,ws_client,hs,services,params['ws_id'],annotation_id,params['genome_id'],fasta_file,hisat2_dir,token)
# Determine the num_threads provided by the user otherwise default the number of threads to 2
if('num_threads' in params and params['num_threads'] is not None):
num_threads = int(params['num_threads'])
else:
num_threads = 2
num_cores = mp.cpu_count()
logger.info("Number of available cores : {0}".format(num_cores))
b_tasks =[]
if sample_type == 'KBaseRNASeq.RNASeqSampleSet':
reads = sample['data']['sample_ids']
reads_type= sample['data']['Library_type']
r_label = sample['data']['condition']
num_samples = len(reads)
if num_cores != 1:
pool_size,num_threads=handler_util.optimize_parallel_run(num_samples,num_threads,num_cores)