"data": bowtie2_out,
"name": output_name
}]
})
except Exception, e:
#logger.exception("Failed to save alignment to workspace")
raise Exception("Failed to save alignment to workspace")
except Exception, e:
#logger.exception("Failed to create bowtie2 Alignment {0}".format(" ".join(traceback.print_exc())))
raise Exception("Failed to create bowtie2 Alignment {0}".format(
" ".join(traceback.print_exc())))
finally:
if os.path.exists(out_file_path): os.remove(out_file_path)
if os.path.exists(output_dir): shutil.rmtree(output_dir)
ret = script_util.if_obj_exists(None, ws_client, ws_id,
"KBaseRNASeq.RNASeqAlignment",
[output_name])
if not ret is None:
return (read_sample, output_name)
else:
return None
def _CallTophat(logger, services, ws_client, hs, ws_id, sample_type,
num_threads, read_sample, gtf_file, condition, directory,
bowtie2index_id, genome_id, sampleset_id, params, token):
print "Downloading Read Sample{0}".format(read_sample)
if not logger:
logger = create_logger(directory, "run_Tophat_" + read_sample)
try:
r_sample = ws_client.get_objects([{
'mapped_rnaseq_alignment' : { sample_id : s_alignment },
'tool_used' : self.tool_used,
'tool_version' : self.tool_version,
'tool_opts' : tool_opts,
'file' : handle
}
res= ws_client.save_objects(
{"workspace":ws_id,
"objects": [{
"type":"KBaseRNASeq.RNASeqExpression",
"data":es_obj,
"name":output_name}
]})[0]
expr_id = str(res[6]) + '/' + str(res[0]) + '/' + str(res[4])
except Exception, e:
logger.exception("".join(traceback.format_exc()))
raise Exception("Failed to upload the ExpressionSample: {0}".format(output_name))
except Exception,e:
logger.exception("".join(traceback.format_exc()))
raise Exception("Error executing stringtie {0},{1}".format(cufflinks_command,directory))
finally:
if os.path.exists(out_file_path): os.remove(out_file_path)
if os.path.exists(output_dir): shutil.rmtree(output_dir)
if os.path.exists(input_direc): shutil.rmtree(input_direc)
ret = script_util.if_obj_exists(None,ws_client,ws_id,"KBaseRNASeq.RNASeqExpression",[output_name])
if not ret is None:
return (alignment_name, output_name )
return None
"name": output_name
}]
})
except Exception, e:
#logger.exception("Failed to save alignment to workspace")
raise Exception("Failed to save alignment to workspace")
except Exception, e:
#logger.exception("Failed to create hisat2 Alignment {0}".format(" ".join(traceback.print_exc())))
raise Exception("Failed to create hisat2 Alignment {0}".format(
" ".join(traceback.print_exc())))
finally:
if os.path.exists(input_direc): shutil.rmtree(input_direc)
if os.path.exists(out_file_path): os.remove(out_file_path)
if os.path.exists(output_dir): shutil.rmtree(output_dir)
ret = script_util.if_obj_exists(None, ws_client, ws_id,
"KBaseRNASeq.RNASeqAlignment",
[output_name])
if not ret is None:
return (read_sample, output_name)
#else:
return None
def runMethod(logger, token, ws_client, hs, services, hisat2_dir, params):
try:
sample, annotation_name = ws_client.get_objects([{
'name':
params['sampleset_id'],
'workspace':
params['ws_id']
}, {
except Exception, e:
raise Exception("Failed to upload zipped output file".format(out_file_path))
#### Replace version with get_version command#####
logger.info("Preparing output object")
tophat_out = { "file" : tophat_handle ,"size" : os.path.getsize(out_file_path), "aligned_using" : "tophat" , "aligner_version" : "2.2.1" , 'library_type' : lib_type , 'condition' : condition ,'read_sample_id': read_sample, 'genome_id' : genome_id , 'bowtie2_index': self.bowtie2index_id, "alignment_stats" : stats_data }
if not sampleset_id is None: tophat_out['sampleset_id'] = sampleset_id
pprint(tophat_out)
try:
res= ws_client.save_objects(
{"workspace":ws_id,
"objects": [{
"type":"KBaseRNASeq.RNASeqAlignment",
"data":tophat_out,
"name":output_name}
]})
except Exception, e:
raise Exception(e)
#logger.exception("Failed to save alignment to workspace")
raise Exception("Failed to save alignment to workspace")
except Exception, e:
#logger.exception("Failed to create tophat Alignment {0}".format(" ".join(traceback.print_exc())))
raise Exception("Failed to create tophat Alignment {0}".format(" ".join(traceback.print_exc())))
finally:
if os.path.exists(out_file_path): os.remove(out_file_path)
if os.path.exists(output_dir): shutil.rmtree(output_dir)
ret = script_util.if_obj_exists(None,ws_client,ws_id,"KBaseRNASeq.RNASeqAlignment",[output_name])
if not ret is None:
return (read_sample,output_name)
else :
return None
## Get the Input object type and info #
e_sample_info = ws_client.get_object_info_new({"objects": [{'name': params['expressionset_id'], 'workspace': params['ws_id']}]})[0]
e_sample_type = e_sample_info[2].split('-')[0]
expressionset_id = str(e_sample_info[6]) + '/' + str(e_sample_info[0]) + '/' + str(e_sample_info[4])
alignmentset_id = e_sample['data']['alignmentSet_id']
sampleset_id = e_sample['data']['sampleset_id']
expression_ids = e_sample['data']['sample_expression_ids']
num_samples = len(expression_ids)
if num_samples < 2:
raise ValueError("Please ensure you have atleast 2 expressions to run diffExpCallforBallgown in Set mode")
### Check if the gtf file exists in the workspace. if exists download the file from that
annotation_id = e_sample['data']['genome_id']
logger.info("Check if the gtf file exists in the workspace".format(annotation_id))
annotation_name = ws_client.get_object_info([{"ref" :annotation_id}],includeMetadata=None)[0][1]
gtf_obj_name = annotation_name+"_GTF_Annotation"
ret = script_util.if_obj_exists(None,ws_client,params['ws_id'],"KBaseRNASeq.GFFAnnotation",[gtf_obj_name])
if not ret is None:
logger.info("GFF Annotation Exist for Genome Annotation {0}.... Skipping step ".format(annotation_name))
gtf_obj= ws_client.get_objects([{'name' : gtf_obj_name,'workspace' : params['ws_id']}])[0]
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()))
num_samples = len(expression_ids)
if num_samples < 2:
raise ValueError(
"Please ensure you have atleast 2 expressions to run diffExpCallforBallgown in Set mode"
)
### Check if the gtf file exists in the workspace. if exists download the file from that
annotation_id = e_sample['data']['genome_id']
logger.info(
"Check if the gtf file exists in the workspace".format(annotation_id))
annotation_name = ws_client.get_object_info([{
"ref": annotation_id
}],
includeMetadata=None)[0][1]
gtf_obj_name = annotation_name + "_GTF_Annotation"
ret = script_util.if_obj_exists(None, ws_client, params['ws_id'],
"KBaseRNASeq.GFFAnnotation",
[gtf_obj_name])
if not ret is None:
logger.info(
"GFF Annotation Exist for Genome Annotation {0}.... Skipping step "
.format(annotation_name))
gtf_obj = ws_client.get_objects([{
'name': gtf_obj_name,
'workspace': params['ws_id']
}])[0]
gtf_info = ws_client.get_object_info_new({
"objects": [{
'name': gtf_obj_name,
'workspace': params['ws_id']
}]
})[0]
"objects": [{
"type":"KBaseRNASeq.RNASeqAlignment",
"data":hisat2_out,
"name":output_name}
]})
except Exception, e:
#logger.exception("Failed to save alignment to workspace")
raise Exception("Failed to save alignment to workspace")
except Exception, e:
#logger.exception("Failed to create hisat2 Alignment {0}".format(" ".join(traceback.print_exc())))
raise Exception("Failed to create hisat2 Alignment {0}".format(" ".join(traceback.print_exc())))
finally:
if os.path.exists(input_direc): shutil.rmtree(input_direc)
if os.path.exists(out_file_path): os.remove(out_file_path)
if os.path.exists(output_dir): shutil.rmtree(output_dir)
ret = script_util.if_obj_exists(None,ws_client,ws_id,"KBaseRNASeq.RNASeqAlignment",[output_name])
if not ret is None:
return (read_sample,output_name)
#else:
return None
def runMethod(logger,token,ws_client,hs,services,hisat2_dir,params):
try:
sample,annotation_name = ws_client.get_objects(
[{ 'name' : params['sampleset_id'], 'workspace' : params['ws_id']},
{ 'name' : params['genome_id'], 'workspace' : params['ws_id']}])
except Exception,e:
logger.exception("".join(traceback.format_exc()))
raise ValueError(" Error Downloading objects from the workspace ")
### Get obejct IDs
sampleset_info,annotation_info = ws_client.get_object_info_new({"objects": [