try:
a_sample = ws_client.get_objects(
[{'name' : params['alignmentset_id'],'workspace' : params['ws_id']}])[0]
except Exception,e:
logger.exception("".join(traceback.format_exc()))
raise Exception("Error Downloading objects from the workspace ")
## Get the Input object type ##
a_sample_info = ws_client.get_object_info_new({"objects": [{'name': params['alignmentset_id'], 'workspace': params['ws_id']}]})[0]
a_sample_type = a_sample_info[2].split('-')[0]
alignmentset_id = str(a_sample_info[6]) + '/' + str(a_sample_info[0]) + '/' + str(a_sample_info[4])
## Check if the Alignment objects exist in the same workspace
logger.info("Check if the Alignment objects do exist in the current workspace")
if a_sample_type == 'KBaseRNASeq.RNASeqAlignmentSet':
a_names = list(numpy.array([ i.values() for i in a_sample['data']['mapped_rnaseq_alignments']]).flatten())
a_type = 'KBaseRNASeq.RNASeqAlignment'
e_ws_objs = script_util.if_ws_obj_exists(None,ws_client,params['ws_id'],a_type,a_names)
missing_objs = [i for i in a_names if not i in e_ws_objs]
if len(e_ws_objs) != len(a_names):
raise ValueError('Missing Alignment objects {0} in the {1}. please copy them and run this method'.format(",".join(missing_objs),params['ws_id']))
### Check if the gtf file exists in the workspace. if exists download the file from that
annotation_id = a_sample['data']['genome_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']
### Get the workspace object ids for the objects ###
sampleset_id = str(sampleset_info[6]) + '/' + str(
sampleset_info[0]) + '/' + str(sampleset_info[4])
annotation_id = str(annotation_info[6]) + '/' + str(
annotation_info[0]) + '/' + str(annotation_info[4])
sample_type = sampleset_info[2].split('-')[0]
### Check if the Library objects exist in the same workspace
logger.info(
"Check if the Library objects do exist in the current workspace")
if sample_type == 'KBaseRNASeq.RNASeqSampleSet':
reads = sample['data']['sample_ids']
reads_type = sample['data']['Library_type']
if reads_type == 'PairedEnd': r_type = 'KBaseAssembly.PairedEndLibrary'
else: r_type = 'KBaseAssembly.SingleEndLibrary'
e_ws_objs = script_util.if_ws_obj_exists(None, ws_client,
params['ws_id'], r_type,
reads)
missing_objs = [i for i in reads if not i in e_ws_objs]
if len(e_ws_objs) != len(reads):
raise Exception(
'Missing Library objects {0} in the {1}. please copy them and run this method'
.format(",".join(missing_objs), params['ws_id']))
### Build Hisat2 index
fasta_file = script_util.generate_fasta(logger, services, token,
annotation_id, hisat2_dir,
params['genome_id'])
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,
sampleset_info,annotation_info = ws_client.get_object_info_new({"objects": [
{'name': params['sampleset_id'], 'workspace': params['ws_id']},
{'name': params['genome_id'], 'workspace': params['ws_id']}
]})
### Get the workspace object ids for the objects ###
sampleset_id = str(sampleset_info[6]) + '/' + str(sampleset_info[0]) + '/' + str(sampleset_info[4])
annotation_id = str(annotation_info[6]) + '/' + str(annotation_info[0]) + '/' + str(annotation_info[4])
sample_type = sampleset_info[2].split('-')[0]
### Check if the Library objects exist in the same workspace
logger.info("Check if the Library objects do exist in the current workspace")
if sample_type == 'KBaseRNASeq.RNASeqSampleSet':
reads = sample['data']['sample_ids']
reads_type= sample['data']['Library_type']
if reads_type == 'PairedEnd': r_type = 'KBaseAssembly.PairedEndLibrary'
else: r_type = 'KBaseAssembly.SingleEndLibrary'
e_ws_objs = script_util.if_ws_obj_exists(None,ws_client,params['ws_id'],r_type,reads)
missing_objs = [i for i in reads if not i in e_ws_objs]
if len(e_ws_objs) != len(reads):
raise Exception('Missing Library objects {0} in the {1}. please copy them and run this method'.format(",".join(missing_objs),params['ws_id']))
### Build Hisat2 index
fasta_file = script_util.generate_fasta(logger,services,token,annotation_id,hisat2_dir,params['genome_id'])
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()))
hisat2base =os.path.join(hisat2_dir,handler_util.get_file_with_suffix(hisat2_dir,".fasta"))
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)
