"Unable to download shock file , {0} or {1}".format(
read1_name, read2_name))
try:
logger.info("Executing: bowtie2 {0}".format(bowtie2_cmd))
cmdline_output = script_util.runProgram(logger, "bowtie2",
bowtie2_cmd, None,
directory)
#print cmdline_output
except Exception, e:
#logger.exception("Failed to upload the index")
raise Exception("Failed to upload the index")
try:
#stats_obj_name = params['output_obj_name']+"_"+str(hex(uuid.getnode()))+"_AlignmentStats"
stats_data = {}
stats_data = script_util.extractAlignmentStatsInfo(
logger, "bowtie2", ws_client, ws_id, None,
cmdline_output['stderr'], None)
bam_file = os.path.join(output_dir, "accepted_hits_unsorted.bam")
logger.info("Executing: sam_to_bam {0}".format(bam_file))
sam_to_bam = "view -bS -o {0} {1}".format(bam_file, out_file)
script_util.runProgram(logger, "samtools", sam_to_bam, None,
directory)
final_bam_prefix = os.path.join(output_dir, "accepted_hits")
logger.info("Executing: Sorting bam file {0}".format(bam_file))
sort_bam_cmd = "sort {0} {1}".format(bam_file, final_bam_prefix)
script_util.runProgram(logger, "samtools", sort_bam_cmd, None,
directory)
except Exception, e:
#logger.exception("Error Running the bowtie2 command {0},{1} {2}".format(bowtie2_cmd,directory," ".join(traceback.print_exc())))
raise Exception(
"Error Running the bowtie2 command {0},{1} {2}".format(
class HiSat2(ExecutionBase):
def __init__(self, logger, directory, urls, max_cores):
pprint(self.__class__)
super(HiSat2, self).__init__(logger, directory, urls, max_cores)
# user defined shared variables across methods
#self.sample = None
#self.sampleset_info = None
self.num_threads = None
def runEach(self, task_params):
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']
read_sample = task_params['job_id']
condition = task_params['label']
directory = task_params['hisat2_dir']
ws_id = task_params['ws_id']
genome_id = task_params['annotation_id']
sampleset_id = task_params['sampleset_id']
print "Downloading Read Sample{0}".format(read_sample)
logger.info("Downloading Read Sample{0}".format(read_sample))
try:
#r_sample = ws_client.get_objects(
# [{ 'name' : read_sample, 'workspace' : ws_id}])[0]
#r_sample_info = ws_client.get_object_info_new({"objects": [{'name': read_sample, 'workspace': ws_id}]})[0]
#sample_type = r_sample_info[2].split('-')[0]
r_sample = script_util.ws_get_obj(self.logger, ws_client, ws_id,
read_sample)[0]
sample_type = script_util.ws_get_type_name(self.logger, ws_client,
ws_id, read_sample)
sample_name = script_util.ws_get_obj_name4file(
self.logger, ws_client, ws_id, read_sample)
input_direc = os.path.join(
directory,
sample_name.split('.')[0] + "_hisat2_input")
if not os.path.exists(input_direc): os.mkdir(input_direc)
output_name = sample_name.split('.')[0] + "_hisat2_alignment"
output_dir = os.path.join(directory, output_name)
if not os.path.exists(output_dir): os.mkdir(output_dir)
print directory
base = handler_util.get_file_with_suffix(directory, ".1.ht2")
print base
hisat2_base = os.path.join(directory, base)
### Adding advanced options to Bowtie2Call
hisat2_cmd = ''
hisat2_cmd += (' -p {0}'.format(self.num_threads))
if ('quality_score' in params
and params['quality_score'] is not None):
hisat2_cmd += (' --' + params['quality_score'])
if ('alignment_type' in params
and params['alignment_type'] is not None):
hisat2_cmd += (' --' + params['alignment_type'])
if ('trim5' in params and params['trim5'] is not None):
hisat2_cmd += (' --trim5 ' + str(params['trim5']))
if ('trim3' in params and params['trim3'] is not None):
hisat2_cmd += (' --trim3 ' + str(params['trim3']))
if ('np' in params and params['np'] is not None):
hisat2_cmd += (' --np ' + str(params['np']))
if ('minins' in params and params['minins'] is not None):
hisat2_cmd += (' --minins ' + str(params['minins']))
if ('maxins' in params and params['maxins'] is not None):
hisat2_cmd += (' --maxins ' + str(params['maxins']))
#if('orientation' in params and params['orientation'] is not None): hisat2_cmd += ( ' --'+params['orientation'])
if ('min_intron_length' in params
and params['min_intron_length'] is not None):
hisat2_cmd += (' --min-intronlen ' +
str(params['min_intron_length']))
if ('max_intron_length' in params
and params['max_intron_length'] is not None):
hisat2_cmd += (' --max-intronlen ' +
str(params['max_intron_length']))
if ('no_spliced_alignment' in params
and params['no_spliced_alignment'] != 0):
hisat2_cmd += (' --no-spliced-alignment')
if ('transcriptome_mapping_only' in params
and params['transcriptome_mapping_only'] != 0):
hisat2_cmd += (' --transcriptome-mapping-only')
if ('tailor_alignments' in params
and params['tailor_alignments'] is not None):
hisat2_cmd += (' --' + params['tailor_alignments'])
out_file = output_dir + "/accepted_hits.sam"
####
try:
sample_ref = script_util.ws_get_ref(self.logger, ws_client,
ws_id, read_sample)
ds = script_util.ru_reads_download(self.logger, sample_ref,
input_direc, token)
self.logger.info(ds)
except Exception, e:
self.logger.exception(e)
raise Exception(
"Unable to download reads file , {0}".format(read_sample))
if sample_type == 'KBaseAssembly.SingleEndLibrary' or sample_type == 'KBaseFile.SingleEndLibrary':
lib_type = 'SingleEnd'
hisat2_cmd += " -U {0} -x {1} -S {2}".format(
ds['fwd'], hisat2_base, out_file)
if sample_type == 'KBaseAssembly.PairedEndLibrary' or sample_type == 'KBaseFile.PairedEndLibrary':
lib_type = 'PairedEnd'
if sample_type == 'KBaseAssembly.PairedEndLibrary':
if ('orientation' in params
and params['orientation'] is not None):
hisat2_cmd += (' --' + params['orientation'])
else:
# TODO: the following can be read from PEL object
if ('orientation' in params
and params['orientation'] is not None):
hisat2_cmd += (' --' + params['orientation'])
hisat2_cmd += " -1 {0} -2 {1} -x {2} -S {3}".format(
ds['fwd'], ds['rev'], hisat2_base, out_file)
#if sample_type == 'KBaseAssembly.SingleEndLibrary' or sample_type == 'KBaseFile.SingleEndLibrary':
# lib_type = 'SingleEnd'
# if sample_type == 'KBaseAssembly.SingleEndLibrary':
# read_id = r_sample['data']['handle']['id']
# read_name = r_sample['data']['handle']['file_name']
# else:
# read_id = r_sample['data']['lib']['file']['id']
# read_name = r_sample['data']['lib']['file']['file_name']
# try:
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read_id,filename=read_name, directory=input_direc,token=token)
# hisat2_cmd += " -U {0} -x {1} -S {2}".format(os.path.join(input_direc,read_name),hisat2_base,out_file)
# except Exception,e:
# self.logger.exception(e)
# raise Exception( "Unable to download shock file , {0}".format(read_name))
#if sample_type == 'KBaseAssembly.PairedEndLibrary' or sample_type == 'KBaseFile.PairedEndLibrary':
# lib_type = 'PairedEnd'
# if sample_type == 'KBaseAssembly.PairedEndLibrary':
# if('orientation' in params and params['orientation'] is not None): hisat2_cmd += ( ' --'+params['orientation'])
# read1_id = r_sample['data']['handle_1']['id']
# read1_name = r_sample['data']['handle_1']['file_name']
# read2_id = r_sample['data']['handle_2']['id']
# read2_name = r_sample['data']['handle_2']['file_name']
# else:
# # TODO: the following can be read from PEL object
# if('orientation' in params and params['orientation'] is not None): hisat2_cmd += ( ' --'+params['orientation'])
# read1_id = r_sample['data']['lib1']['file']['id']
# read1_name = r_sample['data']['lib1']['file']['file_name']
# read2_id = r_sample['data']['lib2']['file']['id']
# read2_name = r_sample['data']['lib2']['file']['file_name']
# try:
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read1_id,filename=read1_name, directory=input_direc,token=token)
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read2_id,filename=read2_name, directory=input_direc,token=token)
# hisat2_cmd += " -1 {0} -2 {1} -x {2} -S {3}".format(os.path.join(input_direc,read1_name),os.path.join(input_direc,read2_name),hisat2_base,out_file)
# except Exception,e:
# logger.exception(e)
# raise Exception( "Unable to download shock file , {0} or {1}".format(read1_name,read2_name))
try:
self.logger.info("Executing: hisat2 {0}".format(hisat2_cmd))
cmdline_output = script_util.runProgram(
self.logger, "hisat2", hisat2_cmd, None, directory)
except Exception, e:
logger.exception(e)
raise Exception("Failed to run command {0}".format(hisat2_cmd))
try:
stats_data = {}
stats_data = script_util.extractAlignmentStatsInfo(
self.logger, "bowtie2", ws_client, ws_id, None,
cmdline_output['stderr'], None)
bam_file = os.path.join(output_dir,
"accepted_hits_unsorted.bam")
logger.info("Executing: sam_to_bam {0}".format(bam_file))
sam_to_bam = "view -bS -o {0} {1}".format(bam_file, out_file)
script_util.runProgram(self.logger, "samtools", sam_to_bam,
None, directory)
final_bam_prefix = os.path.join(output_dir, "accepted_hits")
logger.info(
"Executing: Sorting bam file {0}".format(bam_file))
sort_bam_cmd = "sort {0} {1}".format(bam_file,
final_bam_prefix)
script_util.runProgram(self.logger, "samtools", sort_bam_cmd,
None, directory)
except Exception, e:
logger.exception(e)
raise Exception(
"Error Running the hisat2 command {0},{1} {2}".format(
hisat2_cmd, directory,
" ".join(traceback.print_exc())))
except Exception,e:
raise Exception( "Unable to download shock file , {0} or {1}".format(read1_name,read2_name))
try:
self.logger.info("Executing: tophat {0}".format(tophat_cmd))
cmdline_output, cmd_err = script_util.runProgram(self.logger,"tophat",tophat_cmd,None,directory)
except Exception,e:
raise Exception("Failed to run command {0}\n{1}\n{2}".format(tophat_cmd,cmdline_output,cmd_err))
try:
bam_file = output_dir+"/accepted_hits.bam"
align_stats_cmd="flagstat {0}".format(bam_file)
stats = script_util.runProgram(logger,"samtools",align_stats_cmd,None,directory)
#print stats
stats_data = {}
# Pass it to the stats['result']
#stats_obj_name = params['output_obj_name']+"_"+str(hex(uuid.getnode()))+"_AlignmentStats"
stats_data =script_util.extractAlignmentStatsInfo(logger,"samtools",ws_client,ws_id,None,stats['result'],None)
except Exception , e :
raise Exception("Failed to create RNASeqAlignmentStats: {0}".format(bam_file))
# Zip tophat folder
out_file_path = os.path.join(directory,"%s.zip" % output_name)
try:
logger.info("Zipping the output files".format(out_file_path))
script_util.zip_files(logger, output_dir,out_file_path)
except Exception, e:
raise Exception("Failed to compress the index: {0}".format(out_file_path))
## Upload the file using handle service
try:
tophat_handle = hs.upload(out_file_path)
except Exception, e:
raise Exception("Failed to upload zipped output file".format(out_file_path))
#### Replace version with get_version command#####
)
except Exception, e:
# logger.Exception( "Unable to download shock file , {0} or {1}".format(read1_name,read2_name))
raise Exception("Unable to download shock file , {0} or {1}".format(read1_name, read2_name))
try:
logger.info("Executing: bowtie2 {0}".format(bowtie2_cmd))
cmdline_output = script_util.runProgram(logger, "bowtie2", bowtie2_cmd, None, directory)
# print cmdline_output
except Exception, e:
# logger.exception("Failed to upload the index")
raise Exception("Failed to upload the index")
try:
# stats_obj_name = params['output_obj_name']+"_"+str(hex(uuid.getnode()))+"_AlignmentStats"
stats_data = {}
stats_data = script_util.extractAlignmentStatsInfo(
logger, "bowtie2", ws_client, ws_id, None, cmdline_output["stderr"], None
)
bam_file = os.path.join(output_dir, "accepted_hits_unsorted.bam")
logger.info("Executing: sam_to_bam {0}".format(bam_file))
sam_to_bam = "view -bS -o {0} {1}".format(bam_file, out_file)
script_util.runProgram(logger, "samtools", sam_to_bam, None, directory)
final_bam_prefix = os.path.join(output_dir, "accepted_hits")
logger.info("Executing: Sorting bam file {0}".format(bam_file))
sort_bam_cmd = "sort {0} {1}".format(bam_file, final_bam_prefix)
script_util.runProgram(logger, "samtools", sort_bam_cmd, None, directory)
except Exception, e:
# logger.exception("Error Running the bowtie2 command {0},{1} {2}".format(bowtie2_cmd,directory," ".join(traceback.print_exc())))
raise Exception(
"Error Running the bowtie2 command {0},{1} {2}".format(
bowtie2_cmd, directory, " ".join(traceback.print_exc())
)
read2_id = r_sample['data']['handle_2']['id']
read2_name = r_sample['data']['handle_2']['file_name']
try:
script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read1_id,filename=read1_name, directory=input_direc,token=token)
script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read2_id,filename=read2_name, directory=input_direc,token=token)
hisat2_cmd += " -1 {0} -2 {1} -x {2} -S {3}".format(os.path.join(input_direc,read1_name),os.path.join(output_dir,read2_name),hisat2_base,out_file)
except Exception,e:
raise Exception( "Unable to download shock file , {0} or {1}".format(read1_name,read2_name))
try:
self.logger.info("Executing: hisat2 {0}".format(hisat2_cmd))
cmdline_output = script_util.runProgram(self.logger,"hisat2",hisat2_cmd,None,directory)
except Exception,e:
raise Exception("Failed to run command {0}".format(hisat2_cmd))
try:
stats_data = {}
stats_data = script_util.extractAlignmentStatsInfo(self.logger,"bowtie2",ws_client,ws_id,None,cmdline_output['stderr'],None)
bam_file = os.path.join(output_dir,"accepted_hits_unsorted.bam")
logger.info("Executing: sam_to_bam {0}".format(bam_file))
sam_to_bam = "view -bS -o {0} {1}".format(bam_file,out_file)
script_util.runProgram(self.logger,"samtools",sam_to_bam,None,directory)
final_bam_prefix = os.path.join(output_dir,"accepted_hits")
logger.info("Executing: Sorting bam file {0}".format(bam_file))
sort_bam_cmd = "sort {0} {1}".format(bam_file,final_bam_prefix)
script_util.runProgram(self.logger,"samtools",sort_bam_cmd,None,directory)
except Exception,e:
raise Exception("Error Running the hisat2 command {0},{1} {2}".format(hisat2_cmd,directory," ".join(traceback.print_exc())))
# Zip tophat folder
out_file_path = os.path.join(directory,"%s.zip" % output_name)
try:
logger.info("Zipping the output files".format(out_file_path))
class Tophat(ExecutionBase):
def __init__(self, logger, directory, urls, max_cores):
pprint(self.__class__)
super(Tophat, self).__init__(logger, directory, urls, max_cores)
# user defined shared variables across methods
#self.sample = None
#self.sampleset_info = None
self.num_threads = None
def runEach(self, task_params):
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']
read_sample = task_params['job_id']
condition = task_params['label']
directory = task_params['tophat_dir']
ws_id = task_params['ws_id']
genome_id = task_params['annotation_id']
sampleset_id = task_params['sampleset_id']
gtf_file = task_params['gtf_file']
print "Downloading Read Sample{0}".format(read_sample)
logger.info("Downloading Read Sample{0}".format(read_sample))
try:
#r_sample = ws_client.get_objects(
# [{ 'name' : read_sample, 'workspace' : ws_id}])[0]
r_sample = script_util.ws_get_obj(logger, ws_client, ws_id,
read_sample)[0]
#r_sample_info = ws_client.get_object_info_new({"objects": [{'name': read_sample, 'workspace': ws_id}]})[0]
#sample_type = r_sample_info[2].split('-')[0]
sample_type = script_util.ws_get_type_name(logger, ws_client,
ws_id, read_sample)
sample_name = script_util.ws_get_obj_name4file(
self.logger, ws_client, ws_id, read_sample)
output_name = sample_name.split('.')[0] + "_tophat_alignment"
output_dir = os.path.join(directory, output_name)
#if not os.path.exists(output_dir): os.makedirs(output_dir)
#out_file = output_dir +"/accepted_hits.sam"
bowtie2_base = os.path.join(
directory,
handler_util.get_file_with_suffix(directory, ".rev.1.bt2"))
### Adding advanced options to Bowtie2Call
tophat_cmd = (' -p ' + str(self.num_threads))
if ('max_intron_length' in params
and params['max_intron_length'] is not None):
tophat_cmd += (' -I ' + str(params['max_intron_length']))
if ('min_intron_length' in params
and params['min_intron_length'] is not None):
tophat_cmd += (' -i ' + str(params['min_intron_length']))
if ('min_anchor_length' in params
and params['min_anchor_length'] is not None):
tophat_cmd += (' -a ' + str(params['min_anchor_length']))
if ('read_edit_dist' in params
and params['read_edit_dist'] is not None):
tophat_cmd += (' --read-edit-dist ' +
str(params['read_edit_dist']))
if ('read_gap_length' in params
and params['read_gap_length'] is not None):
tophat_cmd += (' --read-gap-length ' +
str(params['read_gap_length']))
if ('read_mismatches' in params
and params['read_mismatches'] is not None):
tophat_cmd += (' -N ' + str(params['read_mismatches']))
if ('library_type' in params
and params['library_type'] is not None):
tophat_cmd += (' --library-type ' + params['library_type'])
if ('report_secondary_alignments' in params
and int(params['report_secondary_alignments']) == 1):
tophat_cmd += ' --report-secondary-alignments'
if ('no_coverage_search' in params
and int(params['no_coverage_search']) == 1):
tophat_cmd += ' --no-coverage-search'
if ('preset_options' in params
and params['preset_options'] is not None):
tophat_cmd += ' --' + params['preset_options']
#out_file = output_dir +"/accepted_hits.sam"
try:
sample_ref = script_util.ws_get_ref(self.logger, ws_client,
ws_id, read_sample)
ds = script_util.ru_reads_download(self.logger, sample_ref,
directory, token)
except Exception, e:
self.logger.exception(e)
raise Exception(
"Unable to download reads file , {0}".format(read_sample))
if sample_type == 'KBaseAssembly.SingleEndLibrary' or sample_type == 'KBaseFile.SingleEndLibrary':
lib_type = 'SingleEnd'
tophat_cmd += ' -o {0} -G {1} {2} {3}'.format(
output_dir, gtf_file, bowtie2_base, ds['fwd'])
if sample_type == 'KBaseAssembly.PairedEndLibrary' or sample_type == 'KBaseFile.PairedEndLibrary':
lib_type = 'PairedEnd'
if sample_type == 'KBaseAssembly.PairedEndLibrary':
if ('orientation' in params
and params['orientation'] is not None):
tophat_cmd += (' --' + params['orientation'])
else:
# TODO: the following can be read from PEL object
if ('orientation' in params
and params['orientation'] is not None):
tophat_cmd += (' --' + params['orientation'])
tophat_cmd += ' -o {0} -G {1} {2} {3} {4}'.format(
output_dir, gtf_file, bowtie2_base, ds['fwd'], ds['rev'])
# if sample_type == 'KBaseAssembly.SingleEndLibrary' or sample_type == 'KBaseFile.SingleEndLibrary':
# lib_type = 'SingleEnd'
# if sample_type == 'KBaseAssembly.SingleEndLibrary':
# read_id = r_sample['data']['handle']['id']
# read_name = r_sample['data']['handle']['file_name']
# else:
# read_id = r_sample['data']['lib']['file']['id']
# read_name = r_sample['data']['lib']['file']['file_name']
# try:
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read_id,filename=read_name, directory=directory,token=token)
# tophat_cmd += ' -o {0} -G {1} {2} {3}'.format(output_dir,gtf_file,bowtie2_base,os.path.join(directory,read_name))
# except Exception,e:
# self.logger.exception(e)
# raise Exception( "Unable to download shock file , {0}".format(read_name))
# if sample_type == 'KBaseAssembly.PairedEndLibrary' or sample_type == 'KBaseFile.PairedEndLibrary':
# lib_type = 'PairedEnd'
# if sample_type == 'KBaseAssembly.PairedEndLibrary':
# if('orientation' in params and params['orientation'] is not None): tophat_cmd += ( ' --'+params['orientation'])
# read1_id = r_sample['data']['handle_1']['id']
# read1_name = r_sample['data']['handle_1']['file_name']
# read2_id = r_sample['data']['handle_2']['id']
# read2_name = r_sample['data']['handle_2']['file_name']
# else:
# # TODO: the following can be read from PEL object
# if('orientation' in params and params['orientation'] is not None): tophat_cmd += ( ' --'+params['orientation'])
# read1_id = r_sample['data']['lib1']['file']['id']
# read1_name = r_sample['data']['lib1']['file']['file_name']
# read2_id = r_sample['data']['lib2']['file']['id']
# read2_name = r_sample['data']['lib2']['file']['file_name']
# try:
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read1_id,filename=read1_name, directory=directory,token=token)
# script_util.download_file_from_shock(self.logger, shock_service_url=self.urls['shock_service_url'], shock_id=read2_id,filename=read2_name, directory=directory,token=token)
# tophat_cmd += ' -o {0} -G {1} {2} {3} {4}'.format(output_dir,gtf_file,bowtie2_base,os.path.join(directory,read1_name),os.path.join(directory,read2_name))
# except Exception,e:
# raise Exception( "Unable to download shock file , {0} or {1}".format(read1_name,read2_name))
try:
self.logger.info("Executing: tophat {0}".format(tophat_cmd))
cmdline_output, cmd_err = script_util.runProgram(
self.logger, "tophat", tophat_cmd, None, directory)
except Exception, e:
raise Exception("Failed to run command {0}\n{1}\n{2}".format(
tophat_cmd, cmdline_output, cmd_err))
try:
bam_file = output_dir + "/accepted_hits.bam"
align_stats_cmd = "flagstat {0}".format(bam_file)
stats = script_util.runProgram(logger, "samtools",
align_stats_cmd, None,
directory)
#print stats
stats_data = {}
# Pass it to the stats['result']
#stats_obj_name = params['output_obj_name']+"_"+str(hex(uuid.getnode()))+"_AlignmentStats"
stats_data = script_util.extractAlignmentStatsInfo(
logger, "samtools", ws_client, ws_id, None,
stats['result'], None)
except Exception, e:
raise Exception(
"Failed to create RNASeqAlignmentStats: {0}".format(
bam_file))
