def upload_alignment_set(self, alignment_items, alignmentset_name,
ws_name):
"""
Compiles and saves a set of alignment references (+ other stuff) into a
KBaseRNASeq.RNASeqAlignmentSet.
Returns the reference to the new alignment set.
alignment_items: [{
"ref": alignment_ref,
"label": condition label.
}]
# alignment_info = dict like this:
# {
# reads_ref: {
# "ref": alignment_ref
# }
# }
# reads_info = dict like this:
# {
# reads_ref: {
# "condition": "some condition"
# }
# }
# input_params = global input params to HISAT2, also has ws_name for the target workspace.
# alignmentset_name = name of final set object.
"""
print("Uploading completed alignment set")
alignment_set = {
"description":
"Alignments using HISAT2, v.{}".format(HISAT_VERSION),
"items": alignment_items
}
set_api = SetAPI(self.srv_wiz_url)
set_info = set_api.save_reads_alignment_set_v1({
"workspace": ws_name,
"output_object_name": alignmentset_name,
"data": alignment_set
})
return set_info["set_ref"]
def prepare_data(cls):
workspace_id = cls.dfu.ws_name_to_id(cls.wsName)
# upload genome object
genbank_file_name = 'minimal.gbff'
genbank_file_path = os.path.join(cls.scratch, genbank_file_name)
shutil.copy(os.path.join('data', genbank_file_name), genbank_file_path)
genome_object_name = 'test_Genome'
cls.genome_ref = cls.gfu.genbank_to_genome({
'file': {
'path': genbank_file_path
},
'workspace_name':
cls.wsName,
'genome_name':
genome_object_name
})['genome_ref']
print('TEST genome_ref=' + cls.genome_ref)
# upload assembly object
file_name = 'test.fna'
fasta_path = os.path.join(cls.scratch, file_name)
shutil.copy(os.path.join('data', file_name), fasta_path)
assembly_name = 'test_assembly'
cls.assembly_ref = cls.au.save_assembly_from_fasta({
'file': {
'path': fasta_path
},
'workspace_name':
cls.wsName,
'assembly_name':
assembly_name
})
print('TEST assembly_ref=' + cls.assembly_ref)
# upload reads object
reads_file_name = 'Sample1.fastq'
reads_file_path = os.path.join(cls.scratch, reads_file_name)
shutil.copy(os.path.join('data', reads_file_name), reads_file_path)
reads_object_name_1 = 'test_Reads_1'
cls.reads_ref_1 = cls.ru.upload_reads({
'fwd_file': reads_file_path,
'wsname': cls.wsName,
'sequencing_tech': 'Unknown',
'interleaved': 0,
'name': reads_object_name_1
})['obj_ref']
print(('TEST reads_ref_1=' + cls.reads_ref_1))
reads_object_name_2 = 'test_Reads_2'
cls.reads_ref_2 = cls.ru.upload_reads({
'fwd_file': reads_file_path,
'wsname': cls.wsName,
'sequencing_tech': 'Unknown',
'interleaved': 0,
'name': reads_object_name_2
})['obj_ref']
print('TEST reads_ref_2=' + cls.reads_ref_2)
# upload alignment object
alignment_file_name = 'accepted_hits.bam'
alignment_file_path = os.path.join(cls.scratch, alignment_file_name)
shutil.copy(os.path.join('data', alignment_file_name),
alignment_file_path)
alignment_object_name_1 = 'test_Alignment_1'
cls.condition_1 = 'test_condition_1'
cls.alignment_ref_1 = cls.rau.upload_alignment({
'file_path':
alignment_file_path,
'destination_ref':
cls.wsName + '/' + alignment_object_name_1,
'read_library_ref':
cls.reads_ref_1,
'condition':
cls.condition_1,
'library_type':
'single_end',
'assembly_or_genome_ref':
cls.genome_ref
})['obj_ref']
print('TEST alignment_ref_1=' + cls.alignment_ref_1)
alignment_object_name_2 = 'test_Alignment_2'
cls.condition_2 = 'test_condition_2'
cls.alignment_ref_2 = cls.rau.upload_alignment({
'file_path':
alignment_file_path,
'destination_ref':
cls.wsName + '/' + alignment_object_name_2,
'read_library_ref':
cls.reads_ref_2,
'condition':
cls.condition_2,
'library_type':
'single_end',
'assembly_or_genome_ref':
cls.genome_ref
})['obj_ref']
print('TEST alignment_ref_2=' + cls.alignment_ref_2)
alignment_object_name_3 = 'test_Alignment_3'
cls.condition_3 = 'test_condition_3'
cls.alignment_ref_3 = cls.rau.upload_alignment({
'file_path':
alignment_file_path,
'destination_ref':
cls.wsName + '/' + alignment_object_name_3,
'read_library_ref':
cls.reads_ref_2,
'condition':
cls.condition_3,
'library_type':
'single_end',
'assembly_or_genome_ref':
cls.assembly_ref
})['obj_ref']
print('TEST alignment_ref_3=' + cls.alignment_ref_3)
# upload sample_set object
sample_set_object_name = 'test_Sample_Set'
sample_set_data = {
'sampleset_id': sample_set_object_name,
'sample_ids': [cls.reads_ref_1, cls.reads_ref_2],
'sampleset_desc': 'test sampleset object',
'Library_type': 'SingleEnd',
'condition': [cls.condition_1, cls.condition_2],
'domain': 'Unknown',
'num_samples': 2,
'platform': 'Unknown'
}
save_object_params = {
'id':
workspace_id,
'objects': [{
'type': 'KBaseRNASeq.RNASeqSampleSet',
'data': sample_set_data,
'name': sample_set_object_name
}]
}
dfu_oi = cls.dfu.save_objects(save_object_params)[0]
cls.sample_set_ref = str(dfu_oi[6]) + '/' + str(dfu_oi[0]) + '/' + str(
dfu_oi[4])
print(('TEST sample_set_ref=' + cls.sample_set_ref))
# upload alignment_set object
object_type = 'KBaseRNASeq.RNASeqAlignmentSet'
alignment_set_object_name = 'test_Alignment_Set'
alignment_set_data = {
'genome_id':
cls.genome_ref,
'read_sample_ids': [reads_object_name_1, reads_object_name_2],
'mapped_rnaseq_alignments': [{
reads_object_name_1:
alignment_object_name_1
}, {
reads_object_name_2:
alignment_object_name_2
}],
'mapped_alignments_ids': [{
reads_object_name_1: cls.alignment_ref_1
}, {
reads_object_name_2: cls.alignment_ref_2
}],
'sample_alignments': [cls.alignment_ref_1, cls.alignment_ref_2],
'sampleset_id':
cls.sample_set_ref
}
save_object_params = {
'id':
workspace_id,
'objects': [{
'type': object_type,
'data': alignment_set_data,
'name': alignment_set_object_name
}]
}
dfu_oi = cls.dfu.save_objects(save_object_params)[0]
cls.old_alignment_set_ref = str(dfu_oi[6]) + '/' + str(
dfu_oi[0]) + '/' + str(dfu_oi[4])
print('TEST (legacy) KBaseRNASeq.alignment_set_ref=' +
cls.old_alignment_set_ref)
# Save the alignment set
items = [{
'ref': cls.alignment_ref_1,
'label': 'c1'
}, {
'ref': cls.alignment_ref_2,
'label': 'c2'
}]
alignment_set_data = {'description': '', 'items': items}
alignment_set_save_params = {
'data': alignment_set_data,
'workspace': cls.wsName,
'output_object_name': 'MyReadsAlignmentSet'
}
set_api = SetAPI(cls.srv_wiz_url)
save_result = set_api.save_reads_alignment_set_v1(
alignment_set_save_params)
cls.new_alignment_set_ref = save_result['set_ref']
print('TEST KBaseSet.alignment_set_ref=')
print(cls.new_alignment_set_ref)
def process_batch_result(self, batch_result, validated_params, reads,
input_set_info):
n_jobs = len(batch_result['results'])
n_success = 0
n_error = 0
ran_locally = 0
ran_njsw = 0
# reads alignment set items
items = []
objects_created = []
for k in range(0, len(batch_result['results'])):
job = batch_result['results'][k]
result_package = job['result_package']
if job['is_error']:
n_error += 1
else:
n_success += 1
print(result_package['result'])
print(result_package['result'][0])
print(result_package['result'][0]['output_info'])
output_info = result_package['result'][0]['output_info']
ra_ref = output_info['upload_results']['obj_ref']
# Note: could add a label to the alignment here?
items.append({'ref': ra_ref, 'label': reads[k]['condition']})
objects_created.append({'ref': ra_ref})
if result_package['run_context']['location'] == 'local':
ran_locally += 1
if result_package['run_context']['location'] == 'njsw':
ran_njsw += 1
# Save the alignment set
alignment_set_data = {'description': '', 'items': items}
alignment_set_save_params = {
'data':
alignment_set_data,
'workspace':
validated_params['output_workspace'],
'output_object_name':
str(input_set_info[1]) + validated_params['output_obj_name_suffix']
}
set_api = SetAPI(self.srv_wiz_url)
save_result = set_api.save_reads_alignment_set_v1(
alignment_set_save_params)
print('Saved ReadsAlignment=')
pprint(save_result)
objects_created.append({
'ref':
save_result['set_ref'],
'description':
'Set of all reads alignments generated'
})
set_name = save_result['set_info'][1]
# run qualimap
qualimap_report = self.qualimap.run_bamqc(
{'input_ref': save_result['set_ref']})
qc_result_zip_info = qualimap_report['qc_result_zip_info']
# create the report
report_text = 'Ran on SampleSet or ReadsSet.\n\n'
report_text = 'Created ReadsAlignmentSet: ' + str(set_name) + '\n\n'
report_text += 'Total ReadsLibraries = ' + str(n_jobs) + '\n'
report_text += ' Successful runs = ' + str(n_success) + '\n'
report_text += ' Failed runs = ' + str(n_error) + '\n'
report_text += ' Ran on main node = ' + str(ran_locally) + '\n'
report_text += ' Ran on remote worker = ' + str(ran_njsw) + '\n\n'
print('Report text=')
print(report_text)
kbr = KBaseReport(self.callback_url)
report_info = kbr.create_extended_report({
'message':
report_text,
'objects_created':
objects_created,
'report_object_name':
'kb_Bwa_' + str(uuid.uuid4()),
'direct_html_link_index':
0,
'html_links': [{
'shock_id': qc_result_zip_info['shock_id'],
'name': qc_result_zip_info['index_html_file_name'],
'label': qc_result_zip_info['name']
}],
'workspace_name':
validated_params['output_workspace']
})
result = {
'report_info': {
'report_name': report_info['name'],
'report_ref': report_info['ref']
}
}
result['batch_output_info'] = batch_result
return result