def convert(hca_data: dict):
use_spec = deepcopy(spec)
is_specimen = ('describedBy' in hca_data.get('biomaterial', {}).get(
'content', {}) and get_concrete_type(
hca_data['biomaterial']['content']['describedBy'])
== 'specimen_from_organism')
if 'releaseDate' not in hca_data.get('project', {}):
use_spec['releaseDate'] = ['biomaterial.submissionDate', format_date]
if is_specimen and 'organ' in hca_data['biomaterial']['content']:
use_spec['attributes']['Organ'] = [
'biomaterial.content.organ', dsp_ontology
]
converted_data = JsonMapper(hca_data).map(use_spec)
if is_specimen and 'organ_parts' in hca_data['biomaterial']['content']:
organ_parts = hca_data['biomaterial']['content']['organ_parts']
if len(organ_parts) == 1:
converted_data['attributes']['Organ Part'] = dsp_ontology(
organ_parts[0])
elif len(organ_parts) > 1:
for index, organ_part in enumerate(organ_parts):
converted_data['attributes'][
f'Organ Part - {index}'] = dsp_ontology(organ_parts[index])
return converted_data
def convert(self, entity: Entity, xml_spec: dict = None) -> Element:
if not xml_spec:
xml_spec = deepcopy(self.xml_spec)
self.add_alias(xml_spec, entity)
xml_map = JsonMapper(entity.attributes).map(xml_spec)
root = etree.Element(self.ena_type.upper())
self.add_children(parent=root, children=xml_map)
self.post_conversion(entity, root)
return root
def convert_sequencing_run(hca_data: dict):
mapper = JsonMapper(hca_data)
converted_data = mapper.map({
'$on':
'process',
# being overwritten 'alias': ['uuid.uuid', prefix_with, _sq_run_alias_prefix],
'title': ['content.process_core.process_name', default_to, ''],
'description':
['content.process_core.process_description', default_to, ''],
# being overwritten 'assayRefs': ['uuid.uuid', _sq_run_assay_ref]
})
converted_files = mapper.map({
'$on': 'files',
'name': ['content.file_core.file_name'],
'format': ['content.file_core.format'],
'uuid': ['uuid.uuid'],
'lane_index': ['content.lane_index'],
'read_index': ['content.read_index']
})
converted_data['attributes'] = _sq_run_file_attributes(converted_files)
converted_data['files'] = _sq_run_files(converted_files, hca_data)
return converted_data
def convert_project(hca_data: dict):
return JsonMapper(hca_data).map(project_spec)
def convert_study(hca_data: dict):
return JsonMapper(hca_data).map(study_spec)
def convert_sequencing_experiment(hca_data: dict):
return JsonMapper(hca_data).map(sq_experiment_spec)
def convert(hca_data: dict):
# added these for easier typing
sp = 'sequencing_protocol'
lp = 'library_preparation_protocol'
ib = 'input_biomaterial'
spec = {
'alias': [f'{sp}.content.protocol_core.protocol_id'],
'title': [f'{sp}.content.protocol_core.protocol_name'],
'description': [f'{sp}.content.protocol_core.protocol_description'],
'sampleUses':
json_array({'sampleRef': {
'alias': '{sampleAlias.placeholder}'
}}),
'studyRef':
json_object({'alias': '{studyAlias.placeholder}'}),
'attributes': {
'HCA Input Biomaterial UUID': [f'{ib}.uuid.uuid', dsp_attribute],
'HCA Library Preparation Protocol UUID':
[f'{lp}.uuid.uuid', dsp_attribute],
'HCA Process UUID': ['process.uuid.uuid', dsp_attribute],
'HCA Sequencing Protocol UUID': [f'{sp}.uuid.uuid', dsp_attribute],
'Input Biomaterial - Biomaterial Core - Biomaterial Id':
[f'{ib}.content.biomaterial_core.biomaterial_id', dsp_attribute],
'Input Biomaterial - Biomaterial Core - Ncbi Taxon Id - 0': [
f'{ib}.content.biomaterial_core.ncbi_taxon_id',
taxon_id_attribute
],
'Library Preparation Protocol - End Bias':
[f'{lp}.content.end_bias', dsp_attribute],
'Library Preparation Protocol - Library Construction Method':
[f'{lp}.content.library_construction_method', dsp_ontology],
'Library Preparation Protocol - Nucleic Acid Source':
[f'{lp}.content.nucleic_acid_source', dsp_attribute],
'Library Preparation Protocol - Primer':
[f'{lp}.content.primer', dsp_attribute],
'Library Preparation Protocol - Protocol Core - Protocol Id':
[f'{lp}.content.protocol_core.protocol_id', dsp_attribute],
'Library Preparation Protocol - Strand':
[f'{lp}.content.strand', dsp_attribute],
'Process - Process Core - Process Id':
['process.content.process_core.process_id', dsp_attribute],
'Sequencing Protocol - Paired End':
[f'{sp}.content.paired_end', dsp_attribute],
'Sequencing Protocol - Protocol Core - Protocol Id':
[f'{sp}.content.protocol_core.protocol_id', dsp_attribute],
'Sequencing Protocol - Sequencing Approach':
[f'{sp}.content.sequencing_approach', dsp_ontology],
'library_strategy': ['', fixed_dsp_attribute, 'OTHER'],
'library_source': [
'', fixed_dsp_attribute, 'TRANSCRIPTOMIC SINGLE CELL'
],
'library_selection': [f'{lp}.content.primer', map_primer],
'library_layout': [
f'{sp}.content.paired_end', library_layout_attribute
],
'library_name': [
f'{ib}.content.biomaterial_core.biomaterial_id', dsp_attribute
],
'instrument_model': [
f'{sp}.content.instrument_manufacturer_model.text',
instrument_model
],
'platform_type': ['', fixed_dsp_attribute, 'ILLUMINA'],
'design_description': ['', fixed_dsp_attribute, 'unspecified'],
# TODO if library_layout is SINGLE, this is "0"
'nominal_length': [f'{lp}.content.nominal_length', nominal_value],
'nominal_sdev': [f'{lp}.content.nominal_sdev', nominal_value]
}
}
return JsonMapper(hca_data).map(spec)
def convert_study(entity: Entity):
submission_payload = JsonMapper(entity.attributes).map(BIO_STUDY_SPEC)
return BioStudyConverter.__add_accession(entity, submission_payload)
def __add_attributes(sample: Sample, biomaterial: dict):
converted_attributes = JsonMapper(biomaterial).map(ATTRIBUTE_SPEC)
for name, value in converted_attributes.items():
sample.attributes.append(Attribute(name, value))
BioSamplesConverter.__add_project_attribute(sample)