class Treatment(Item):
item_type = 'treatment'
schema = load_schema('encoded:schemas/treatment.json')
embedded = []
set_status_up = [
'biosamples_used',
'antibodies_used',
]
set_status_down = []
class Project(FileSet, CalculatedFileSetAssay, CalculatedFileSetBiosample, CalculatedBiosampleSlims, CalculatedBiosampleSynonyms, CalculatedAssaySynonyms):
item_type = 'project'
schema = load_schema('encoded:schemas/project.json')
embedded = FileSet.embedded + [
'files.dataset',
'files.replicate.library',
'files.replicate.experiment.target',
'organism'
]
class HiglassViewConfig(Item):
"""
Item type which contains a `view_config` property and other metadata.
"""
item_type = 'higlass_view_config'
schema = load_schema('encoded:schemas/higlass_view_config.json')
embedded_list = []
name_key = 'name'
class PublicationData(FileSet, CalculatedFileSetBiosample,
CalculatedFileSetAssay, CalculatedBiosampleSlims,
CalculatedBiosampleSynonyms, CalculatedAssaySynonyms):
item_type = 'publication_data'
schema = load_schema('encoded:schemas/publication_data.json')
embedded = [
'organism', 'submitted_by', 'lab', 'award.pi.lab', 'documents.lab',
'documents.award', 'documents.submitted_by', 'references'
]
class Bioproject(BiofileSet, CalculatedFileSetAssay,
CalculatedFileSetBiosample, CalculatedAssaySynonyms):
item_type = 'bioproject'
schema = load_schema('encoded:schemas/bioproject.json')
embedded = BiofileSet.embedded + [
'files.biodataset', 'files.bioreplicate.biolibrary',
'files.bioreplicate', 'files.bioreplicate.bioexperiment', 'award',
'lab'
]
class User(Item):
"""The user class."""
item_type = 'user'
schema = load_schema('encoded:schemas/user.json')
embedded_list = [
'project_roles.role',
'project_roles.project.name',
'project_roles.project.description',
'project_roles.project.pi',
]
# TODO (C4-332): consolidate all acls into once place
STATUS_ACL = {
'current': ONLY_OWNER_VIEW_PROFILE_ACL,
'deleted': DELETED_USER_ACL,
'revoked': DELETED_USER_ACL,
'inactive': ONLY_OWNER_VIEW_PROFILE_ACL,
}
@calculated_property(schema={
"title": "Title",
"type": "string",
})
def title(self, first_name, last_name):
"""return first and last name."""
title = u'{} {}'.format(first_name, last_name)
return title
@calculated_property(
schema={
"title": "Display Title",
"description": "A calculated title for every object in 4DN",
"type": "string"
})
def display_title(self, first_name, last_name):
return self.title(first_name, last_name)
@calculated_property(
schema={
"title": "Contact Email",
"description":
"E-Mail address by which this person should be contacted.",
"type": "string",
"format": "email"
})
def contact_email(self, email, preferred_email=None):
"""Returns `email` if `preferred_email` is not defined."""
if preferred_email:
return preferred_email
else:
return email
def __ac_local_roles__(self):
"""return the owner user."""
owner = 'userid.%s' % self.uuid
return {owner: 'role.owner'}
class Library(Item):
item_type = 'library'
schema = load_schema('encoded:schemas/library.json')
name_key = 'accession'
embedded = [
'biosample',
'biosample.donor',
'biosample.donor.organism',
]
class Bioseries(Biodataset, CalculatedSeriesAssay, CalculatedSeriesBiosample,
CalculatedSeriesTarget, CalculatedSeriesTreatment,
CalculatedAssaySynonyms):
item_type = 'bioseries'
base_types = ['Bioseries'] + Biodataset.base_types
schema = load_schema('encoded:schemas/bioseries.json')
embedded = Biodataset.embedded + [
'references', 'related_datasets.biospecimen', 'related_datasets.files',
'related_datasets.lab', 'related_datasets.submitted_by',
'related_datasets.award.pi.lab',
'related_datasets.bioreplicate.biolibrary',
'related_datasets.bioreplicate.biolibrary.biospecimen.submitted_by',
'related_datasets.bioreplicate.biolibrary.biospecimen',
'related_datasets.bioreplicate.biolibrary.biospecimen.donor',
'related_datasets.possible_controls',
'related_datasets.possible_controls.lab',
'related_datasets.references', 'files.platform', 'files.lab',
'files.bioreplicate.biolibrary.biospecimen',
'files.biolibrary.biospecimen', 'award', 'lab'
]
@calculated_property(
schema={
"title": "Revoked datasets",
"type": "array",
"items": {
"type": "string",
"linkTo": "Biofile",
},
})
def revoked_datasets(self, request, related_datasets):
return [
path for path in related_datasets
if item_is_revoked(request, path)
]
@calculated_property(define=True,
schema={
"title": "Genome assembly",
"type": "array",
"items": {
"type": "string",
},
})
def assembly(self, request, original_files, related_datasets, status):
combined_assembly = set()
for assembly_from_original_files in calculate_assembly(
request, original_files, status):
combined_assembly.add(assembly_from_original_files)
for biodataset in related_datasets:
properties = request.embed(biodataset, '@@object')
if properties['status'] not in ('deleted', 'replaced'):
for assembly_from_related_dataset in properties['assembly']:
combined_assembly.add(assembly_from_related_dataset)
return list(combined_assembly)
class Page(Item):
"""Links to StaticSections"""
item_type = 'page'
schema = load_schema('encoded:schemas/page.json')
embedded_list = ['content.*']
# STATUS_ACL = StaticSection.STATUS_ACL
class Collection(Item.Collection):
pass
class Tvp_a2(Item):
item_type = "tvp_a2"
schema = load_schema("encoded:schemas/tvp_a2.json")
embedded = [
]
rev = {
}
audit_inherit = []
set_status_up = []
set_status_down = []
class AnalysisStepVersion(Item):
item_type = 'analysis_step_version'
schema = load_schema('encoded:schemas/analysis_step_version.json')
def unique_keys(self, properties):
keys = super(AnalysisStepVersion, self).unique_keys(properties)
value = u'{analysis_step}/{version}'.format(**properties)
keys.setdefault('analysis_step_version:analysis_step_version',
[]).append(value)
return keys
class Fvp_b7(Item):
item_type = "fvp_b7"
schema = load_schema("encoded:schemas/fvp_b7.json")
embedded = [
]
rev = {
}
audit_inherit = []
set_status_up = []
set_status_down = []
class GeneticModification(Item):
item_type = 'genetic_modification'
schema = load_schema('encoded:schemas/genetic_modification.json')
name_key = 'accession'
embedded = [
'characterizations', 'modified_site_by_target_id', 'treatments', 'lab'
]
rev = {
'biosamples_modified': ('Biosample', 'genetic_modifications'),
'donors_modified': ('Donor', 'genetic_modifications'),
'characterizations':
('GeneticModificationCharacterization', 'characterizes')
}
@calculated_property(
schema={
"title": "Biosamples modified",
"description":
"Biosamples genetically altered using this modification",
"type": "array",
"items": {
"type": ['string', 'object'],
"linkFrom": "Biosample.genetic_modifications",
},
})
def biosamples_modified(self, request, biosamples_modified):
return paths_filtered_by_status(request, biosamples_modified)
@calculated_property(
schema={
"title": "Donors modified",
"description":
"Donors genetically altered using this modification",
"type": "array",
"items": {
"type": ['string', 'object'],
"linkFrom": "Donor.genetic_modifications",
},
})
def donors_modified(self, request, donors_modified):
return paths_filtered_by_status(request, donors_modified)
@calculated_property(
schema={
"title": "Characterizations",
"type": "array",
"items": {
"type": ['string', 'object'],
"linkFrom":
"GeneticModificationCharacterization.characterizes",
},
})
def characterizations(self, request, characterizations):
return paths_filtered_by_status(request, characterizations)
class LabResults(Item):
item_type = 'lab_results'
schema = load_schema('encoded:schemas/lab_results.json')
embedded = ['patient']
def __ac_local_roles__(self):
# Use patient object for access control.
properties = self.upgrade_properties()
root = find_root(self)
patient = root.get_by_uuid(properties['patient'])
return patient.__ac_local_roles__()
class Platform(Item):
item_type = 'platform'
schema = load_schema('encoded:schemas/platform.json')
name_key = 'term_id'
@calculated_property(schema={
"title": "Title",
"type": "string",
})
def title(self, term_name):
return term_name
class SoftwareVersion(Item):
item_type = 'software_version'
schema = load_schema('encoded:schemas/software_version.json')
embedded = ['software', 'software.references']
def __ac_local_roles__(self):
# Use lab/award from parent software object for access control.
properties = self.upgrade_properties()
root = find_root(self)
software = root.get_by_uuid(properties['software'])
return software.__ac_local_roles__()
class M1(Item):
item_type = "m1"
schema = load_schema("encoded:schemas/m1.json")
embedded = [
]
rev = {
}
audit_inherit = []
set_status_up = []
set_status_down = []
class Award(Item):
item_type = 'award'
schema = load_schema('encoded:schemas/award.json')
name_key = 'name'
embedded = ['pi.lab']
STATUS_ACL = {
'current': ALLOW_CURRENT,
'deleted': DELETED,
'replaced': DELETED,
'disabled': ALLOW_CURRENT
}
class Ivp_b6(Item):
item_type = "ivp_b6"
schema = load_schema("encoded:schemas/ivp_b6.json")
embedded = [
]
rev = {
}
audit_inherit = []
set_status_up = []
set_status_down = []
class AntibodyApproval(Item):
schema = load_schema('encoded:schemas/antibody_approval.json')
item_type = 'antibody_approval'
__acl__ = DELETED
def unique_keys(self, properties):
keys = super(AntibodyApproval, self).unique_keys(properties)
value = u'{antibody}/{target}'.format(**properties)
keys.setdefault('antibody_approval:lot_target', []).append(value)
return keys
class MouseDonor(Donor):
item_type = 'mouse_donor'
schema = load_schema('encoded:schemas/mouse_donor.json')
embedded = Donor.embedded + [
'references', 'genetic_modifications',
'genetic_modifications.modified_site_by_target_id',
'genetic_modifications.treatments'
]
def __ac_local_roles__(self):
# Disallow lab submitter edits
return {Authenticated: 'role.viewing_group_member'}
class Library(Item):
item_type = 'library'
schema = load_schema('encoded:schemas/library.json')
name_key = 'accession'
embedded = [
'biosample',
'biosample.donor',
'biosample.donor.organism',
]
set_status_up = [
'biosample',
'documents',
'source',
'treatments',
]
set_status_down = []
@calculated_property(condition='nucleic_acid_term_name',
schema={
"title": "nucleic_acid_term_id",
"type": "string",
})
def nucleic_acid_term_id(self, request, nucleic_acid_term_name):
term_lookup = {
'DNA': 'SO:0000352',
'RNA': 'SO:0000356',
'polyadenylated mRNA': 'SO:0000871',
'miRNA': 'SO:0000276',
'protein': 'SO:0000104'
}
term_id = None
if nucleic_acid_term_name in term_lookup:
term_id = term_lookup.get(nucleic_acid_term_name)
return term_id
@calculated_property(condition='depleted_in_term_name',
schema={
"title": "depleted_in_term_id",
"type": "string",
})
def depleted_in_term_id(self, request, depleted_in_term_name):
term_lookup = {
'rRNA': 'SO:0000252',
'polyadenylated mRNA': 'SO:0000871',
'capped mRNA': 'SO:0000862'
}
term_id = list()
for term_name in depleted_in_term_name:
if term_name in term_lookup:
term_id.append(term_lookup.get(term_name))
else:
term_id.append('Term ID unknown')
return term_id
class StructuralVariant(Item):
""" Structural variant class """
item_type = "structural_variant"
name_key = "annotation_id"
schema = load_schema("encoded:schemas/structural_variant.json")
embedded_list = build_structural_variant_embedded_list()
@classmethod
def create(cls, registry, uuid, properties, sheets=None):
"""
Sets the annotation_id field on this structural variant prior to passing on.
"""
properties[ANNOTATION_ID] = build_structural_variant_display_title(
properties["SV_TYPE"],
properties["CHROM"],
properties["START"],
properties["END"],
)
return super().create(registry, uuid, properties, sheets)
@calculated_property(
schema={
"title": "Display Title",
"description": "A calculated title for every object in CGAP",
"type": "string",
}
)
def display_title(self, SV_TYPE, CHROM, START, END):
return build_structural_variant_display_title(SV_TYPE, CHROM, START, END)
@calculated_property(
schema={
"title": "Start position (genome coordinates)",
"description": "Start absolute position in genome coordinates",
"type": "integer",
}
)
def START_ABS(self, CHROM, START):
chrom_info = nc.get_chrominfo("hg38")
return nc.chr_pos_to_genome_pos("chr" + CHROM, START, chrom_info)
@calculated_property(
schema={
"title": "End position (genome coordinates)",
"description": "End absolute position in genome coordinates",
"type": "integer",
}
)
def END_ABS(self, CHROM, END):
chrom_info = nc.get_chrominfo("hg38")
return nc.chr_pos_to_genome_pos("chr" + CHROM, END, chrom_info)
class Snowflake(Item):
item_type = 'snowflake'
schema = load_schema('snowflakes:schemas/snowflake.json')
name_key = 'accession'
embedded = [
'lab',
'submitted_by',
]
audit_inherit = [
'lab',
'submitted_by',
]
class Disorder(Item):
item_type = 'disorder'
schema = load_schema('encoded:schemas/disorder.json')
embedded_list = []
name_key = 'disorder_id'
@calculated_property(schema={
"title": "Display Title",
"description": "A calculated title for every object in 4DN",
"type": "string"
})
def display_title(self, disorder_name):
return disorder_name
class AnalysisStepRun(Item):
item_type = 'analysis_step_run'
schema = load_schema('encoded:schemas/analysis_step_run.json')
embedded = [
'analysis_step_version.analysis_step',
]
audit_inherit = ['*']
# Avoid using reverse links on this object as invalidating a
# step_run can cause thousands of objects to be reindexed.
set_status_up = [
'analysis_step_version',
]
set_status_down = []
class AnalysisStep(Item):
item_type = 'analysis_step'
schema = load_schema('encoded:schemas/analysis_step.json')
name_key = 'name'
rev = {
'pipelines': ('Pipeline', 'analysis_steps'),
'versions': ('AnalysisStepVersion', 'analysis_step')
}
embedded = [
'current_version', 'current_version.software_versions',
'current_version.software_versions.software', 'parents'
]
@calculated_property(
schema={
"title": "Pipelines",
"type": "array",
"items": {
"type": 'string',
"linkTo": "Pipeline",
},
})
def pipelines(self, request, pipelines):
return paths_filtered_by_status(request, pipelines)
@calculated_property(
schema={
"title": "Current version",
"type": "string",
"linkTo": "AnalysisStepVersion",
})
def current_version(self, request, versions):
version_objects = [
request.embed(path, '@@object')
for path in paths_filtered_by_status(request, versions)
]
if version_objects:
current = max(version_objects, key=lambda obj: obj['version'])
return current['@id']
@calculated_property(
schema={
"title": "Versions",
"type": "array",
"items": {
"type": 'string',
"linkTo": "AnalysisStepVersion",
},
})
def versions(self, request, versions):
return paths_filtered_by_status(request, versions)
class FileFormat(Item, ItemWithAttachment):
"""The class to store information about 4DN file formats"""
item_type = 'file_format'
schema = load_schema('encoded:schemas/file_format.json')
name_key = 'file_format'
@calculated_property(
schema={
"title": "Display Title",
"description": "File Format name or extension.",
"type": "string"
})
def display_title(self, file_format):
return file_format
class AntibodyLot(SharedItem):
item_type = 'antibody_lot'
schema = load_schema('encoded:schemas/antibody_lot.json')
name_key = 'accession'
rev = {
'characterizations': ('AntibodyCharacterization', 'characterizes'),
}
embedded = [
'source', 'host_organism', 'targets', 'targets.organism',
'characterizations.award', 'characterizations.documents',
'characterizations.lab', 'characterizations.submitted_by',
'characterizations.target.organism', 'lot_reviews.targets',
'lot_reviews.targets.organism', 'lot_reviews.organisms'
]
audit_inherit = [
'source', 'host_organism', 'targets', 'targets.organism',
'characterizations', 'characterizations.documents',
'lot_reviews.targets', 'lot_reviews.targets.organism',
'lot_reviews.organisms'
]
def unique_keys(self, properties):
keys = super(AntibodyLot, self).unique_keys(properties)
source = properties['source']
product_id = properties['product_id']
lot_ids = [properties['lot_id']] + properties.get('lot_id_alias', [])
values = (u'{}/{}/{}'.format(source, product_id, lot_id)
for lot_id in lot_ids)
keys.setdefault('antibody_lot:source_product_lot', []).extend(values)
return keys
@calculated_property(schema={
"title": "Title",
"type": "string",
})
def title(self, accession):
return accession
@calculated_property(
schema={
"title": "Characterizations",
"type": "array",
"items": {
"type": ['string', 'object'],
"linkFrom": "AntibodyCharacterization.characterizes",
},
})
def characterizations(self, request, characterizations):
return paths_filtered_by_status(request, characterizations)
class StaticSection(UserContent):
"""The Software class that contains the software... used."""
item_type = 'static_section'
schema = load_schema('encoded:schemas/static_section.json')
@calculated_property(
schema={
"title": "Content",
"description": "Content for the page",
"type": "string"
})
def content(self, request, body=None, file=None):
if isinstance(body, str) or isinstance(body, dict) or isinstance(
body, list):
# Don't need to load in anything. We don't currently support dict/json body (via schema) but could in future.
return body
if isinstance(file, str):
if file[0:4] == 'http' and '://' in file[4:8]: # Remote File
return get_remote_file_contents(file)
else: # Local File
file_path = os.path.abspath(
os.path.dirname(os.path.realpath(__file__)) + "/../../.." +
file) # Go to top of repo, append file
return get_local_file_contents(file_path)
return None
@calculated_property(
schema={
"title": "File Type",
"description": "Type of file used for content",
"type": "string"
})
def filetype(self, request, body=None, file=None, options=None):
if options and options.get('filetype') is not None:
return options['filetype']
if isinstance(body, str):
return 'txt'
if isinstance(body, dict) or isinstance(body, list):
return 'json'
if isinstance(file, str):
filename_parts = file.split('.')
if len(filename_parts) > 1:
return filename_parts[len(filename_parts) - 1]
else:
return 'txt' # Default if no file extension.
return None
"type" : "object"
}
},
"value" : { # This is used in place of run_data.file, e.g. for a parameter string value, that does not actually have a file.
"title" : "Value",
"type" : "string",
"description" : "Value used for this output argument."
},
"type" : {
"type" : "string",
"title" : "I/O Type"
}
}
}
workflow_schema = load_schema('encoded:schemas/workflow.json')
workflow_steps_property_schema = workflow_schema.get('properties', {}).get('steps')
# This is the schema used for WorkflowRun.steps. Extends Workflow.steps schema.
workflow_run_steps_property_schema = copy.deepcopy(workflow_steps_property_schema)
workflow_run_steps_property_schema['items']['properties']['inputs']['items']['properties']['run_data'] = steps_run_data_schema
workflow_run_steps_property_schema['items']['properties']['outputs']['items']['properties']['run_data'] = steps_run_data_schema
def get_unique_key_from_at_id(at_id):
if not at_id:
return None
at_id_parts = at_id.split('/')
return at_id_parts[2]