Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Karlburke/add dataset type attribute #580

Closed
wants to merge 2 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 0 additions & 53 deletions entity-api-spec.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -406,59 +406,6 @@ components:
- section
- suspension
description: "A code representing the type of specimen. Must be an organ, block, section, or suspension"
specimen_type:
type: string
enum:
- atacseq
- biopsy
- blood
- cell_lysate
- clarity_hydrogel
- codex
- cryosections_curls_from_fresh_frozen_oct
- cryosections_curls_rnalater
- ffpe_block
- ffpe_slide
- fixed_frozen_section_slide
- fixed_tissue_piece
- flash_frozen_liquid_nitrogen
- formalin_fixed_oct_block
- fresh_frozen_oct_block
- fresh_frozen_section_slide
- fresh_frozen_tissue
- fresh_frozen_tissue_section
- fresh_tissue
- frozen_cell_pellet_buffy_coat
- gdna
- module
- nuclei
- nuclei_rnalater
- organ
- organ_piece
- other
- pbmc
- pfa_fixed_frozen_oct_block
- plasma
- protein
- ran_poly_a_enriched
- rna_total
- rnalater_treated_and_stored
- rnaseq
- scatacseq
- scrnaseq
- segment
- seqfish
- sequence_library
- serum
- single_cell_cryopreserved
- snatacseq
- snrnaseq
- tissue_lysate
- wgs
description: "DEPRECATED: No longer a required field. A code representing the type of specimen. Must be one of the codes specified in: [tissue sample types](https://github.com/hubmapconsortium/search-api/blob/main/src/search-schema/data/definitions/enums/tissue_sample_types.yaml)"
specimen_type_other:
type: string
description: "The user provided sample type if the 'other' sample_type is chosen."
protocol_url:
type: string
description: "The protocols.io doi url pointing the protocol under wich the sample was obtained and/or prepared."
Expand Down
252 changes: 102 additions & 150 deletions src/app.py

Large diffs are not rendered by default.

5 changes: 3 additions & 2 deletions src/app_neo4j_queries.py
Original file line number Diff line number Diff line change
Expand Up @@ -736,7 +736,7 @@ def get_prov_info(neo4j_driver, param_dict, published_only):
f" WITH ds, FIRSTSAMPLE, DONOR, REVISIONS, METASAMPLE, RUISAMPLE, ORGAN, COLLECT(distinct processed_dataset) AS PROCESSED_DATASET"
f" RETURN ds.uuid, FIRSTSAMPLE, DONOR, RUISAMPLE, ORGAN, ds.hubmap_id, ds.status, ds.group_name,"
f" ds.group_uuid, ds.created_timestamp, ds.created_by_user_email, ds.last_modified_timestamp, "
f" ds.last_modified_user_email, ds.lab_dataset_id, ds.data_types, METASAMPLE, PROCESSED_DATASET, REVISIONS")
f" ds.last_modified_user_email, ds.lab_dataset_id, ds.data_types, METASAMPLE, PROCESSED_DATASET, REVISIONS") # TODO replace ds.data_types with ds.dataset_type when required

logger.info("======get_prov_info() query======")
logger.info(query)
Expand Down Expand Up @@ -834,7 +834,7 @@ def get_individual_prov_info(neo4j_driver, dataset_uuid):
f" WITH ds, FIRSTSAMPLE, DONOR, METASAMPLE, RUISAMPLE, ORGAN, COLLECT(distinct processed_dataset) AS PROCESSED_DATASET"
f" RETURN ds.uuid, FIRSTSAMPLE, DONOR, RUISAMPLE, ORGAN, ds.hubmap_id, ds.status, ds.group_name,"
f" ds.group_uuid, ds.created_timestamp, ds.created_by_user_email, ds.last_modified_timestamp, "
f" ds.last_modified_user_email, ds.lab_dataset_id, ds.data_types, METASAMPLE, PROCESSED_DATASET")
f" ds.last_modified_user_email, ds.lab_dataset_id, ds.data_types, METASAMPLE, PROCESSED_DATASET, ds.dataset_type")
logger.info("======get_prov_info() query======")
logger.info(query)

Expand Down Expand Up @@ -891,6 +891,7 @@ def get_individual_prov_info(neo4j_driver, dataset_uuid):
node_dict = schema_neo4j_queries.node_to_dict(entry)
content_sixteen.append(node_dict)
record_dict['processed_dataset'] = content_sixteen
record_dict['dataset_type'] = record_contents[17] if record_contents[17] is not None else ''
return record_dict


Expand Down
4 changes: 4 additions & 0 deletions src/instance/app.cfg.example
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,10 @@ UUID_API_URL = 'http://uuid-api:8080'
# Works regardless of the trailing slash
INGEST_API_URL = 'https://ingest-api.dev.hubmapconsortium.org'

# URL for talking to Ontology API (default for DEV)
# Works regardless of the trailing slash
ONTOLOGY_API_URL = 'https://ontology-api.dev.hubmapconsortium.org'

# A list of URLs for talking to multiple Search API instances (default value used for docker deployment, no token needed)
# Works regardless of the trailing slash /
SEARCH_API_URL_LIST = ['http://search-api:8080']
Expand Down
64 changes: 36 additions & 28 deletions src/schema/provenance_schema.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -332,6 +332,14 @@ ENTITIES:
type: list
required_on_create: true # Only required for create via POST, not update via PUT
description: "The data or assay types contained in this dataset as a json array of strings. Each is an assay code from [assay types](https://github.com/hubmapconsortium/search-api/blob/main/src/search-schema/data/definitions/enums/assay_types.yaml)."
dataset_type:
before_property_create_validators:
- validate_recognized_dataset_type
before_property_update_validators:
- validate_recognized_dataset_type
type: string
required_on_create: false # Once replaces data_types, will be required for create via POST, not update via PUT
description: "The assay types of this Dataset. Valid values are from UBKG are queried by schema_manager.get_valueset_dataset_type() using the Ontology API."
collections:
type: list
transient: true
Expand Down Expand Up @@ -901,33 +909,6 @@ ENTITIES:
- validate_sample_category
before_property_update_validators:
- validate_sample_category

# No logner required on create, specimen_type -> sample_category 12/15/2022
specimen_type:
type: string
#required_on_create: true # Only required for create via POST, not update via PUT
description: "A code representing the type of specimen. Must be one of the codes specified in: [tissue sample types](https://github.com/hubmapconsortium/search-api/blob/main/src/search-schema/data/definitions/enums/tissue_sample_types.yaml)"
# Validate the given value against the definitions: https://github.com/hubmapconsortium/search-api/blob/main/src/search-schema/data/definitions/enums/tissue_sample_types.yaml
# Disabled validation 12/15/2022
# before_property_create_validators:
# - validate_specimen_type
# before_property_update_validators:
# - validate_specimen_type
specimen_type_other:
type: string
description: "The user provided sample type if the 'other' sample_type is chosen."


# specimen_type no logner required on create, will remove this field when removing specimen_type
# Simply always set to 'Unknown' and no need to update 12/15/2022
tissue_type:
type: string
generated: true # Can not be updated via the PUT
#auto_update: true # Will always update automatically if the entity gets updated
description: 'The type of the tissue based on the mapping between type (Block/Section/Suspension) and the specimen_type, default is Unknown'
before_create_trigger: set_tissue_type
#before_update_trigger: set_tissue_type

portal_metadata_upload_files:
type: json_string
description: "A list of relative paths to metadata files"
Expand All @@ -940,6 +921,34 @@ ENTITIES:
#todo: migrate to new attribute set as above portal_metadata_upload files
type: json_string
description: "A list of uploaded image files and descriptions of the files."
thumbnail_file:
generated: true
type: json_string
description: "The dataset thumbnail file detail. Stored in db as a stringfied json, e.g., {'filename': 'thumbnail.jpg', 'file_uuid': 'dadasdasdadda'}"
# The updated_peripherally tag is a temporary measure to correctly handle any attributes
# which are potentially updated by multiple triggers
updated_peripherally: true
thumbnail_file_to_add:
type: json_string
transient: true
exposed: false
description: 'Just a temporary file id. Provide as a json object with an temp_file_id like {"temp_file_id":"dzevgd6xjs4d5grmcp4n"}'
before_create_trigger: commit_thumbnail_file
# This before_update_trigger with the same commit process can be used by ingest-api to update the dataset via PUT call
before_update_trigger: commit_thumbnail_file
# The updated_peripherally tag is a temporary measure to correctly handle any attributes
# which are potentially updated by multiple triggers
updated_peripherally: true
thumbnail_file_to_remove:
# This is only valid on update via a PUT request
type: string
transient: true
exposed: false
description: 'The thumbnail image file previously uploaded to delete. Provide as a string of the file_uuid like: "232934234234234234234270c0ea6c51d604a850558ef2247d0b4"'
before_update_trigger: delete_thumbnail_file
# The updated_peripherally tag is a temporary measure to correctly handle any attributes
# which are potentially updated by multiple triggers
updated_peripherally: true
# A user who is a member of multiple groups HAS to send in the group_uuid
group_uuid:
type: string
Expand All @@ -953,7 +962,6 @@ ENTITIES:
immutable: true
description: "The displayname of globus group which the user who created this entity is a member of"
before_create_trigger: set_group_name
# Should be required on create only when specimen_type==organ
organ:
type: string
description: "Organ code specifier, only set if sample_type == organ. Valid values found in: [organ types](https://github.com/hubmapconsortium/search-api/blob/main/src/search-schema/data/definitions/enums/organ_types.yaml)"
Expand Down
13 changes: 5 additions & 8 deletions src/schema/schema_constants.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,23 +2,20 @@
class SchemaConstants(object):
MEMCACHED_TTL = 7200

# Constants used by validators
INGEST_API_APP = 'ingest-api'
INGEST_PIPELINE_APP = 'ingest-pipeline'
HUBMAP_APP_HEADER = 'X-Hubmap-Application'
DATASET_STATUS_PUBLISHED = 'published'

# Used by triggers, all lowercase for easy comparision
ACCESS_LEVEL_PUBLIC = 'public'
ACCESS_LEVEL_CONSORTIUM = 'consortium'
ACCESS_LEVEL_PROTECTED = 'protected'

# Yaml file to parse organ description
ORGAN_TYPES_YAML = 'https://raw.githubusercontent.com/hubmapconsortium/search-api/main/src/search-schema/data/definitions/enums/organ_types.yaml'
ASSAY_TYPES_YAML = 'https://raw.githubusercontent.com/hubmapconsortium/search-api/main/src/search-schema/data/definitions/enums/assay_types.yaml'

# For generating Sample.tissue_type
TISSUE_TYPES_YAML = 'https://raw.githubusercontent.com/hubmapconsortium/search-api/main/src/search-schema/data/definitions/enums/tissue_sample_types.yaml'
UUID_API_ID_ENDPOINT = '/uuid'
INGEST_API_FILE_COMMIT_ENDPOINT = '/file-commit'
INGEST_API_FILE_REMOVE_ENDPOINT = '/file-remove'
ONTOLOGY_API_ASSAY_TYPES_ENDPOINT = '/assaytype?application_context=HUBMAP'
ONTOLOGY_API_ORGAN_TYPES_ENDPOINT = '/organs/by-code?application_context=HUBMAP'

DOI_BASE_URL = 'https://doi.org/'

Expand Down
3 changes: 3 additions & 0 deletions src/schema/schema_errors.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@

class UnimplementedValidatorException(Exception):
pass

class SchemaValidationException(Exception):
pass

Expand Down
Loading