Skip to content

Commit

Permalink
CDM schema updates
Browse files Browse the repository at this point in the history
  • Loading branch information
@ialarmedalien
ialarmedalien committed Feb 3, 2025
1 parent b0f88ce commit 0155eab
Showing 1 changed file with 156 additions and 39 deletions.
195 changes: 156 additions & 39 deletions src/cdm_schema/schema/cdm_schema.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ version: 0.0.1

imports:
- linkml:types
- basin_3d_schema
# - basin_3d_schema
# - rdf
# - owl
# - omo
Expand Down Expand Up @@ -80,6 +80,34 @@ classes:
description: Represents an entity with a hash value generated from combining its unique attributes.
is_a: NamedThingWithId

Cluster:
attributes:
cluster_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true
description:
description: Description of the cluster.
protocol_id:
description: Protocol used to generate the cluster.
description: Represents an individual execution of a clustering protocol. See the Cluster_X_Protein class for clustering results.

Cluster_X_Protein:
attributes:
cluster_id:
range: UUID
required: true
description: Internal (CDM) unique identifier.
protein_id:
range: UUID
required: true
description: Internal (CDM) unique identifier for a protein within a cluster.
score:
range: float
description: Output from clustering protocol.
description: Relationship representing membership of a cluster. An optional score can be assigned to each cluster member.

Contig:
attributes:
contig_id:
Expand All @@ -93,11 +121,45 @@ classes:
length:
description: Length of the contig in bp.
range: integer
part_of_contigset:
description: Contigset that this contig is part of.
multivalued: true
range: Contigset
has_features:
description: Features that are part of this contig.
multivalued: true
range: Feature
description: A contig (derived from the word "contiguous") is a set of DNA
segments or sequences that overlap in a way that provides a contiguous
representation of a genomic region. A contig should not contain any gaps.
is_a: UniqueNamedThing

Contig_X_Contigset:
represents_relationship: true
attributes:
contig_id:
description: Internal (CDM) unique identifier for a contig.
range: UUID
required: true
contigset_id:
description: Internal (CDM) unique identifier for a contigset.
range: UUID
required: true
description: Captures the relationship between a contig and a contigset; equivalent to contig part-of contigset.

Contig_X_Feature:
represents_relationship: true
attributes:
contig_id:
description: Internal (CDM) unique identifier for a contig.
range: UUID
required: true
feature_id:
description: Internal (CDM) unique identifier for a feature.
range: UUID
required: true
description: Captures the relationship between a contig and a feature; equivalent to feature part-of contig.

Contigset:
aliases:
- genome
Expand Down Expand Up @@ -127,10 +189,6 @@ classes:
contigset_type:
description: The type of contig collection.
range: ContigsetType
# contigs:
# description: The contigs in this contigset.
# multivalued: true
# range: Contig
ctg_L50:
description: Given a set of contigs, the L50 is defined as the sequence length
of the shortest contig at 50% of the total contigset length
Expand Down Expand Up @@ -220,6 +278,10 @@ classes:
description: Powersum of all scaffolds is the same as logsum except that it uses
the sum of (length*(length^P)) for some power P (default P=0.25).
range: float
has_contigs:
description: Contigs that are part of this contigset.
multivalued: true
range: Contig
description: A set of individual, overlapping contigs that represent the
complete sequenced genome of an organism.
is_a: UniqueNamedThing
Expand Down Expand Up @@ -365,16 +427,37 @@ classes:
# name:
# required: true

DataSource:
attributes:
entity_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true
entity_type:
# range: valid CDM classes
description: The class of the entity. Must be a valid CDM class.
required: true
created:
description: When the entity was created.
required: true
range: datetime
updated:
description: When the entity was updated.
required: true
range: datetime
provenance:
description: How this entity was derived and added to the database.
required: true
description: The source from which a given database entity was derived.

EncodedFeature:
attributes:
encoded_feature_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true
# encoded_by:
# description: The feature that encodes this EncodedFeature.
# range: Feature
has_stop_codon:
description: Captures whether or not the sequence includes a stop coordinates.
range: boolean
Expand All @@ -383,20 +466,35 @@ classes:
description: An entity generated from a feature, such as a transcript.
is_a: UniqueNamedThing


EncodedFeature_X_Feature:
attributes:
encoded_feature_id:
description: Internal (CDM) unique identifier.
range: UUID
required: true
feature_id:
description: Internal (CDM) unique identifier.
range: UUID
required: true
description: Captures the relationship between a feature and its transcription product.

EnvironmentalContext:
description: The environmental context for the event.
abstract: true
is_a: UniqueNamedThing

GoldEnvironmentalContext:
description: Environmental context, described using JGI's five level system.
is_a: EnvironmentalContext
attributes:
gold_environmental_context_id:
environmental_context_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true


GoldEnvironmentalContext:
description: Environmental context, described using JGI's five level system.
is_a: EnvironmentalContext
attributes:
ecosystem:
description: JGI GOLD descriptor representing the top level ecosystem categorization.
ecosystem_category:
Expand All @@ -407,6 +505,11 @@ classes:
description: JGI GOLD descriptor representing the ecosystem type. May be "Unclassified".
specific_ecosystem:
description: JGI GOLD descriptor representing the most specific level of ecosystem categorization. May be "Unclassified".
# gold_environmental_context_id:
# description: Internal (CDM) unique identifier.
# identifier: true
# range: UUID
# required: true

MixsEnvironmentalContext:
description: Environmental context, described using the MiXS convention of broad and local environment, plus the medium.
Expand All @@ -426,7 +529,7 @@ classes:
aliases:
- broad-scale environmental context
string_serialization: '{termLabel} {[termID]}'
slot_uri: MIXS:0000012
slot_uri: mixs:0000012
# range: ControlledIdentifiedTermValue
range: uriorcurie
multivalued: false
Expand All @@ -435,7 +538,7 @@ classes:
expected_value:
tag: expected_value
value: Environmental entities having causal influences upon the entity at time of sampling.
tooltip: The specific environmental entities or features near the sample or specimen that significantly influence its characteristics or composition. These entities are typically smaller in scale than the broad environmental context. Values for this field should be countable, material nouns and must be chosen from subclasses of BFO:0000040 (material entity) that appear in the Environment Ontology (ENVO). For host-associated or plant-associated samples, use terms from the UBERON or Plant Ontology to describe specific anatomical structures or plant parts.
tooltip: The specific environmental entities or features near the sample or specimen that significantly influence its characteristics or composition. These entities are typically smaller in scale than the broad environmental context. Values for this field should be countable, material nouns and must be chosen from subclasses of BFO:0000040 (material entity) that appear in the Environment Ontology (ENVO). For host-associated or plant-associated samples, use terms from the UBERON or Plant Ontology to describe specific anatomical structures or plant parts.
description: "Report the entity or entities which are in the sample or specimen's local vicinity and which you believe have significant causal influences on your sample or specimen. We recommend using EnvO terms which are of smaller spatial grain than your entry for env_broad_scale. Terms, such as anatomical sites, from other OBO Library ontologies which interoperate with EnvO (e.g. UBERON) are accepted in this field. EnvO documentation about how to use the field: https://github.com/EnvironmentOntology/envo/wiki/Using-ENVO-with-MIxS."
title: local environmental context
examples:
Expand All @@ -444,7 +547,7 @@ classes:
aliases:
- local environmental context
string_serialization: '{termLabel} {[termID]}'
slot_uri: MIXS:0000013
slot_uri: mixs:0000013
# range: ControlledIdentifiedTermValue
range: uriorcurie
multivalued: false
Expand All @@ -462,15 +565,15 @@ classes:
aliases:
- environmental medium
string_serialization: '{termLabel} {[termID]}'
slot_uri: MIXS:0000014
slot_uri: mixs:0000014
# range: ControlledIdentifiedTermValue
range: uriorcurie
multivalued: false
mixs_environmental_context_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true
# mixs_environmental_context_id:
# description: Internal (CDM) unique identifier.
# identifier: true
# range: UUID
# required: true

Event:
attributes:
Expand Down Expand Up @@ -531,10 +634,6 @@ classes:
description: The 'score' of the feature. The semantics of this field are
ill-defined. E-values should be used for sequence similarity features.
range: float
encodes:
description: Known or predicted transcription products from this feature.
multivalued: true
range: EncodedFeature
end:
description: The start and end coordinates of the feature are given in positive
1-based int coordinates, relative to the landmark given in column one.
Expand Down Expand Up @@ -578,7 +677,7 @@ classes:
# FIXME: should be an organisation from the ontology tables
# range: Organization
range: uriorcurie
source_protocol:
protocol_id:
description: ID of the protocol used to generate the feature.
range: Protocol
type:
Expand All @@ -589,6 +688,18 @@ classes:
(SO:0000110) or an is_a child of it.
pattern: ^SO:\d+$
range: uriorcurie
part_of_contig:
description: The contig that this feature appears on.
multivalued: true
range: Contig
encodes:
description: Known or predicted transcription products from this feature.
multivalued: true
range: EncodedFeature
has_translation_product:
description: Known or predicted proteins related to this feature.
multivalued: true
range: Protein
comments:
- corresponds to an entry in GFF3
description: A feature localized to an interval along a contig.
Expand All @@ -609,7 +720,8 @@ classes:
description: The value of the attribute.
description: Additional attributes of a feature, parsed from column 9 of a GFF file.

FeatureXProtein:
Feature_X_Protein:
represents_relationship: true
attributes:
feature_id:
description: Internal (CDM) unique identifier for a feature.
Expand All @@ -619,10 +731,7 @@ classes:
description: Internal (CDM) unique identifier for a protein.
range: UUID
required: true
protocol_id:
description: Internal (CDM) unique identifier for a protocol.
range: UUID
description: Captures the relationship between a feature and a protein; equivalent to feature encodes protein. An additional protocol ID may be specified to annotate the protocol used to elucidate or predict the relationship.
description: Captures the relationship between a feature and a protein; equivalent to feature encodes protein.

Genome:
description: A contigset with a completeness score of greater than 90% and a
Expand All @@ -639,6 +748,7 @@ classes:
range: UUID
required: true
identifier:
identifier: true
description: Fully-qualifier URL or CURIE used as an identifier for an entity.
range: uriorcurie
required: true
Expand Down Expand Up @@ -699,6 +809,7 @@ classes:
required: true
name:
description: The string used as a name.
identifier: true
required: true
slot_uri: schema:name
examples:
Expand All @@ -716,11 +827,11 @@ classes:

ProcessedMeasurement:
attributes:
processed_measurement_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true
# processed_measurement_id:
# description: Internal (CDM) unique identifier.
# identifier: true
# range: UUID
# required: true
quality:
description: The quality of the measurement, indicating the confidence that one can have in its correctness.
description: A measurement that requires additional processing to generate a result.
Expand Down Expand Up @@ -791,8 +902,13 @@ classes:

ProtocolParticipant:
description: Either an input or an output of a protocol.
is_a: NamedThing
# attributes:
is_a: NamedThingWithId
attributes:
protocol_participant_id:
description: Internal (CDM) unique identifier.
identifier: true
range: UUID
required: true

# Relationship:
# description: tbd
Expand Down Expand Up @@ -939,6 +1055,7 @@ enums:

types:
UUID:
uri: xsd:string
base: str
description: A universally unique ID, generating using uuid4.
# 8-4-4-4-12, x = [0-9a-f]

0 comments on commit 0155eab

Please sign in to comment.