diff --git a/erdiagram-autogen/library_generation.md b/erdiagram-autogen/library_generation.md index 24817e09..82406026 100644 --- a/erdiagram-autogen/library_generation.md +++ b/erdiagram-autogen/library_generation.md @@ -303,92 +303,61 @@ Donor { ProvEntity ||--|o ProvEntity : "was_derived_from" ProvEntity ||--|o ProvActivity : "was_generated_by" -ProvEntity ||--|o ProvEntity : "annotates" -ProvEntity ||--|o ProvEntity : "dissection_was_guided_by" ProvActivity ||--|o ProvEntity : "used" -ProvActivity ||--|o ProvEntity : "was_guided_by" DissectionRoiPolygon ||--|o DissectionRoiDelineation : "was_generated_by" DissectionRoiPolygon ||--|o BrainSlab : "annotates" DissectionRoiPolygon ||--|o ProvEntity : "was_derived_from" -DissectionRoiPolygon ||--|o ProvEntity : "dissection_was_guided_by" DissectionRoiPolygon ||--}o Attribute : "has attribute" LibraryPooling ||--}o LibraryAliquot : "used" -LibraryPooling ||--|o ProvEntity : "was_guided_by" LibraryPooling ||--}o Attribute : "has attribute" LibraryConstruction ||--|o ProvEntity : "used" -LibraryConstruction ||--|o ProvEntity : "was_guided_by" LibraryConstruction ||--}o Attribute : "has attribute" CdnaAmplification ||--|o BarcodedCellSample : "used" -CdnaAmplification ||--|o ProvEntity : "was_guided_by" CdnaAmplification ||--}o Attribute : "has attribute" CellBarcoding ||--}o ProvEntity : "used" -CellBarcoding ||--|o ProvEntity : "was_guided_by" CellBarcoding ||--}o Attribute : "has attribute" EnrichedCellSampleSplitting ||--|o EnrichedCellSample : "used" -EnrichedCellSampleSplitting ||--|o ProvEntity : "was_guided_by" EnrichedCellSampleSplitting ||--}o Attribute : "has attribute" CellEnrichment ||--}o DissociatedCellSample : "used" -CellEnrichment ||--|o ProvEntity : "was_guided_by" CellEnrichment ||--}o Attribute : "has attribute" CellDissociation ||--}o TissueSample : "used" -CellDissociation ||--|o ProvEntity : "was_guided_by" CellDissociation ||--}o Attribute : "has attribute" -TissueDissection ||--|o DissectionRoiPolygon : "was_guided_by" TissueDissection ||--|o BrainSlab : "used" +TissueDissection ||--|o DissectionRoiPolygon : "was_guided_by" TissueDissection ||--}o Attribute : "has attribute" DissectionRoiDelineation ||--|o BrainSlab : "used" -DissectionRoiDelineation ||--|o ProvEntity : "was_guided_by" DissectionRoiDelineation ||--}o Attribute : "has attribute" LibraryPool ||--|o LibraryPooling : "was_generated_by" LibraryPool ||--}o LibraryAliquot : "was_derived_from" -LibraryPool ||--|o ProvEntity : "annotates" -LibraryPool ||--|o ProvEntity : "dissection_was_guided_by" LibraryPool ||--}o Attribute : "has attribute" LibraryAliquot ||--|o Library : "was_derived_from" LibraryAliquot ||--|o ProvActivity : "was_generated_by" -LibraryAliquot ||--|o ProvEntity : "annotates" -LibraryAliquot ||--|o ProvEntity : "dissection_was_guided_by" LibraryAliquot ||--}o Attribute : "has attribute" Library ||--|o LibraryConstruction : "was_generated_by" Library ||--|o ProvEntity : "was_derived_from" -Library ||--|o ProvEntity : "annotates" -Library ||--|o ProvEntity : "dissection_was_guided_by" Library ||--}o Attribute : "has attribute" AmplifiedCdna ||--|o CdnaAmplification : "was_generated_by" AmplifiedCdna ||--|o BarcodedCellSample : "was_derived_from" -AmplifiedCdna ||--|o ProvEntity : "annotates" -AmplifiedCdna ||--|o ProvEntity : "dissection_was_guided_by" AmplifiedCdna ||--}o Attribute : "has attribute" BarcodedCellSample ||--|o CellBarcoding : "was_generated_by" BarcodedCellSample ||--}o ProvEntity : "was_derived_from" -BarcodedCellSample ||--|o ProvEntity : "annotates" -BarcodedCellSample ||--|o ProvEntity : "dissection_was_guided_by" BarcodedCellSample ||--}o Attribute : "has attribute" EnrichedCellSample ||--|o ProvActivity : "was_generated_by" EnrichedCellSample ||--}o ProvEntity : "was_derived_from" -EnrichedCellSample ||--|o ProvEntity : "annotates" -EnrichedCellSample ||--|o ProvEntity : "dissection_was_guided_by" EnrichedCellSample ||--}o Attribute : "has attribute" DissociatedCellSample ||--|o CellDissociation : "was_generated_by" DissociatedCellSample ||--}o TissueSample : "was_derived_from" -DissociatedCellSample ||--|o ProvEntity : "annotates" -DissociatedCellSample ||--|o ProvEntity : "dissection_was_guided_by" DissociatedCellSample ||--}o Attribute : "has attribute" TissueSample ||--|o Donor : "was_derived_from" TissueSample ||--|o TissueDissection : "was_generated_by" TissueSample ||--|o DissectionRoiPolygon : "dissection_was_guided_by" -TissueSample ||--|o ProvEntity : "annotates" TissueSample ||--}o Attribute : "has attribute" BrainSlab ||--|o Donor : "was_derived_from" BrainSlab ||--|o ProvActivity : "was_generated_by" -BrainSlab ||--|o ProvEntity : "annotates" -BrainSlab ||--|o ProvEntity : "dissection_was_guided_by" BrainSlab ||--}o Attribute : "has attribute" Donor ||--}o OrganismTaxon : "in taxon" Donor ||--|o ProvEntity : "was_derived_from" Donor ||--|o ProvActivity : "was_generated_by" -Donor ||--|o ProvEntity : "annotates" -Donor ||--|o ProvEntity : "dissection_was_guided_by" Donor ||--}o Attribute : "has attribute" ``` diff --git a/json-schema-autogen/library_generation.json b/json-schema-autogen/library_generation.json index 5646282f..1acbc44d 100644 --- a/json-schema-autogen/library_generation.json +++ b/json-schema-autogen/library_generation.json @@ -114,10 +114,6 @@ "description": "QC metric to measure mRNA degradation of cDNA. Higher % is higher quality starting material. Over 400bp is used as a universal cutoff for intact (full length) vs degraded cDNA and is a common output from Bioanalyzer and Fragment Analyzer elecropheragrams.", "type": "number" }, - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -137,10 +133,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "full_name": { "description": "a long-form human readable name for a thing", "type": "string" @@ -316,10 +308,6 @@ "additionalProperties": false, "description": "A collection of molecularly barcoded cells. Input will be either dissociated cell sample or enriched cell sample. Cell barcodes are only guaranteed to be unique within this one collection. One dissociated cell sample or enriched cell sample can lead to multiple barcoded cell samples. The sequences of the molecular barcodes are revealed during alignment of the resulting fastq files for the barcoded cell sample. The barcoded cell sample name and the cell level molecular barcode together uniquely identify a single cell.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -339,10 +327,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "expected_cell_capture": { "description": "Expected number of cells/nuclei of a barcoded_cell_sample that will be barcoded and available for sequencing. This is a derived number from 'Barcoded cell input quantity count' that is dependent on the \"capture rate\" of the barcoding method. It is usually a calculated fraction of the 'Barcoded cell input quantity count' going into the barcoding method.", "type": "integer" @@ -438,10 +422,6 @@ "additionalProperties": false, "description": "A thick flat piece of brain tissue obtained by slicing a whole brain, brain hemisphere or subdivision with a blade at regular interval. When multiple brain slabs are obtained from the slicing process, an ordinal is assigned to provide information about the relative positioning of the slabs.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -461,10 +441,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "full_name": { "description": "a long-form human readable name for a thing", "type": "string" @@ -621,10 +597,6 @@ "description": "The input barcoded cell sample from which amplified cDNA was derived from.", "type": "string" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -736,10 +708,6 @@ }, "type": "array" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -831,10 +799,6 @@ }, "type": "array" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -926,10 +890,6 @@ }, "type": "array" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -1107,10 +1067,6 @@ "description": "The brain slab that was annotated by the delineation process.", "type": "string" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -1152,10 +1108,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "has_attribute": { "description": "connects any entity to an attribute", "items": { @@ -1200,10 +1152,6 @@ "additionalProperties": false, "description": "A collection of dissociated cells or nuclei derived from dissociation of a tissue sample.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -1223,10 +1171,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "dissociated_cell_oligo_tag_name": { "$ref": "#/$defs/DissociatedCellSampleCellLabelBarcode", "description": "Name of cell source oligo used in cell plexing. The oligo molecularly tags all the cells in the dissociated cell sample and allows separate dissociated cell samples to be combined downstream in the barcoded cell sample. The oligo name is associated with a sequence in a lookup table. This sequence will be needed during alignment to associate reads with the parent source dissociated cell sample." @@ -1361,10 +1305,6 @@ "description": "The value representing the donor age from the reference point.", "type": "number" }, - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "biological_sex": { "$ref": "#/$defs/Sex", "description": "Biological sex of donor at birth" @@ -1388,10 +1328,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "donor_species": { "description": "Species of donor.", "type": "string" @@ -1476,10 +1412,6 @@ "additionalProperties": false, "description": "A collection of enriched cells or nuclei after enrichment process, usually via fluorescence-activated cell sorting (FACS) using the enrichment plan, is applied to dissociated cell sample.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -1503,10 +1435,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "enrichment_population": { "description": "Actual percentage of cells as a result of using set of fluorescent marker label(s) to enrich dissociated_cell_sample with desired mix of cell populations. This plan can also be used to describe 'No FACS' where no enrichment was performed. This is a property of enriched_cell_prep_container.", "type": "string" @@ -1669,10 +1597,6 @@ "description": "The enrichment cell sample splitting process from which the enriched cell sample was generated by.", "type": "string" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -1887,10 +1811,6 @@ "$ref": "#/$defs/LibraryR1R2Index", "description": "Name of the pair of library indexes used for sequencing. Indexes allow libraries to be pooled together for sequencing. Sequencing output (fastq) are demultiplexed by using the indexes for each library. The name will be associated with the sequences of i7, i5, and i5as, which are needed by SeqCores for demultiplexing. The required direction of the sequence (sense or antisense) of the index can differ depending on sequencing instruments." }, - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -1910,10 +1830,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "full_name": { "description": "a long-form human readable name for a thing", "type": "string" @@ -2011,10 +1927,6 @@ "additionalProperties": false, "description": "One library in the library pool. Each library aliquot in a library pool will have a unique R1/R2 index to allow for sequencing together then separating the sequencing output by originating library aliquot through the process of demultiplexing. The resulting demultiplexed fastq files will include the library aliquot name. A given library may produce multiple library aliquots, which is done in the case of resequencing. Each library aliquot will produce a set of fastq files.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -2034,10 +1946,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "full_name": { "description": "a long-form human readable name for a thing", "type": "string" @@ -2198,10 +2106,6 @@ } ] }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -2220,10 +2124,6 @@ "additionalProperties": false, "description": "A library pool is made up of library aliquots from multiple libraries. Each library aliquot in a library pool will have a unique R1/R2 index to allow for sequencing together then separating the sequencing output by originating library aliquot through the process of demultiplexing.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -2243,10 +2143,6 @@ "description": "a human-readable description of an entity", "type": "string" }, - "dissection_was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Tranformation (dissection) of one entity into another entity." - }, "full_name": { "description": "a long-form human readable name for a thing", "type": "string" @@ -2396,10 +2292,6 @@ }, "type": "array" }, - "was_guided_by": { - "$ref": "#/$defs/ProvEntity", - "description": "Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer." - }, "xref": { "description": "A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.", "items": { @@ -3498,10 +3390,6 @@ "additionalProperties": false, "description": "The final intact piece of tissue before cell or nuclei prep. This piece of tissue will be used in dissociation and has an region of interest polygon (ROI) associated with it.", "properties": { - "annotates": { - "$ref": "#/$defs/ProvEntity", - "description": "Annotation is the addition of metadata to an entity" - }, "category": { "description": "Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}", "enum": [ @@ -3598,11 +3486,11 @@ "type": "object" } }, - "$id": "https://identifiers.org/brain-bican/kb-model", + "$id": "https://identifiers.org/brain-bican/library-generation-schema", "$schema": "https://json-schema.org/draft/2019-09/schema", "additionalProperties": true, "metamodel_version": "1.7.0", - "title": "kb-model", + "title": "library-generation-schema", "type": "object", "version": null } diff --git a/jsonld-context-autogen/library_generation.context.jsonld b/jsonld-context-autogen/library_generation.context.jsonld index f741b64f..1aa528f2 100644 --- a/jsonld-context-autogen/library_generation.context.jsonld +++ b/jsonld-context-autogen/library_generation.context.jsonld @@ -212,10 +212,6 @@ "@type": "xsd:float", "@id": "0db79d05-8612-4896-b9d3-eb1558841449" }, - "annotates": { - "@type": "@id", - "@id": "annotates" - }, "expected_cell_capture": { "@type": "xsd:integer", "@id": "f10e928d-5a2b-4943-af18-d8fe5d05528d" @@ -265,9 +261,9 @@ "description": { "@id": "dct:description" }, - "dissection_was_guided_by": { + "annotates": { "@type": "@id", - "@id": "dissection_was_guided_by" + "@id": "annotates" }, "dissociated_cell_sample_cell_prep_type": { "@context": { @@ -468,6 +464,14 @@ "synonym": { "@id": "biolink:synonym" }, + "was_guided_by": { + "@type": "@id", + "@id": "was_guided_by" + }, + "dissection_was_guided_by": { + "@type": "@id", + "@id": "dissection_was_guided_by" + }, "tissue_sample_structure": { "@id": "tissue_sample_structure" }, @@ -489,10 +493,6 @@ "@type": "@id", "@id": "prov:wasGeneratedBy" }, - "was_guided_by": { - "@type": "@id", - "@id": "was_guided_by" - }, "xref": { "@type": "@id", "@id": "biolink:xref" diff --git a/models_py-autogen/library_generation.py b/models_py-autogen/library_generation.py index 4711701c..d19570fb 100644 --- a/models_py-autogen/library_generation.py +++ b/models_py-autogen/library_generation.py @@ -1571,7 +1571,6 @@ class ProvActivity(ConfiguredBaseModel): An activity is something that occurs over a period of time and acts upon or with entities; it may include consuming, processing, transforming, modifying, relocating, using, or generating entities. """ used: Optional[str] = Field(None, description="""Usage is the beginning of utilizing an entity by an activity. Before usage, the activity had not begun to utilize this entity and could not have been affected by the entity.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") class DissectionRoiDelineation(ProvActivity, Procedure): @@ -1579,7 +1578,6 @@ class DissectionRoiDelineation(ProvActivity, Procedure): The process of outlining a region of interest on a brain slab image to guide the dissection and generation of a tissue sample. """ used: Optional[str] = Field(None, description="""The brain slab that was annotated by the delineation process.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/DissectionRoiDelineation","bican:DissectionRoiDelineation"]] = Field(["bican:DissectionRoiDelineation"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1610,8 +1608,8 @@ class TissueDissection(ProvActivity, Procedure): """ The process of dissecting a tissue sample from a brain slab guided by a dissection region of interest (ROI) delineation. """ - was_guided_by: Optional[str] = Field(None, description="""The dissection ROI polygon which was used to guide the tissue dissection.""") used: Optional[str] = Field(None, description="""The brain slab from which the tissue sample was dissected from.""") + was_guided_by: Optional[str] = Field(None, description="""The dissection ROI polygon which was used to guide the tissue dissection.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/TissueDissection","bican:TissueDissection"]] = Field(["bican:TissueDissection"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1644,7 +1642,6 @@ class CellDissociation(ProvActivity, Procedure): """ used: Optional[List[str]] = Field(default_factory=list, description="""The input tissue sample(s) from which the dissociated cell sample was derived from.""") process_date: Optional[str] = Field(None, description="""Date of cell dissociation process.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/CellDissociation","bican:CellDissociation"]] = Field(["bican:CellDissociation"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1677,7 +1674,6 @@ class CellEnrichment(ProvActivity, Procedure): """ used: Optional[List[str]] = Field(default_factory=list, description="""The input dissociated cell sample(s) from which the enriched cell sample was derived from.""") process_date: Optional[str] = Field(None, description="""Date of cell enrichment process.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/CellEnrichment","bican:CellEnrichment"]] = Field(["bican:CellEnrichment"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1709,7 +1705,6 @@ class EnrichedCellSampleSplitting(ProvActivity, Procedure): The process of splitting an enriched cell sample into several portions. Each portion may be used by the same or different groups for different scientific studies. """ used: Optional[str] = Field(None, description="""The enrichment cell sample splitting process from which the enriched cell sample was generated by.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/EnrichedCellSampleSplitting","bican:EnrichedCellSampleSplitting"]] = Field(["bican:EnrichedCellSampleSplitting"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1745,7 +1740,6 @@ class CellBarcoding(ProvActivity, Procedure): input_quantity: Optional[int] = Field(None, description="""Number of enriched or dissociated cells/nuclei going into the barcoding process.""") process_date: Optional[str] = Field(None, description="""Date of cell barcoding process.""") method: Optional[BarcodedCellSampleTechnique] = Field(None, description="""Standardized nomenclature to describe the general barcoding method used. For example: Multiome, ATAC Only, GEX Only or snm3C-seq.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/CellBarcoding","bican:CellBarcoding"]] = Field(["bican:CellBarcoding"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1780,7 +1774,6 @@ class CdnaAmplification(ProvActivity, Procedure): pcr_cycles: Optional[int] = Field(None, description="""Number of PCR cycles used during cDNA amplification for this cDNA.""") process_date: Optional[date] = Field(None, description="""Date of cDNA amplification.""") set: Optional[str] = Field(None, description="""cDNA amplification set, containing multiple amplified_cDNA_names that were processed at the same time.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/CdnaAmplification","bican:CdnaAmplification"]] = Field(["bican:CdnaAmplification"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1816,7 +1809,6 @@ class LibraryConstruction(ProvActivity, Procedure): process_date: Optional[date] = Field(None, description="""Date of library construction.""") input_quantity_ng: Optional[float] = Field(None, description="""Amount of cDNA going into library construction in nanograms.""") set: Optional[str] = Field(None, description="""Library set, containing multiple library_names that were processed at the same time.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/LibraryConstruction","bican:LibraryConstruction"]] = Field(["bican:LibraryConstruction"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1849,7 +1841,6 @@ class LibraryPooling(ProvActivity, Procedure): """ used: Optional[List[str]] = Field(default_factory=list, description="""The input aliquot(s) from which the library pool was derived from.""") process_date: Optional[str] = Field(None, description="""Date of library pooling process.""") - was_guided_by: Optional[str] = Field(None, description="""Guidance is the influence of an entity on an activity. This entity is known as an influencer, and the activity is influenced by the influencer.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/LibraryPooling","bican:LibraryPooling"]] = Field(["bican:LibraryPooling"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1882,11 +1873,9 @@ class ProvEntity(ConfiguredBaseModel): """ was_derived_from: Optional[str] = Field(None, description="""A derivation is a transformation of an entity into another, an update of an entity resulting in a new one, or the construction of a new entity based on a pre-existing entity.""") was_generated_by: Optional[str] = Field(None, description="""Generation is the completion of production of a new entity by an activity. This entity did not exist before generation and becomes available for usage after this generation.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") -class Donor(ProvEntity, ThingWithTaxon, MaterialSample): +class Donor(ProvEntity, ThingWithTaxon, PhysicalEntity): """ A person or organism that is the source of a biological sample for scientific study. Many biological samples are generated from a single donor. """ @@ -1901,8 +1890,6 @@ class Donor(ProvEntity, ThingWithTaxon, MaterialSample): in_taxon_label: Optional[str] = Field(None, description="""The human readable scientific name for the taxon of the entity.""") was_derived_from: Optional[str] = Field(None, description="""A derivation is a transformation of an entity into another, an update of an entity resulting in a new one, or the construction of a new entity based on a pre-existing entity.""") was_generated_by: Optional[str] = Field(None, description="""Generation is the completion of production of a new entity by an activity. This entity did not exist before generation and becomes available for usage after this generation.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/Donor","bican:Donor"]] = Field(["bican:Donor"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1935,8 +1922,6 @@ class BrainSlab(ProvEntity, MaterialSample): was_derived_from: Optional[str] = Field(None, description="""The donor from which the brain slab was derived from.""") name: Optional[str] = Field(None, description="""Name of a thick flat piece of brain tissue obtained by slicing a whole brain, brain hemisphere or subdivision with a blade at regular interval. When multiple brain slabs are obtained from the slicing process, an ordinal is assigned to provide information about the relative positioning of the slabs.""") was_generated_by: Optional[str] = Field(None, description="""Generation is the completion of production of a new entity by an activity. This entity did not exist before generation and becomes available for usage after this generation.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/BrainSlab","bican:BrainSlab"]] = Field(["bican:BrainSlab"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -1968,10 +1953,9 @@ class TissueSample(ProvEntity, MaterialSample): """ was_derived_from: Optional[str] = Field(None, description="""The donor or brain slab from which the tissue sample was derived from.""") was_generated_by: Optional[str] = Field(None, description="""The dissection process from which the tissue sample was generated by.""") - dissection_was_guided_by: Optional[str] = Field(None, description="""The dissection ROI polygon that was used to guide the dissection.""") name: Optional[str] = Field(None, description="""Identifier name for final intact piece of tissue before cell or nuclei prep. This piece of tissue will be used in dissociation and has an ROI associated with it.""") + dissection_was_guided_by: Optional[str] = Field(None, description="""The dissection ROI polygon that was used to guide the dissection.""") structure: Optional[List[str]] = Field(default_factory=list, description="""Strucure of tissue sample.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/TissueSample","bican:TissueSample"]] = Field(["bican:TissueSample"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2006,8 +1990,6 @@ class DissociatedCellSample(ProvEntity, MaterialSample): name: Optional[str] = Field(None, description="""Name of a collection of dissociated cells or nuclei derived from dissociation of a tissue sample.""") cell_prep_type: Optional[DissociatedCellSampleCellPrepType] = Field(None, description="""The type of cell preparation. For example: Cells, Nuclei. This is a property of dissociated_cell_sample.""") cell_source_oligo_name: Optional[DissociatedCellSampleCellLabelBarcode] = Field(None, description="""Name of cell source oligo used in cell plexing. The oligo molecularly tags all the cells in the dissociated cell sample and allows separate dissociated cell samples to be combined downstream in the barcoded cell sample. The oligo name is associated with a sequence in a lookup table. This sequence will be needed during alignment to associate reads with the parent source dissociated cell sample.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/DissociatedCellSample","bican:DissociatedCellSample"]] = Field(["bican:DissociatedCellSample"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2043,8 +2025,6 @@ class EnrichedCellSample(ProvEntity, MaterialSample): enrichment_population: Optional[str] = Field(None, description="""Actual percentage of cells as a result of using set of fluorescent marker label(s) to enrich dissociated_cell_sample with desired mix of cell populations. This plan can also be used to describe 'No FACS' where no enrichment was performed. This is a property of enriched_cell_prep_container.""") cell_source_oligo_name: Optional[str] = Field(None, description="""Name of cell source oligo used in cell plexing. The oligo molecularly tags all the cells in the enriched cell sample and allows separate enriched cell samples to be combined downstream in the barcoded cell sample. The oligo name is associated with a sequence in a lookup table. This sequence will be needed during alignment to associate reads with the parent source enriched cell sample.""") histone_modification_marker: Optional[str] = Field(None, description="""Histone modification marker antibodies (eg H3K27ac, H3K27me3, H3K9me3) used in conjunction with an Enriched Cell Source Barcode in order to combine multiple Enriched Cell Populations before Barcoded Cell Sample step for 10xMultiome method. Each of the Histone antibodies captures an essential part of the epigenome.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/EnrichedCellSample","bican:EnrichedCellSample"]] = Field(["bican:EnrichedCellSample"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2078,8 +2058,6 @@ class BarcodedCellSample(ProvEntity, MaterialSample): was_derived_from: Optional[List[str]] = Field(default_factory=list, description="""The input dissociated or enriched cell sample(s) from which the barcoded cell sample was derived from.""") name: Optional[str] = Field(None, description="""Name of a collection of barcoded cells. Input will be either dissociated_cell_sample or enriched_cell_sample. Cell barcodes are only guaranteed to be unique within this one collection. One dissociated_cell_sample or enriched_cell_sample can lead to multiple barcoded_cell_samples.""") number_of_expected_cells: Optional[int] = Field(None, description="""Expected number of cells/nuclei of a barcoded_cell_sample that will be barcoded and available for sequencing. This is a derived number from 'Barcoded cell input quantity count' that is dependent on the \"capture rate\" of the barcoding method. It is usually a calculated fraction of the 'Barcoded cell input quantity count' going into the barcoding method.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/BarcodedCellSample","bican:BarcodedCellSample"]] = Field(["bican:BarcodedCellSample"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2115,8 +2093,6 @@ class AmplifiedCdna(ProvEntity, MaterialSample): quantity_ng: Optional[float] = Field(None, description="""Amount of cDNA produced after cDNA amplification measured in nanograms.""") pass_fail_result: Optional[AmplifiedCdnaRnaAmplificationPassFail] = Field(None, description="""Pass or Fail result based on qualitative assessment of cDNA yield and size.""") percent_cdna_longer_than_400bp: Optional[float] = Field(None, description="""QC metric to measure mRNA degradation of cDNA. Higher % is higher quality starting material. Over 400bp is used as a universal cutoff for intact (full length) vs degraded cDNA and is a common output from Bioanalyzer and Fragment Analyzer elecropheragrams.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/AmplifiedCdna","bican:AmplifiedCdna"]] = Field(["bican:AmplifiedCdna"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2155,8 +2131,6 @@ class Library(ProvEntity, MaterialSample): quantity_fmol: Optional[float] = Field(None, description="""Amount of library generated in terms of femtomoles""") quantity_ng: Optional[float] = Field(None, description="""Amount of library generated in terms of nanograms""") r1_r2_index: Optional[LibraryR1R2Index] = Field(None, description="""Name of the pair of library indexes used for sequencing. Indexes allow libraries to be pooled together for sequencing. Sequencing output (fastq) are demultiplexed by using the indexes for each library. The name will be associated with the sequences of i7, i5, and i5as, which are needed by SeqCores for demultiplexing. The required direction of the sequence (sense or antisense) of the index can differ depending on sequencing instruments.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/Library","bican:Library"]] = Field(["bican:Library"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2189,8 +2163,6 @@ class LibraryAliquot(ProvEntity, MaterialSample): was_derived_from: Optional[str] = Field(None, description="""The input library from which the library aliquot was derived from.""") name: Optional[str] = Field(None, description="""One library in the library pool. Each Library_aliquot_name in a library pool will have a unique R1/R2 index to allow for sequencing together then separating the sequencing output by originating library aliquot through the process of demultiplexing. The resulting demultiplexed fastq files will include the library_aliquot_name.""") was_generated_by: Optional[str] = Field(None, description="""Generation is the completion of production of a new entity by an activity. This entity did not exist before generation and becomes available for usage after this generation.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/LibraryAliquot","bican:LibraryAliquot"]] = Field(["bican:LibraryAliquot"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2224,8 +2196,6 @@ class LibraryPool(ProvEntity, MaterialSample): was_derived_from: Optional[List[str]] = Field(default_factory=list, description="""The input aliquot(s) from which the library pool was derived from.""") name: Optional[str] = Field(None, description="""Library lab's library pool name. For some labs this may be the same as \"Libray pool tube local name\". Other labs distinguish between the local tube label of the library pool and the library pool name provided to SeqCore for tracking. Local Pool Name is used to communicate sequencing status between SeqCore and Library Labs.""") local_tube_id: Optional[str] = Field(None, description="""Library Pool Tube local name. Label of the tube containing the library pool, which is made up of multiple library_aliquots. This is a Library Lab local tube name, before the pool is aliquoted to the Seq Core provided tube 'Library Pool Tube Name'.""") - annotates: Optional[str] = Field(None, description="""Annotation is the addition of metadata to an entity""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/LibraryPool","bican:LibraryPool"]] = Field(["bican:LibraryPool"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""") @@ -2256,10 +2226,9 @@ class DissectionRoiPolygon(ProvEntity, Entity): A polygon annotated on a brain slab image delineating a region of interest (ROI) for a tissue sample dissectioning. """ was_generated_by: Optional[str] = Field(None, description="""The delineation process from which the dissection ROI polygon was generated by.""") - annotates: Optional[str] = Field(None, description="""The brain slab that was annotated by the delineation process.""") name: Optional[str] = Field(None, description="""Name of a polygon annotated on a brain slab image delineating a region of interest (ROI) for a tissue sample dissectioning.""") + annotates: Optional[str] = Field(None, description="""The brain slab that was annotated by the delineation process.""") was_derived_from: Optional[str] = Field(None, description="""A derivation is a transformation of an entity into another, an update of an entity resulting in a new one, or the construction of a new entity based on a pre-existing entity.""") - dissection_was_guided_by: Optional[str] = Field(None, description="""Tranformation (dissection) of one entity into another entity.""") id: str = Field(..., description="""A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI""") iri: Optional[str] = Field(None, description="""An IRI for an entity. This is determined by the id using expansion rules.""") category: List[Literal["https://identifiers.org/brain-bican/vocab/DissectionRoiPolygon","bican:DissectionRoiPolygon"]] = Field(["bican:DissectionRoiPolygon"], description="""Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values `biolink:Protein`, `biolink:GeneProduct`, `biolink:MolecularEntity`. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature `f` may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}""")