generate new version of the linkml model

puja-trivedi · Oct 3, 2024 · 44f2c83 · 44f2c83
1 parent 75f9ccf
commit 44f2c83
Show file tree

Hide file tree

Showing 7 changed files with 153 additions and 112 deletions.
diff --git a/linkml-schema/library_generation.yaml b/linkml-schema/library_generation.yaml
@@ -6,6 +6,8 @@ title: Library Generation Schema
 id: https://identifiers.org/brain-bican/library-generation-schema
 imports:
 - bican_biolink
+- bican_prov
+- bican_core
 - linkml:types
 prefixes:
   linkml: https://w3id.org/linkml/
@@ -1822,23 +1824,15 @@ enums:
         meaning: NIMP:PD-AVAVEV39
 slots:
   was_derived_from:
-    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.
-    slot_uri: prov:wasDerivedFrom
-    range: ProvEntity
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
   used:
-    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.
-    slot_uri: prov:used
-    range: ProvEntity
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
   was_generated_by:
-    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.
-    slot_uri: prov:wasGeneratedBy
-    range: ProvActivity
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
+  digest:
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
+  content_url:
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
 classes:
   Donor:
     description: A person or organism that is the source of a biological sample for
@@ -1854,6 +1848,9 @@ classes:
     - name
     slot_usage:
       name:
+        local_names:
+          local_name_value: donor_local_id
+          local_name_source: NIMP
         description: Name of person or organism that is the source of a biological
           sample for scientific study.  Many biological samples are generated from
           a single donor.
@@ -1915,6 +1912,7 @@ classes:
       species:
         local_names:
           local_name_value: donor_species
+          local_name_source: NIMP
         description: Species of donor.
         from_schema: https://identifiers.org/brain-bican/library-generation-schema
         slot_uri: bican:6837cb02-6bd7-4fb8-838c-9062ead96ba4
@@ -1941,11 +1939,13 @@ classes:
         description: The donor from which the brain slab was derived from.
         exact_mappings:
         - NIMP:has_parent
-        range: Donor
-        exactly_one_of:
+        any_of:
         - range: Donor
         - range: BrainSlab
       name:
+        local_names:
+          local_name_value: local_name
+          local_name_source: NIMP
         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
@@ -1981,6 +1981,9 @@ classes:
           by.
         range: TissueDissection
       name:
+        local_names:
+          local_name_value: tissue_sample_local_name
+          local_name_source: NIMP
         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.
@@ -1999,10 +2002,11 @@ classes:
       structure:
         local_names:
           local_name_value: structure
+          local_name_source: NIMP
         description: Strucure of tissue sample.
         from_schema: https://identifiers.org/brain-bican/library-generation-schema
-        multivalued: true
         alias: tissue_sample_structure
+        multivalued: true
   DissociatedCellSample:
     description: A collection of dissociated cells or nuclei derived from dissociation
       of a tissue sample.
@@ -2029,9 +2033,12 @@ classes:
           was derived from.
         exact_mappings:
         - NIMP:has_parent
-        multivalued: true
         range: TissueSample
+        multivalued: true
       name:
+        local_names:
+          local_name_value: dissociated_cell_sample_local_name
+          local_name_source: NIMP
         description: Name of a collection of dissociated cells or nuclei derived from
           dissociation of a tissue sample.
         exact_mappings:
@@ -2092,7 +2099,7 @@ classes:
       was_generated_by:
         description: The cell enrichment or sample splitting process from which the
           enriched cell sample was generated by.
-        exactly_one_of:
+        any_of:
         - range: CellEnrichment
         - range: EnrichedCellSampleSplitting
       was_derived_from:
@@ -2105,6 +2112,9 @@ classes:
         - range: DissociatedCellSample
         - range: EnrichedCellSample
       name:
+        local_names:
+          local_name_value: enriched_cell_sample_local_name
+          local_name_source: NIMP
         description: Name of collection of enriched cells or nuclei after enrichment
           process (usually via FACS using the Enrichment Plan) applied to dissociated_cell_sample.
         exact_mappings:
@@ -2190,6 +2200,9 @@ classes:
         - range: DissociatedCellSample
         - range: EnrichedCellSample
       name:
+        local_names:
+          local_name_value: barcoded_cell_sample_local_name
+          local_name_source: NIMP
         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
@@ -2248,6 +2261,9 @@ classes:
         - NIMP:has_parent
         range: BarcodedCellSample
       name:
+        local_names:
+          local_name_value: amplified_cdna_local_name
+          local_name_source: NIMP
         description: Name of a collection of cDNA molecules derived and amplified
           from an input barcoded_cell_sample.  These cDNA molecules represent the
           gene expression of each cell, with all cDNA molecules from a given cell
@@ -2330,10 +2346,13 @@ classes:
           library was derived from.
         exact_mappings:
         - NIMP:has_parent
-        exactly_one_of:
+        any_of:
         - range: BarcodedCellSample
         - range: AmplifiedCdna
       name:
+        local_names:
+          local_name_value: library_local_name
+          local_name_source: NIMP
         description: Name of a library, which is a collection of fragmented and barcode-indexed
           DNA molecules for sequencing.  An index or barcode is typically introduced
           to enable identification of library origin to allow libraries to be pooled
@@ -2456,6 +2475,9 @@ classes:
         - NIMP:has_parent
         range: Library
       name:
+        local_names:
+          local_name_value: library_aliquot_local_name
+          local_name_source: NIMP
         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
@@ -2494,9 +2516,12 @@ classes:
           from.
         exact_mappings:
         - NIMP:has_parent
-        multivalued: true
         range: LibraryAliquot
+        multivalued: true
       name:
+        local_names:
+          local_name_value: library_pool_local_name
+          local_name_source: NIMP
         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
@@ -2584,8 +2609,8 @@ classes:
       used:
         description: The input tissue sample(s) from which the dissociated cell sample
           was derived from.
-        multivalued: true
         range: TissueSample
+        multivalued: true
       category:
         pattern: ^bican:[A-Z][A-Za-z]+$
     attributes:
@@ -2616,8 +2641,8 @@ classes:
       used:
         description: The input dissociated cell sample(s) from which the enriched
           cell sample was derived from.
-        multivalued: true
         range: DissociatedCellSample
+        multivalued: true
       category:
         pattern: ^bican:[A-Z][A-Za-z]+$
     attributes:
@@ -2804,7 +2829,7 @@ classes:
       used:
         description: The input barcoded cell sample or amplified cDNA from which the
           library was derived from.
-        exactly_one_of:
+        any_of:
         - range: BarcodedCellSample
         - range: AmplifiedCdna
       category:
@@ -2885,8 +2910,8 @@ classes:
       used:
         description: The input aliquot(s) from which the library pool was derived
           from.
-        multivalued: true
         range: LibraryAliquot
+        multivalued: true
       category:
         pattern: ^bican:[A-Z][A-Za-z]+$
     attributes:
@@ -2919,6 +2944,9 @@ classes:
           was generated by.
         range: DissectionRoiDelineation
       name:
+        local_names:
+          local_name_value: local_name
+          local_name_source: NIMP
         description: Name of a polygon annotated on a brain slab image delineating
           a region of interest (ROI) for a tissue sample dissectioning.
       category:
@@ -2930,19 +2958,23 @@ classes:
         exact_mappings:
         - NIMP:has_parent
         range: BrainSlab
-  ProvActivity:
-    mixin: true
-    description: 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.
-    slots:
-    - used
-    class_uri: prov:Activity
-  ProvEntity:
-    mixin: true
-    description: An entity is a physical, digital, conceptual, or other kind of thing
-      with some fixed aspects;  entities may be real or imaginary.
+  DigitalAsset:
+    from_schema: https://identifiers.org/brain-bican/library-generation-schema
+    is_a: dataset
+    mixins:
+    - ProvEntity
     slots:
     - was_derived_from
-    - was_generated_by
-    class_uri: prov:Entity
+    - digest
+    - content_url
+    slot_usage:
+      was_derived_from:
+        range: LibraryPool
+      digest: {}
+      content_url: {}
+      category:
+        pattern: ^bican:[A-Z][A-Za-z]+$
+    attributes:
+      data_type:
+        description: The type of data in the file
+        from_schema: https://identifiers.org/brain-bican/library-generation-schema
diff --git a/linkml-schema/source_library_generation/gsheet_output/Classes.tsv b/linkml-schema/source_library_generation/gsheet_output/Classes.tsv
@@ -20,4 +20,5 @@ CellBarcoding	procedure	ProvActivity		bican|library_generation	The process of ad
 CdnaAmplification	procedure	ProvActivity		bican|library_generation	The process of creating a collection of cDNA molecules derived and amplified from an input barcoded cell sample.  A large amount of cDNA is needed to have accurate and reliable sequencing detection of gene expression.  This process generates multiple copies of each mRNA transcript (expressed gene) within each cell while retaining the cell's unique barcode from the barcoding step. This is a necessary step for GEX methods but is not used for ATAC methods.			
 LibraryConstruction	procedure	ProvActivity		bican|library_generation	The process of constructing a library from input material (such as amplified cDNA or barcoded cell sample) derived from one or more cell samples.  cDNA is fragmented into smaller pieces appropriate for sequencing and at the same time a library index barcode is incorporated to enable identification of library origin, allowing libraries to be pooled together for sequencing.			
 LibraryPooling	procedure	ProvActivity		bican|library_generation	The process of constructing of a libray pool by combining library aliquots from a set of input 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.			
-DissectionRoiPolygon	entity	ProvEntity		bican|tissue_specimen	A polygon annotated on a brain slab image delineating a region of interest (ROI) for a tissue sample dissectioning.	Specimen Dissected ROI		
+DissectionRoiPolygon	entity	ProvEntity		bican|tissue_specimen	A polygon annotated on a brain slab image delineating a region of interest (ROI) for a tissue sample dissectioning.	Specimen Dissected ROI		
+DigitalAsset	dataset	ProvEntity