[ENH] BEP032: Extend sample_type and add anatomical location to samples.tsv

src/modality-agnostic-files/data-summary-files.md

@@ -107,12 +107,12 @@ and a guide for using macros can be found at
 `samples.tsv` example:
 
 ```tsv
-sample_id	participant_id	sample_type	derived_from
-sample-01	sub-01	tissue	n/a
-sample-02	sub-01	tissue	sample-01
-sample-03	sub-01	tissue	sample-01
-sample-04	sub-02	tissue	n/a
-sample-05	sub-02	tissue	n/a
+sample_id	participant_id	sample_type	derived_from	anatomical_location
+sample-01	sub-01	tissue block	n/a	brain
+sample-02	sub-01	tissue slice	sample-01	brain
+sample-03	sub-01	tissue slice	sample-01	brain
+sample-04	sub-02	tissue	n/a	n/a
+sample-05	sub-02	tissue	n/a	n/a
 ```
 
 It is RECOMMENDED to accompany each `samples.tsv` file with a sidecar
@@ -124,10 +124,19 @@ It is RECOMMENDED to accompany each `samples.tsv` file with a sidecar
 ```JSON
 {
     "sample_type": {
-        "Description": "type of sample from ENCODE Biosample Type (https://www.encodeproject.org/profiles/biosample_type)"
+        "Description": "type of sample"
     },
     "derived_from": {
         "Description": "sample_id from which the sample is derived"
+    },
+    "anatomical_location": {
+        "Description": "anatomical structure the sample was taken from",
+        "Levels": {
+            "brain": {
+                "Description": "brain",
+                "TermURL": "https://purl.obolibrary.org/obo/UBERON_0000955"
+            }
+        }
     }
 }
 ```

src/schema/objects/columns.yaml

@@ -49,6 +49,17 @@ age:
     "Units": "year",
     "Maximum": 89,
   }
+anatomical_location__samples:
+  name: anatomical_location
+  display_name: Anatomical location
+  description: |
+    The anatomical structure the sample was taken from,
+    for example, `primary visual cortex`, `hippocampus`, or `brain`.
+    The ontology or atlas the terms are taken from SHOULD be documented in `samples.json`,
+    using `TermURL` for the column and, where the individual terms are resolvable, `Levels`
+    to map each term to its own `TermURL`
+    (see [Tabular files](SPEC_ROOT/common-principles.md#tabular-files)).
+  type: string
 AP_angle:
   name: AP_angle
   display_name: AP angle
@@ -783,8 +794,12 @@ sample_type:
   name: sample_type
   display_name: Sample type
   description: |
-    Biosample type defined by
-    [ENCODE Biosample Type](https://www.encodeproject.org/profiles/biosample_type).
+    The type of the sample.
+    Values are drawn from
+    [ENCODE Biosample Type](https://www.encodeproject.org/profiles/biosample_type)
+    and from the tissue sample types defined by
+    [openMINDS](https://openminds.docs.om-i.org/en/latest/instance_libraries/terminologies/tissueSampleType.html).
+    Where no listed value describes a sample, an addition to this list MAY be proposed.
   type: string
   enum:
     - $ref: objects.enums.cell_line.value
@@ -796,6 +811,11 @@ sample_type:
     - $ref: objects.enums.whole_organisms.value
     - $ref: objects.enums.organoid.value
     - $ref: objects.enums.technical_sample.value
+    - $ref: objects.enums.whole_organ.value
+    - $ref: objects.enums.tissue_block.value
+    - $ref: objects.enums.tissue_slice.value
+    - $ref: objects.enums.single_cell.value
+    - $ref: objects.enums.cell_population.value
 sampling_frequency:
   name: sampling_frequency
   display_name: Channel sampling frequency

src/schema/objects/enums.yaml

@@ -1363,6 +1363,36 @@ technical_sample:
   display_name: technical sample
   description: |
     A biosample type (`sample_type`): technical sample
+whole_organ:
+  value: whole organ
+  display_name: whole organ
+  description: |
+    A biosample type (`sample_type`): a complete organ removed from an organism,
+    for example, an extracted brain.
+tissue_block:
+  value: tissue block
+  display_name: tissue block
+  description: |
+    A biosample type (`sample_type`): a block of tissue,
+    typically one from which slices are subsequently cut.
+tissue_slice:
+  value: tissue slice
+  display_name: tissue slice
+  description: |
+    A biosample type (`sample_type`): a slice of tissue,
+    for example, an acute brain slice used for patch clamp recordings.
+single_cell:
+  value: single cell
+  display_name: single cell
+  description: |
+    A biosample type (`sample_type`): an individual cell,
+    for example, a cell recorded from in a patch clamp experiment.
+cell_population:
+  value: cell population
+  display_name: cell population
+  description: |
+    A biosample type (`sample_type`): a group of cells recorded or measured together
+    rather than individually.
 good:
   value: good
   display_name: good

src/schema/rules/tabular_data/modality_agnostic.yaml

@@ -28,6 +28,7 @@ Samples:
     sample_type: required
     pathology: recommended
     derived_from: recommended
+    anatomical_location__samples: optional
   index_columns: [sample_id, participant_id]
   additional_columns: allowed