feat: replace experimenter_full_name with Investigator class

docs/source/example_workflow/example_workflow.py

@@ -3,19 +3,20 @@
 import pandas as pd
 from aind_data_schema_models.modalities import Modality
 from aind_data_schema_models.organizations import Organization
-from aind_data_schema_models.pid_names import PIDName
 from aind_data_schema_models.platforms import Platform
 
 from aind_data_schema.core.data_description import Funding, RawDataDescription
 from aind_data_schema.core.procedures import NanojectInjection, Perfusion, Procedures, Surgery, ViralMaterial
 from aind_data_schema.core.subject import BreedingInfo, Housing, Species, Subject
 
+from aind_data_schema.components.identifiers import Person
+
 sessions_df = pd.read_excel("example_workflow.xlsx", sheet_name="sessions")
 mice_df = pd.read_excel("example_workflow.xlsx", sheet_name="mice")
 procedures_df = pd.read_excel("example_workflow.xlsx", sheet_name="procedures")
 
 # everything was done by one person, so it's not in the spreadsheet
-experimenter = "Sam Student"
+experimenter = Person(name="Some experimenter")
 
 # in our spreadsheet, we stored sex as M/F instead of Male/Female
 subject_sex_lookup = {
@@ -35,7 +36,7 @@
         subject_id=str(session["mouse_id"]),
         creation_time=session["end_time"].to_pydatetime(),
         institution=Organization.OTHER,
-        investigators=[PIDName(name="Some Investigator")],
+        experimenters=[experimenter],
         funding_source=[Funding(funder=Organization.NIMH)],
     )
 
@@ -88,7 +89,7 @@
                 start_date=proc_row["injection_date"].to_pydatetime().date(),
                 protocol_id=protocol,
                 ethics_review_id=ethics_review_id,
-                experimenter_full_name=experimenter,
+                experimenters=[experimenter],
                 procedures=[
                     NanojectInjection(
                         protocol_id=protocol,
@@ -111,7 +112,7 @@
             ),
             Surgery(
                 start_date=proc_row["perfusion_date"].to_pydatetime().date(),
-                experimenter_full_name=experimenter,
+                experimenters=[experimenter],
                 ethics_review_id=ethics_review_id,
                 protocol_id=protocol,
                 procedures=[Perfusion(protocol_id=protocol, output_specimen_ids=["1"])],

docs/source/general.rst

@@ -72,7 +72,7 @@ more ontologies into our schema. We currently use:
 
 * NCBI Taxonomy to specify species
 * Research Organization Registry (ROR) to specify organizations (including manufacturer, funders, research organizations)
-* Open Researcher and Contributor ID (ORCID) to identify investigators
+* Open Researcher and Contributor ID (ORCID) to identify experimenters
 * Research Resource Identifiers (RRID) to identify reagents and other resources
 * Addgene to identify viruses and plasmids
 * Mouse Genome Informatics (MGI) to identify transgenic alleles

examples/aibs_smartspim_procedures.json

@@ -7,7 +7,16 @@
          "procedure_type": "Surgery",
          "protocol_id": "doi_of_protocol_surgery",
          "start_date": "2022-11-17",
-         "experimenter_full_name": "LAS",
+         "experimenters": [
+            {
+               "name": "LAS",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "ethics_review_id": "xxxx",
          "animal_weight_prior": null,
          "animal_weight_post": null,
@@ -33,7 +42,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-13",
          "end_date": "2023-01-17",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -74,7 +92,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-17",
          "end_date": "2023-01-18",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -103,7 +130,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-18",
          "end_date": "2023-01-19",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -132,7 +168,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-19",
          "end_date": "2023-01-20",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -173,7 +218,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-30",
          "end_date": "2023-01-31",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -214,7 +268,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-31",
          "end_date": "2023-02-02",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],
@@ -243,7 +306,16 @@
          "specimen_id": "651286",
          "start_date": "2023-01-31",
          "end_date": "2023-02-02",
-         "experimenter_full_name": "John Smith",
+         "experimenters": [
+            {
+               "name": "John Smith",
+               "registry": {
+                  "name": "Open Researcher and Contributor ID",
+                  "abbreviation": "ORCID"
+               },
+               "registry_identifier": null
+            }
+         ],
          "protocol_id": [
             "unknown"
          ],

examples/aibs_smartspim_procedures.py

@@ -4,9 +4,10 @@
 
 from aind_data_schema_models.organizations import Organization
 
+from aind_data_schema.components.identifiers import Person
 from aind_data_schema.core import procedures
 
-experimenter = "John Smith"
+experimenters = [Person(name="John Smith")]
 # subject and specimen id can be the same?
 specimen_id = "651286"
 
@@ -35,7 +36,7 @@
 
 perfusion = procedures.Surgery(
     start_date=date(2022, 11, 17),
-    experimenter_full_name="LAS",
+    experimenters=[Person(name="LAS")],
     ethics_review_id="xxxx",
     protocol_id="doi_of_protocol_surgery",
     procedures=[
@@ -55,7 +56,7 @@
     procedure_type="Fixation",
     start_date=date(2023, 1, 13),
     end_date=date(2023, 1, 17),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[shield_buffer, shield_epoxy],
 )
@@ -67,7 +68,7 @@
     procedure_type="Fixation",
     start_date=date(2023, 1, 17),
     end_date=date(2023, 1, 18),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[
         shield_on,
@@ -81,7 +82,7 @@
     procedure_type="Soak",
     start_date=date(2023, 1, 18),
     end_date=date(2023, 1, 19),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[
         delipidation_buffer,
@@ -95,7 +96,7 @@
     procedure_name="Active Delipidation",
     start_date=date(2023, 1, 19),
     end_date=date(2023, 1, 20),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[delipidation_buffer, conductivity_buffer],
 )
@@ -107,7 +108,7 @@
     procedure_name="EasyIndex 50%",
     start_date=date(2023, 1, 30),
     end_date=date(2023, 1, 31),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[
         easy_index,
@@ -122,7 +123,7 @@
     procedure_name="EasyIndex 100%",
     start_date=date(2023, 1, 31),
     end_date=date(2023, 2, 2),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[
         easy_index,
@@ -135,7 +136,7 @@
     procedure_type="Embedding",
     start_date=date(2023, 1, 31),
     end_date=date(2023, 2, 2),
-    experimenter_full_name=experimenter,
+    experimenters=experimenters,
     protocol_id=["unknown"],
     reagents=[
         easy_index,

examples/bergamo_ophys_session.json

@@ -2,8 +2,15 @@
    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/session.py",
    "schema_version": "1.1.4",
    "protocol_id": [],
-   "experimenter_full_name": [
-      "John Doe"
+   "experimenters": [
+      {
+         "name": "John Smith",
+         "registry": {
+            "name": "Open Researcher and Contributor ID",
+            "abbreviation": "ORCID"
+         },
+         "registry_identifier": null
+      }
    ],
    "session_start_time": "2022-07-12T07:00:00Z",
    "session_end_time": "2022-07-12T07:00:00Z",

examples/bergamo_ophys_session.py

@@ -5,6 +5,7 @@
 from aind_data_schema_models.modalities import Modality
 from aind_data_schema_models.units import FrequencyUnit
 
+from aind_data_schema.components.identifiers import Person
 from aind_data_schema.components.stimulus import PhotoStimulation, PhotoStimulationGroup
 from aind_data_schema.core.session import (
     DetectorConfig,
@@ -22,7 +23,7 @@
 t = datetime(2022, 7, 12, 7, 00, 00, tzinfo=timezone.utc)
 
 s = Session(
-    experimenter_full_name=["John Doe"],
+    experimenters=[Person(name="John Smith")],
     session_start_time=t,
     session_end_time=t,
     subject_id="652567",

examples/data_description.json

@@ -39,8 +39,10 @@
    "investigators": [
       {
          "name": "Jane Smith",
-         "abbreviation": null,
-         "registry": null,
+         "registry": {
+            "name": "Open Researcher and Contributor ID",
+            "abbreviation": "ORCID"
+         },
          "registry_identifier": null
       }
    ],

examples/data_description.py

@@ -4,9 +4,9 @@
 
 from aind_data_schema_models.modalities import Modality
 from aind_data_schema_models.organizations import Organization
-from aind_data_schema_models.pid_names import PIDName
 from aind_data_schema_models.platforms import Platform
 
+from aind_data_schema.components.identifiers import Person
 from aind_data_schema.core.data_description import Funding, RawDataDescription
 
 d = RawDataDescription(
@@ -15,7 +15,7 @@
     subject_id="12345",
     creation_time=datetime(2022, 2, 21, 16, 30, 1, tzinfo=timezone.utc),
     institution=Organization.AIND,
-    investigators=[PIDName(name="Jane Smith")],
+    investigators=[Person(name="Jane Smith")],
     funding_source=[Funding(funder=Organization.AI)],
 )
 

examples/ephys_session.json

@@ -2,9 +2,15 @@
    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/session.py",
    "schema_version": "1.1.4",
    "protocol_id": [],
-   "experimenter_full_name": [
-      "Max Quibble",
-      "Finn Tickle"
+   "experimenters": [
+      {
+         "name": "John Smith",
+         "registry": {
+            "name": "Open Researcher and Contributor ID",
+            "abbreviation": "ORCID"
+         },
+         "registry_identifier": null
+      }
    ],
    "session_start_time": "2023-04-25T02:35:00Z",
    "session_end_time": "2023-04-25T03:16:00Z",

examples/ephys_session.py

@@ -5,6 +5,7 @@
 from aind_data_schema_models.modalities import Modality
 
 from aind_data_schema.components.devices import Software
+from aind_data_schema.components.identifiers import Person
 from aind_data_schema.core.session import (
     CcfCoords,
     Coordinates3d,
@@ -19,7 +20,7 @@
 from aind_data_schema_models.brain_atlas import CCFStructure
 
 session = Session(
-    experimenter_full_name=["Max Quibble", "Finn Tickle"],
+    experimenters=[Person(name="John Smith")],
     subject_id="664484",
     session_start_time=datetime(year=2023, month=4, day=25, hour=2, minute=35, second=0, tzinfo=timezone.utc),
     session_end_time=datetime(year=2023, month=4, day=25, hour=3, minute=16, second=0, tzinfo=timezone.utc),