Airr2akc refactor

.gitmodules

@@ -0,0 +1,6 @@
+[submodule "src/airr_schema/airr-standards-v1.5"]
+	path = src/airr_schema/airr-standards-v1.5
+	url = https://github.com/airr-community/airr-standards.git
+[submodule "src/airr_schema/airr-standards-v2.0"]
+	path = src/airr_schema/airr-standards-v2.0
+	url = https://github.com/airr-community/airr-standards.git

Dockerfile

@@ -2,8 +2,7 @@
 FROM python:3.9
 
 # Install jq so we can process JSON
-RUN apt-get update
-RUN apt-get install jq -y
+RUN apt-get update && apt-get install jq -y
 
 # https://stackoverflow.com/questions/53835198/integrating-python-poetry-with-docker
 ENV YOUR_ENV=${YOUR_ENV} \

Makefile.AIRR

@@ -1,105 +1,17 @@
-AIRR_SCHEMA_DIR=src/ak_schema/schema/airr
+AIRR_SCHEMA_OUTPUT_DIR=src/ak_schema/schema
 SCRIPT_DIR=src/scripts/airr2akc
+AIRR_SCHEMA_V1.5_INPUT=src/airr_schema/airr-standards-v1.5/specs/airr-schema-openapi3.yaml
+AIRR_SCHEMA_V2.0_INPUT=src/airr_schema/airr-standards-v2.0/specs/airr-schema-openapi3.yaml
+LOGFILE_DIR=logs
 
-airr: repertoire rearrangement clone cell receptor germline
+all: airr_schema airr_schema_1.5 airr_schema_2.0
 
-repertoire: Study Subject Diagnosis Genotype MHCGenotype Sample PCRTarget CellProcessing NucleicAcidProcessing SequencingRun SequencingData DataProcessing Repertoire
+airr_schema:
+	python $(SCRIPT_DIR)/airr2akc.py -o $(AIRR_SCHEMA_OUTPUT_DIR)/ak_airr.yaml -a $(AIRR_SCHEMA_V1.5_INPUT) -f $(AIRR_SCHEMA_OUTPUT_DIR) -l $(LOGFILE_DIR)/airr2akc.log
 
-rearrangement: Rearrangement
+airr_schema_1.5:
+	python $(SCRIPT_DIR)/airr2akc.py -o $(AIRR_SCHEMA_OUTPUT_DIR)/ak_airr_v1.5.yaml -a $(AIRR_SCHEMA_V1.5_INPUT) -f $(AIRR_SCHEMA_OUTPUT_DIR) -l $(LOGFILE_DIR)/airr2akc_v1.5.log -v
 
-clone: Clone
-
-cell: Cell Expression Reactivity
-
-receptor: Receptor
-
-germline: GermlineSet AlleleDescription SequenceDelineationV RearrangedSequence UnrearrangedSequence
-
-Study:
-	python $(SCRIPT_DIR)/airr2akc.py Study > $(AIRR_SCHEMA_DIR)/ak_slot_Study.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Study > $(AIRR_SCHEMA_DIR)/ak_enum_Study.yaml
-Subject:
-	python $(SCRIPT_DIR)/airr2akc.py Subject > $(AIRR_SCHEMA_DIR)/ak_slot_Subject.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Subject > $(AIRR_SCHEMA_DIR)/ak_enum_Subject.yaml
-Diagnosis:
-	python $(SCRIPT_DIR)/airr2akc.py Diagnosis > $(AIRR_SCHEMA_DIR)/ak_slot_Diagnosis.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Diagnosis > $(AIRR_SCHEMA_DIR)/ak_enum_Diagnosis.yaml
-Genotype:
-	python $(SCRIPT_DIR)/airr2akc.py Genotype > $(AIRR_SCHEMA_DIR)/ak_slot_Genotype.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Genotype > $(AIRR_SCHEMA_DIR)/ak_enum_Genotype.yaml
-MHCGenotype:
-	python $(SCRIPT_DIR)/airr2akc.py MHCGenotype > $(AIRR_SCHEMA_DIR)/ak_slot_MHCGenotype.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e MHCGenotype > $(AIRR_SCHEMA_DIR)/ak_enum_MHCGenotype.yaml
-Sample:
-	python $(SCRIPT_DIR)/airr2akc.py Sample > $(AIRR_SCHEMA_DIR)/ak_slot_Sample.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Sample > $(AIRR_SCHEMA_DIR)/ak_enum_Sample.yaml
-PCRTarget:
-	python $(SCRIPT_DIR)/airr2akc.py PCRTarget > $(AIRR_SCHEMA_DIR)/ak_slot_PCRTarget.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e PCRTarget > $(AIRR_SCHEMA_DIR)/ak_enum_PCRTarget.yaml
-CellProcessing:
-	python $(SCRIPT_DIR)/airr2akc.py CellProcessing > $(AIRR_SCHEMA_DIR)/ak_slot_CellProcessing.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e CellProcessing > $(AIRR_SCHEMA_DIR)/ak_enum_CellProcessing.yaml
-NucleicAcidProcessing:
-	python $(SCRIPT_DIR)/airr2akc.py NucleicAcidProcessing > $(AIRR_SCHEMA_DIR)/ak_slot_NucleicAcidProcessing.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e NucleicAcidProcessing > $(AIRR_SCHEMA_DIR)/ak_enum_NucleicAcidProcessing.yaml
-SequencingRun:
-	python $(SCRIPT_DIR)/airr2akc.py SequencingRun > $(AIRR_SCHEMA_DIR)/ak_slot_SequencingRun.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e SequencingRun > $(AIRR_SCHEMA_DIR)/ak_enum_SequencingRun.yaml
-SequencingData:
-	python $(SCRIPT_DIR)/airr2akc.py SequencingData > $(AIRR_SCHEMA_DIR)/ak_slot_SequencingData.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e SequencingData > $(AIRR_SCHEMA_DIR)/ak_enum_SequencingData.yaml
-DataProcessing:
-	python $(SCRIPT_DIR)/airr2akc.py DataProcessing > $(AIRR_SCHEMA_DIR)/ak_slot_DataProcessing.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e DataProcessing > $(AIRR_SCHEMA_DIR)/ak_enum_DataProcessing.yaml
-Repertoire:
-	python $(SCRIPT_DIR)/airr2akc.py Repertoire > $(AIRR_SCHEMA_DIR)/ak_slot_Repertoire.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Repertoire > $(AIRR_SCHEMA_DIR)/ak_enum_Repertoire.yaml
-#
-# Rearrangement rules
-# 
-Rearrangement:
-	python $(SCRIPT_DIR)/airr2akc.py Rearrangement > $(AIRR_SCHEMA_DIR)/ak_slot_Rearrangement.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Rearrangement > $(AIRR_SCHEMA_DIR)/ak_enum_Rearrangement.yaml
-#
-# Clone rules
-# 
-Clone:
-	python $(SCRIPT_DIR)/airr2akc.py Clone > $(AIRR_SCHEMA_DIR)/ak_slot_Clone.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Clone > $(AIRR_SCHEMA_DIR)/ak_enum_Clone.yaml
-#
-# Cell rules
-# 
-Cell:
-	python $(SCRIPT_DIR)/airr2akc.py Cell > $(AIRR_SCHEMA_DIR)/ak_slot_Cell.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Cell > $(AIRR_SCHEMA_DIR)/ak_enum_Cell.yaml
-Expression:
-	python $(SCRIPT_DIR)/airr2akc.py CellExpression > $(AIRR_SCHEMA_DIR)/ak_slot_CellExpression.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e CellExpression > $(AIRR_SCHEMA_DIR)/ak_enum_CellExpression.yaml
-Reactivity:
-	python $(SCRIPT_DIR)/airr2akc.py ReceptorReactivity > $(AIRR_SCHEMA_DIR)/ak_slot_ReceptorReactivity.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e ReceptorReactivity > $(AIRR_SCHEMA_DIR)/ak_enum_ReceptorReactivity.yaml
-#
-# Rearrangement rules
-# 
-Receptor:
-	python $(SCRIPT_DIR)/airr2akc.py Receptor > $(AIRR_SCHEMA_DIR)/ak_slot_Receptor.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e Receptor > $(AIRR_SCHEMA_DIR)/ak_enum_Receptor.yaml
-#
-# Germline rules
-# 
-GermlineSet:
-	python $(SCRIPT_DIR)/airr2akc.py GermlineSet > $(AIRR_SCHEMA_DIR)/ak_slot_GermlineSet.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e GermlineSet > $(AIRR_SCHEMA_DIR)/ak_enum_GermlineSet.yaml
-AlleleDescription:
-	python $(SCRIPT_DIR)/airr2akc.py AlleleDescription > $(AIRR_SCHEMA_DIR)/ak_slot_AlleleDescription.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e AlleleDescription > $(AIRR_SCHEMA_DIR)/ak_enum_AlleleDescription.yaml
-RearrangedSequence:
-	python $(SCRIPT_DIR)/airr2akc.py RearrangedSequence > $(AIRR_SCHEMA_DIR)/ak_slot_RearrangedSequence.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e RearrangedSequence > $(AIRR_SCHEMA_DIR)/ak_enum_RearrangedSequence.yaml
-UnrearrangedSequence:
-	python $(SCRIPT_DIR)/airr2akc.py UnrearrangedSequence > $(AIRR_SCHEMA_DIR)/ak_slot_UnrearrangedSequence.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e UnrearrangedSequence > $(AIRR_SCHEMA_DIR)/ak_enum_UnrearrangedSequence.yaml
-SequenceDelineationV:
-	python $(SCRIPT_DIR)/airr2akc.py SequenceDelineationV > $(AIRR_SCHEMA_DIR)/ak_slot_SequenceDelineationV.yaml
-	python $(SCRIPT_DIR)/airr2akc.py -e SequenceDelineationV > $(AIRR_SCHEMA_DIR)/ak_enum_SequenceDelineationV.yaml
+airr_schema_2.0:
+	python $(SCRIPT_DIR)/airr2akc.py -o $(AIRR_SCHEMA_OUTPUT_DIR)/ak_airr_v2.0.yaml -a $(AIRR_SCHEMA_V2.0_INPUT) -f $(AIRR_SCHEMA_OUTPUT_DIR) -l $(LOGFILE_DIR)/airr2akc_v2.0.log -v
 

README.md

@@ -20,6 +20,15 @@ AIRR Knowledge Data Model
 
 ## Developer Documentation
 
+This repository now contains submodules. When doing a `git clone`, those submodules are
+not automatically populated, and additional command is required.
+
+```
+git clone https://airr-knowledge.github.com/ak-schema
+cd ak-schema
+git submodule update --init --recursive
+```
+
 Use the docker container to have a consistent development environment.
 
 * `docker pull airrknowledge/ak-schema:tag`: pull published container for specific tagged version.

examples/iedb/example.json

@@ -108,7 +108,6 @@
       "specimen": "example:specimen-3480642",
       "type": "TCellReceptorEpitopeBindingAssay",
       "assay_type": "OBI:1110179",
-      "value": "Positive",
       "epitope": "iedb_epitope:20788",
       "tcell_receptors": [
         "iedb_receptor:20833",
@@ -800,7 +799,8 @@
         "iedb_receptor:24245",
         "iedb_receptor:24246",
         "iedb_receptor:24247"
-      ]
+      ],
+      "value": "Positive"
     }
   },
   "datasets": {

examples/iedb/example.yaml

@@ -89,7 +89,6 @@ assays:
     specimen: example:specimen-3480642
     type: TCellReceptorEpitopeBindingAssay
     assay_type: OBI:1110179
-    value: Positive
     epitope: iedb_epitope:20788
     tcell_receptors:
     - iedb_receptor:20833
@@ -781,6 +780,7 @@ assays:
     - iedb_receptor:24245
     - iedb_receptor:24246
     - iedb_receptor:24247
+    value: Positive
 datasets:
   example:dataset-3480642:
     akc_id: example:dataset-3480642

logs/.gitignore

@@ -0,0 +1 @@
+*.log