Merge pull request #40 from brain-bican/author_annotation_fields

Author annotation fields

Author: hkir-dev

setup.py

@@ -8,7 +8,7 @@
 
 setup(
     name="tdta",
-    version="0.1.0.dev10",
+    version="0.1.0.dev11",
     description="The aim of this project is to provide taxonomy development tools custom actions.",
     long_description=README,
     long_description_content_type="text/markdown",

src/tdta/tdt_export.py

@@ -4,6 +4,7 @@
 import json
 from contextlib import closing
 from pathlib import Path
+from datetime import datetime
 
 from tdta.utils import read_project_config
 from cas.model import (CellTypeAnnotation, Annotation, Labelset, AnnotationTransfer, AutomatedAnnotation, Review)
@@ -35,12 +36,13 @@ def export_cas_data(sqlite_db: str, output_file: str, dataset_cache_folder: str
             parse_labelset_data(cta, sqlite_db, table_name)
         elif table_name == "annotation_transfer":
             parse_annotation_transfer_data(cta, sqlite_db, table_name)
-        elif table_name == "review":
-            parse_review_data(cta, sqlite_db, table_name)
+        # elif table_name == "review":
+        #     # don't export reviews to the CAS json for now
+        #     parse_review_data(cta, sqlite_db, table_name)
 
     project_config = read_project_config(Path(output_file).parent.absolute())
 
-    if "matrix_file_id" in project_config:
+    if project_config and "matrix_file_id" in project_config:
         matrix_file_id = str(project_config["matrix_file_id"]).strip()
         anndata = resolve_matrix_file(matrix_file_id, dataset_cache_folder)
         labelsets = cta.labelsets.copy()
@@ -163,6 +165,7 @@ def parse_annotation_transfer_data(cta, sqlite_db, table_name):
                             else:
                                 filtered_annotations[0].transferred_annotations = [at]
 
+
 def parse_review_data(cta, sqlite_db, table_name):
     """
     Reads 'Annotation Review' table data into the CAS object
@@ -180,8 +183,10 @@ def parse_review_data(cta, sqlite_db, table_name):
                         filtered_annotations = [a for a in cta.annotations
                                                 if a.cell_set_accession == row[columns.index("target_node_accession")]]
                         if filtered_annotations:
-                            ar = Review("", "", "", "", "")
+                            ar = Review(None, "", "", "")
                             auto_fill_object_from_row(ar, columns, row)
+                            if ar.datestamp and isinstance(ar.datestamp, str):
+                                ar.datestamp = datetime.strptime(ar.datestamp, '%Y-%m-%dT%H:%M:%S.%fZ')
                             if filtered_annotations[0].reviews:
                                 filtered_annotations[0].reviews.append(ar)
                             else:

src/test/tdt_export_test.py

@@ -22,8 +22,10 @@ def test_export(self):
 
         self.assertTrue("author_name" in result)
         self.assertEqual("Nelson Johansen", result["author_name"])
-        self.assertFalse("orcid" in result)
-        self.assertFalse("cellannotation_schema_version" in result)
+        self.assertTrue("orcid" in result)
+        self.assertEqual("https://orcid.org/0000-0002-4436-969X", result["orcid"])
+        self.assertTrue("cellannotation_schema_version" in result)
+        self.assertEqual("0.2b0", result["cellannotation_schema_version"])
 
         self.assertTrue("labelsets" in result)
         self.assertEqual(4, len(result["labelsets"]))
@@ -37,8 +39,8 @@ def test_export(self):
         self.assertEqual(355, len(result["annotations"]))
         # print(result["annotations"][:3])
         test_annotation = [x for x in result["annotations"] if x["cell_label"] == "1_MSN"][0]
-        self.assertEqual("D1-Matrix", test_annotation["parent_cell_set_name"])
         self.assertEqual("AIT115_300", test_annotation["parent_cell_set_accession"])
+        self.assertFalse("parent_cell_set_name" in test_annotation)
         self.assertFalse("marker_gene_evidence" in test_annotation)
         # self.assertEqual(3, len(test_annotation["marker_gene_evidence"]))
         # self.assertTrue("EPYC" in test_annotation["marker_gene_evidence"])
@@ -48,6 +50,16 @@ def test_export(self):
         self.assertFalse("rationale_dois" in test_annotation)
 
         self.assertTrue("author_annotation_fields" in test_annotation)
-        self.assertEqual(12, len(test_annotation["author_annotation_fields"]))
+        print(test_annotation["author_annotation_fields"])
+        self.assertEqual(11, len(test_annotation["author_annotation_fields"]))
         self.assertEqual('16393', test_annotation["author_annotation_fields"]['Cluster size'])
         self.assertEqual('PuR(0.52) | CaH(0.39)', test_annotation["author_annotation_fields"]['region.info _Frequency_'])
+
+        self.assertFalse("reviews" in test_annotation)
+        # self.assertTrue("reviews" in test_annotation)
+        # self.assertEqual(1, len(test_annotation["reviews"]))
+        # self.assertEqual('hkir-dev', test_annotation["reviews"][0]['reviewer'])
+        # self.assertEqual('Disagree', test_annotation["reviews"][0]['review'])
+        # self.assertEqual('incorrect', test_annotation["reviews"][0]['explanation'])
+        # print(test_annotation["reviews"][0]['datestamp'])
+        # self.assertEqual('2024-05-29T08:10:11.126Z', test_annotation["reviews"][0]['datestamp'])