nci-cidc-schemas 0.27.5__tar.gz → 0.27.7__tar.gz

{nci_cidc_schemas-0.27.5/nci_cidc_schemas.egg-info → nci_cidc_schemas-0.27.7}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.5
+Version: 0.27.7
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -37,6 +37,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/cidc_schemas/__init__.py

@@ -2,4 +2,4 @@
 
 __author__ = """NCI"""
 __email__ = "nci-cidc-tools-admin@mail.nih.gov"
-__version__ = "0.27.05"
+__version__ = "0.27.07"

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/cidc_schemas/schemas/sample.json

@@ -168,16 +168,30 @@
             "description": "Indicates the specimen source of the sample shipped. Example: Na Heparin blood draw aliquots (2 of three), FFPE block #52",
             "type": "string",
             "enum": [
-                "Blood Draw",
-                "Excision",
+                "Fine Needle Aspiration",
+                "Phlebotomy",
+                "Bone Marrow Aspiration",
+                "Bone Marrow Core Biopsy",
                 "Core Biopsy",
-                "Punch Biopsy",
                 "Endoscopic Biopsy",
-                "Bone Marrow Core Biopsy",
-                "Bone Marrow Aspirate",
+                "Surgical Excision",
+                "Fine Needle Aspiration",
                 "Lumbar Puncture",
-                "Aspirate",
-                "Fine-Needle Aspiration",
+                "FFPE Block Punch Biopsy",
+                "Skin Biopsy",
+                "Apheresis",
+                "Bone Biopsy",
+                "Bronchoalveolar Lavage",
+                "Buccal Swab",
+                "Leukapheresis",
+                "Mid Stream Urine Collection",
+                "Peritoneal Lavage",
+                "Peritoneal Paracentesis",
+                "Pleural Thoracentesis",
+                "Saliva Collection",
+                "Stool Collection",
+                "Surgical Incision",
+                "Urine Voiding",
                 "Not Reported",
                 "Other"
             ]

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/cidc_schemas/schemas/templates/analyses/wes_analysis_template.json

@@ -293,63 +293,63 @@
                             "type_ref": "sample.json#properties/cimac_id",
                             "process_as": [
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/align/{id}/{id}.sorted.dedup.bam'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/align/{run_id}/{normal_id}.sorted.dedup.bam'",
                                     "merge_pointer": "/normal/alignment/align_sorted_dedup",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/sorted.dedup.bam",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/align/{id}/{id}.sorted.dedup.bam.bai'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/align/{run_id}/{normal_id}.sorted.dedup.bam.bai'",
                                     "merge_pointer": "/normal/alignment/align_sorted_dedup_index",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/sorted.dedup.bam.bai",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/align/{id}/{id}_recalibrated.bam'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/align/{run_id}/{normal_id}_recalibrated.bam'",
                                     "merge_pointer": "/normal/alignment/align_recalibrated",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/recalibrated.bam",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/align/{id}/{id}_recalibrated.bam.bai'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/align/{run_id}/{normal_id}_recalibrated.bam.bai'",
                                     "merge_pointer": "/normal/alignment/align_recalibrated_index",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/recalibrated.bam.bai",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/germline/{id}/{id}_haplotyper.output.vcf'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/germline/{run_id}/{normal_id}_haplotyper.output.vcf'",
                                     "merge_pointer": "/normal/germline/haplotyper_output",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/haplotyper_output.vcf",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/germline/{id}/{id}_haplotyper.targets.vcf.gz'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/germline/{run_id}/{normal_id}_haplotyper.targets.vcf.gz'",
                                     "merge_pointer": "/normal/germline/haplotyper_targets",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/haplotyper_targets.vcf.gz",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/hlahd/{id}/result/{id}_final.result.txt'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/hlahd/{run_id}/result/{normal_id}_final.result.txt'",
                                     "merge_pointer": "/normal/hla/hla_final_result",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/hla_final_result.txt",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/optitype/{id}/{id}_result.tsv'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/optitype/{run_id}/{normal_id}_result.tsv'",
                                     "merge_pointer": "/normal/hla/optitype_result",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/optitype_result.tsv",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",
                                     "is_artifact": 1
                                 },
                                 {
-                                    "parse_through": "lambda id: f'{folder or \"\"}analysis/xhla/{id}/report-{id}-hla.json'",
+                                    "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/xhla/{run_id}/report-{normal_id}-hla.json'",
                                     "merge_pointer": "/normal/hla/xhla_report_hla",
                                     "gcs_uri_format": "{protocol identifier}/wes/{run id}/analysis/normal/{normal cimac id}/xhla_report_hla.json",
                                     "type_ref": "assays/components/local_file.json#properties/file_path",

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/cidc_schemas/template.py

@@ -750,7 +750,7 @@ class _FieldDef(NamedTuple):
 
         if self.parse_through:
             try:
-                raw_val = eval(self.parse_through, format_context, {})(raw_val)
+                raw_val = self._eval_lambda_expression(raw_val, format_context)
 
             # catching everything, because of eval
             except Exception as e:
@@ -786,6 +786,41 @@ class _FieldDef(NamedTuple):
         else:
             return [AtomicChange(self.merge_pointer, val)], files
 
+    def _eval_lambda_expression(self, raw_val: str, format_context: dict):
+        """
+        Evaluates a lambda expression stored in `self.parse_through`, optionally
+        passing an additional parameter if the lambda function has two parameters.
+
+        Args:
+            raw_val (str): Initial value to process.
+            format_context (dict): Dictionary providing format context.
+
+        Returns:
+            Processed value after applying the lambda function.
+        """
+        parse_lambda = self.parse_through
+        # Check for multiple lambda parameters
+        if (
+            parse_lambda.startswith("lambda ")
+            and ":" in parse_lambda
+            and "," in parse_lambda
+        ):
+            # Extract the parameter section (between "lambda " and ":")
+            colon_index = parse_lambda.find(":")
+            param_section = parse_lambda[7:colon_index].strip()
+            params = [param.strip() for param in param_section.split(",")]
+
+            # Handles up to two parameters at this time
+            if len(params) == 2:
+                # Convert underscores to spaces to match column header formatting
+                param_name = params[1].replace("_", " ")
+                extra_val = format_context.get(param_name)
+                # Evaluate the lambda function with two parameters
+                return eval(parse_lambda, format_context, {})(raw_val, extra_val)
+
+        # Evaluate the lambda function with one parameter
+        return eval(parse_lambda, format_context, {})(raw_val)
+
     ## TODO easy - split val coerce / files calc to handle exceptions separately
     ## TODO hard - files (artifact and multi) should be just coerce?
     def _calc_val_and_files(self, raw_val, format_context: dict, encrypt_fn: Callable):

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7/nci_cidc_schemas.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.5
+Version: 0.27.7
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -37,6 +37,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/tests/data/clinicaltrial_examples/CT_1PA_multiWES.json

@@ -96,7 +96,7 @@
                     "box_number": "1",
                     "sample_location": "A4",
                     "type_of_sample": "Whole Blood",
-                    "sample_collection_procedure": "Blood Draw",
+                    "sample_collection_procedure": "Surgical Excision",
                     "type_of_primary_container": "EDTA Tube",
                     "type_of_primary_container_other": "Other",
                     "processed_sample_type": "Bone Marrow Film",
@@ -129,7 +129,7 @@
                     "box_number": "1",
                     "sample_location": "A5",
                     "type_of_sample": "Whole Blood",
-                    "sample_collection_procedure": "Blood Draw",
+                    "sample_collection_procedure": "Surgical Excision",
                     "type_of_primary_container": "EDTA Tube",
                     "type_of_primary_container_other": "Other",
                     "processed_sample_type": "Bone Marrow Film",
@@ -162,7 +162,7 @@
                     "box_number": "1",
                     "sample_location": "A6",
                     "type_of_sample": "Whole Blood",
-                    "sample_collection_procedure": "Blood Draw",
+                    "sample_collection_procedure": "Surgical Excision",
                     "type_of_primary_container": "EDTA Tube",
                     "type_of_primary_container_other": "Other",
                     "processed_sample_type": "Bone Marrow Film",

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/tests/data/clinicaltrial_examples/CT_cytof_with_analysis.json

@@ -199,7 +199,7 @@
           "type_of_primary_container": "Sodium Heparin Tube",
           "type_of_primary_container_other": "Other",
           "material_storage_condition": "Ambient",
-          "sample_collection_procedure": "Blood Draw",
+          "sample_collection_procedure": "Surgical Excision",
           "processed_sample_volume_units": "Microliters"
         },
         {
@@ -223,7 +223,7 @@
           "type_of_primary_container": "Sodium Heparin Tube",
           "type_of_primary_container_other": "Other",
           "material_storage_condition": "Ambient",
-          "sample_collection_procedure": "Blood Draw",
+          "sample_collection_procedure": "Surgical Excision",
           "processed_sample_volume_units": "Microliters"
         }
       ],

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/tests/prism/cidc_test_data/manifest_data.py

@@ -787,7 +787,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A1",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",
@@ -822,7 +822,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A2",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",
@@ -857,7 +857,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A3",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",
@@ -898,7 +898,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A4",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",
@@ -932,7 +932,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A5",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",
@@ -966,7 +966,7 @@ def normal_blood_dna() -> PrismTestData:
                         "box_number": "1",
                         "sample_location": "A6",
                         "type_of_sample": "Whole Blood",
-                        "sample_collection_procedure": "Blood Draw",
+                        "sample_collection_procedure": "Surgical Excision",
                         "type_of_primary_container": "EDTA Tube",
                         "type_of_primary_container_other": "Other",
                         "processed_sample_type": "Bone Marrow Film",

{nci_cidc_schemas-0.27.5 → nci_cidc_schemas-0.27.7}/tests/test_template.py

@@ -676,3 +676,35 @@ def test_fixation_stabilization_type(fixation_type, expected):
     else:
         with pytest.raises(ValueError):
             validate_fixation_stabilization_type(fixation_type)
+
+
+def test_eval_lambda_expression():
+    prop_def_1 = {
+        "parse_through": "lambda id: f'{folder or \"\"}analysis/optitype/{id}/{id}_result.tsv'",
+        "merge_pointer": "/tumor/hla/optitype_result",
+        "is_artifact": 1,
+        "coerce": int,
+        "key_name": "prop1",
+    }
+    raw_val = "test_value"
+    format_context = {"run id": "test_run_id", "folder": "test_folder/"}
+
+    field_def = _FieldDef(**prop_def_1)
+    eval_value = field_def._eval_lambda_expression(raw_val, format_context)
+    assert (
+        eval_value == "test_folder/analysis/optitype/test_value/test_value_result.tsv"
+    )
+
+    prop_def_2 = {
+        "parse_through": "lambda normal_id, run_id: f'{folder or \"\"}analysis/align/{run_id}/{normal_id}.sorted.dedup.bam'",
+        "merge_pointer": "/normal/alignment/align_sorted_dedup",
+        "is_artifact": 1,
+        "coerce": int,
+        "key_name": "prop2",
+    }
+    field_def = _FieldDef(**prop_def_2)
+    eval_value = field_def._eval_lambda_expression(raw_val, format_context)
+    assert (
+        eval_value
+        == "test_folder/analysis/align/test_run_id/test_value.sorted.dedup.bam"
+    )