nci-cidc-schemas 0.26.36__tar.gz → 0.26.38__tar.gz

{nci_cidc_schemas-0.26.36/nci_cidc_schemas.egg-info → nci_cidc_schemas-0.26.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nci_cidc_schemas
-Version: 0.26.36
+Version: 0.26.38
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/__init__.py

@@ -2,4 +2,4 @@
 
 __author__ = """NCI"""
 __email__ = "nci-cidc-tools-admin@mail.nih.gov"
-__version__ = "0.26.36"
+__version__ = "0.26.38"

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/json_validation.py

@@ -497,7 +497,7 @@ def convert(fmt: str, value: str) -> str:
     elif fmt == "date":
         reformatter = _to_date
     elif fmt == "string":
-        reformatter = lambda n: n and str(n)
+        reformatter = lambda n: (n or n == 0) and str(n)
     elif fmt == "integer":
         reformatter = lambda n: n and int(n)
     elif fmt == "boolean":

nci_cidc_schemas-0.26.38/cidc_schemas/schemas/assays/components/hande_local_file.json

@@ -0,0 +1,16 @@
+{
+  "$schema": "metaschema/strict_meta_schema.json#",
+  "$id": "local_file",
+  "title": "Local file type",
+  "type": "object",
+  "description": "A type to store local file paths.",
+  "additionalProperties": false,
+  "properties": {
+    "file_path": {
+      "$id": "local_file_path",
+      "type": "string",
+      "description": "Path to file, relative to the intake bucket. One of image file or annotated file is required."
+    }
+  },
+  "required": []
+}

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/schemas/assays/ctdna_assay.json

@@ -22,10 +22,8 @@
 				"bias_qc_plots",
 				"optimal_solution",
 				"other_solutions",
-				"fraction_cna_subclonal",
 				"fraction_genome_subclonal",
 				"gc_map_correction_mad",
-				"subclone_fraction",
 				"tumor_fraction",
 				"tumor_ploidy"
 			],
@@ -46,7 +44,7 @@
 				"on_premise_rdata_file": {"$ref": "artifacts/artifact_rdata.json"},
 
 				"fraction_cna_subclonal": {
-					"description": "Fraction of copy number altered bins that are subclonal. Accepts NaN. (0-1)",
+					"description": "Fraction of copy number altered bins that are subclonal (0-1)",
 					"type": ["number", "string"]
 				},
 				"fraction_genome_subclonal": {
@@ -60,7 +58,7 @@
 					"type": "number"
 				},
 				"subclone_fraction": {
-					"description": "Fraction of tumor-derived DNA that is subclonal. Accepts NA. (0-1)",
+					"description": "Fraction of tumor-derived DNA that is subclonal (0-1)",
 					"type": ["number", "string"]
 				},
 				"tumor_fraction": {

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/schemas/templates/assays/ctdna_template.json

@@ -59,7 +59,8 @@
             },
             "fraction cna subclonal": {
                 "merge_pointer": "0/fraction_cna_subclonal",
-                "type_ref": "assays/ctdna_assay.json#definitions/entry/properties/fraction_cna_subclonal"
+                "type_ref": "assays/ctdna_assay.json#definitions/entry/properties/fraction_cna_subclonal",
+                "allow_empty": true
             },
             "fraction genome subclonal": {
                 "merge_pointer": "0/fraction_genome_subclonal",
@@ -87,7 +88,8 @@
             },
             "subclone fraction": {
                 "merge_pointer": "0/subclone_fraction",
-                "type_ref": "assays/ctdna_assay.json#definitions/entry/properties/subclone_fraction"
+                "type_ref": "assays/ctdna_assay.json#definitions/entry/properties/subclone_fraction",
+                "allow_empty": true
             },
             "tumor fraction": {
                 "merge_pointer": "0/tumor_fraction",

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/schemas/templates/assays/hande_template.json

@@ -33,8 +33,9 @@
                         "merge_pointer": "0/files/image_file",
                         "is_artifact": 1,
                         "gcs_uri_format": "{protocol identifier}/hande/{cimac id}/image_file.{file type}",
-                        "type_ref": "assays/components/local_file.json#properties/file_path",
-                        "allow_empty": true
+                        "type_ref": "assays/components/hande_local_file.json#properties/file_path",
+                        "allow_empty": true,
+                        "type": "string"
                       },
                       "annotated file type": {
                         "do_not_merge": true,
@@ -46,8 +47,9 @@
                           "merge_pointer": "0/files/annotated_image",
                           "is_artifact": 1,
                           "gcs_uri_format": "{protocol identifier}/hande/{cimac id}/annotated_image.{annotated file type}",
-                          "type_ref": "assays/components/local_file.json#properties/file_path",
-                          "allow_empty": true
+                          "type_ref": "assays/components/hande_local_file.json#properties/file_path",
+                          "allow_empty": true,
+                          "type": "string"
                       },
                       "tumor tissue (% total area)": {
                         "merge_pointer": "0/tumor_tissue_percentage",

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/cidc_schemas/unprism.py

@@ -3,6 +3,7 @@
 from io import StringIO, BytesIO
 from typing import Callable, Dict, List, NamedTuple, Optional, Union
 
+import math
 import pandas as pd
 
 from . import prism
@@ -332,6 +333,9 @@ def _cytof_analysis_derivation(context: DeriveFilesContext) -> DeriveFilesResult
         res_df = pd.DataFrame()
         for index, row in cell_counts_analysis_csvs.iterrows():
             obj_url = row[f"output_files.{combined_f_kind}.object_url"]
+            if isinstance(obj_url, float) and math.isnan(obj_url):
+                # output file does not exist - continue (don't fail when a cytof assay is not included in analysis)
+                continue
 
             cell_counts_csv = context.fetch_artifact(obj_url, True)
 

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38/nci_cidc_schemas.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nci_cidc_schemas
-Version: 0.26.36
+Version: 0.26.38
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/nci_cidc_schemas.egg-info/SOURCES.txt

@@ -95,6 +95,7 @@ cidc_schemas/schemas/assays/components/composite_image.json
 cidc_schemas/schemas/assays/components/controls.json
 cidc_schemas/schemas/assays/components/enrichment_core.json
 cidc_schemas/schemas/assays/components/excluded_samples.json
+cidc_schemas/schemas/assays/components/hande_local_file.json
 cidc_schemas/schemas/assays/components/image.json
 cidc_schemas/schemas/assays/components/imaging_data.json
 cidc_schemas/schemas/assays/components/local_file.json

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/tests/prism/cidc_test_data/assay_data.py

@@ -3513,10 +3513,8 @@ def ctdna() -> PrismTestData:
                             "on_premise_rdata_file": {
                                 "upload_placeholder": "4c409c82-dff7-4f78-801c-222ssff"
                             },
-                            "fraction_cna_subclonal": 0.1,
                             "fraction_genome_subclonal": 0.2,
                             "gc_map_correction_mad": 0.04,
-                            "subclone_fraction": 0.15,
                             "tumor_fraction": 0.25,
                             "tumor_ploidy": 2.599,
                         },

{nci_cidc_schemas-0.26.36 → nci_cidc_schemas-0.26.38}/tests/test_unprism.py

@@ -296,3 +296,9 @@ def test_derive_files_CyTOF_analysis():
         assert sorted([r["cimac_participant_id"] for r in recs]) == sorted(
             list(map(participant_id_from_cimac, cimac_ids))
         )
+
+    # remove 'output_files' from first cytof assay (simulate not included in analysis)
+    ct["assays"]["cytof"][0]["records"][0].pop("output_files", None)
+    # ensure still able to successfully retrieve result even if cytof assay output_files do not exist
+    result = derive_files(DeriveFilesContext(ct, "cytof_analysis", fetch_artifact))
+    assert len(result.artifacts) == 3