nci-cidc-schemas 0.27.27__tar.gz → 0.27.28__tar.gz

{nci_cidc_schemas-0.27.27/nci_cidc_schemas.egg-info → nci_cidc_schemas-0.27.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.27
+Version: 0.27.28
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -130,6 +130,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28}/README.md

@@ -86,6 +86,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28}/cidc_schemas/__init__.py

@@ -2,4 +2,4 @@
 
 __author__ = """NCI"""
 __email__ = "nci-cidc-tools-admin@mail.nih.gov"
-__version__ = "0.27.27"
+__version__ = "0.27.28"

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28}/cidc_schemas/prism/extra_metadata.py

@@ -98,7 +98,7 @@ def parse_npx(xlsx: BinaryIO) -> dict:
 
         # simplify.
         worksheet = workbook[worksheet_name]
-        seen_onlinkid = False
+        seen_id_column = False
         for i, row in enumerate(worksheet.iter_rows()):
 
             # extract values from row
@@ -110,8 +110,8 @@ def parse_npx(xlsx: BinaryIO) -> dict:
             if len(vals) == 0 or first_cell is None:
                 continue
 
-            # find OlinkID to locate the first data row
-            if not seen_onlinkid:
+            # find Cimac ID column to locate the first data row
+            if not seen_id_column:
                 # check that this is actually an NPX file
                 if i == 1 and first_cell != "NPX data":
                     raise ValueError("parse_npx got a file that is not in NPX format")
@@ -119,8 +119,10 @@ def parse_npx(xlsx: BinaryIO) -> dict:
                 # check if we are starting ids
                 # use this to capture cases where the column name changes in spacing / capitalization
                 ## needed because some data has 'OlinkID' while the standard seems to call for 'Olink ID'
-                if str(first_cell).lower().replace(" ", "") == "olinkid":
-                    seen_onlinkid = True
+                # Data is starting to come in with 'Sample ID' column instead - accepting that too
+                lower_first_cell = str(first_cell).lower().replace(" ", "")
+                if lower_first_cell in ["olinkid", "sampleid"]:
+                    seen_id_column = True
                     continue
 
             # once it's found keep getting ids until we're done

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28/nci_cidc_schemas.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.27
+Version: 0.27.28
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -130,6 +130,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28}/tests/prism/test_extra_metadata.py

@@ -6,8 +6,9 @@ from cidc_schemas.prism.extra_metadata import parse_elisa, parse_npx, parse_clin
 
 from ..constants import TEST_DATA_DIR
 
-# Single NPX file and metadata
-npx_file_path = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_1_NPX.xlsx")
+# NPX files in differing acceptable formats and metadata
+npx_file_path_olink = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_1_NPX.xlsx")
+npx_file_path_sample = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_2_NPX.xlsx")
 single_npx_metadata = {
     "number_of_samples": 4,
     "samples": ["CTTTP01A1.00", "CTTTP02A1.00", "CTTTP03A1.00", "CTTTP04A1.00"],
@@ -88,7 +89,8 @@ def test_parse_binaryio_only(parser):
 @pytest.mark.parametrize(
     "parser,file_path,target",
     [
-        (parse_npx, npx_file_path, single_npx_metadata),
+        (parse_npx, npx_file_path_olink, single_npx_metadata),
+        (parse_npx, npx_file_path_sample, single_npx_metadata),
         (parse_npx, npx_combined_file_path, combined_npx_metadata),
         # differ in column order and capitalization/spacing of cimac_id column
         # testing both to prevent unnecessary assumptions in formatting as this is hand generated

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.27.28}/tests/prism/test_merger.py

@@ -12,7 +12,8 @@ from cidc_schemas.prism.core import LocalFileUploadEntry
 from cidc_schemas.prism.constants import PROTOCOL_ID_FIELD_NAME
 
 from .test_extra_metadata import (
-    npx_file_path,
+    npx_file_path_olink,
+    npx_file_path_sample,
     npx_combined_file_path,
     invalid_npx_file_path,
     elisa_file_path_1,
@@ -381,7 +382,14 @@ def olink_ct_metadata():
 def olink_file_infos():
     return [
         LocalFileUploadEntry(
-            local_path=npx_file_path,
+            local_path=npx_file_path_olink,
+            gs_key="",
+            upload_placeholder="npx_1",
+            metadata_availability=True,
+            allow_empty=False,
+        ),
+        LocalFileUploadEntry(
+            local_path=npx_file_path_sample,
             gs_key="",
             upload_placeholder="npx_1",
             metadata_availability=True,