nci-cidc-schemas 0.27.26__py2.py3-none-any.whl → 0.27.28__py2.py3-none-any.whl

cidc_schemas/__init__.py

@@ -2,4 +2,4 @@
 
 __author__ = """NCI"""
 __email__ = "nci-cidc-tools-admin@mail.nih.gov"
-__version__ = "0.27.26"
+__version__ = "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
@@ -131,7 +133,7 @@ def parse_npx(xlsx: BinaryIO) -> dict:
 
                 # otherwise get the identifier
                 # and check that it is a CIMAC ID
-                if cimac_id_regex.match(first_cell):
+                if cimac_id_regex.match(first_cell) and first_cell not in ids:
                     ids.append(first_cell)
 
     sample_count = len(ids)

{nci_cidc_schemas-0.27.26.dist-info → nci_cidc_schemas-0.27.28.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.26
+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-0.27.26.dist-info → nci_cidc_schemas-0.27.28.dist-info}/RECORD

@@ -1,4 +1,4 @@
-cidc_schemas/__init__.py,sha256=s45LJZm6cKT8dLo7q8XG7Y1yQGsbTUXOKCzeMASfAsU,136
+cidc_schemas/__init__.py,sha256=6omZ_AmjReFyYGR3ZLS8zV6hvtmrnyhlW9y94oYbgHs,136
 cidc_schemas/cli.py,sha256=gWiktRlraNH8Q0zNUae9dohKjPwBmcY0BJwdcQ_fIic,4099
 cidc_schemas/constants.py,sha256=RULs7pGuBAVq1teXymrfbVsK23ZowJvLuZlv0KcjL-Y,698
 cidc_schemas/json_validation.py,sha256=spmPsqinib7Ns5GvWOKKa1rc7IrN_s2bqifpTKdaLVU,23288
@@ -13,7 +13,7 @@ cidc_schemas/pipeline_configs/rna_level1_analysis_config.yaml.j2,sha256=6no9sFqw
 cidc_schemas/prism/__init__.py,sha256=J5Tj0X7Di6cyxAjaduOUp2aVyvl8UI67bgxEkgttvcU,530
 cidc_schemas/prism/constants.py,sha256=PevSn-geY8VTGMx1iXdUJ2LgoeuhEdKfIpZYk_LbzwI,4088
 cidc_schemas/prism/core.py,sha256=tXDCCHurvcrxfU11meH3NRAVo9niklup0dpLRoIXwPk,20242
-cidc_schemas/prism/extra_metadata.py,sha256=S9w5EGAT0xwaWMrpYluF7Y1ONsI4wFtxFD8ib6Va_fU,8567
+cidc_schemas/prism/extra_metadata.py,sha256=2qs2PCvWRknZk56GrnRCjQ2hifAQz2YcJ8qXeMlG-Zg,8769
 cidc_schemas/prism/merger.py,sha256=36CKBPVoWecHuvGp3oT9a2d4jWIkvKuS_UofKTEpMYs,13065
 cidc_schemas/prism/pipelines.py,sha256=dvZtoC7pEVgdPual_DZUTBFfgvSV7yTdk1RHwi5h6Vs,33522
 cidc_schemas/schemas/aliquot.json,sha256=F24s6xGTeJl-VT6s6wvV8YtMA4O-0BsUCwtD2OEx_cY,1943
@@ -178,9 +178,9 @@ cidc_schemas/schemas/templates/manifests/tissue_slide_template.json,sha256=q2GmO
 cidc_schemas/schemas/templates/manifests/tumor_normal_pairing_template.json,sha256=lVJrGb28n-vyfjGBzhrzjn1lMKw1b4HXXmWtwA603v0,2797
 cidc_schemas/schemas/templates/manifests/tumor_tissue_dna_template.json,sha256=LpaoDXDS11NCa-Dv37N-tzEGomswQrx5fypkUcG7xJk,18956
 cidc_schemas/schemas/templates/manifests/tumor_tissue_rna_template.json,sha256=-gww6NCHbtbI5z7UmNSmKyPK3IqKCE8F6n4XwTAb_gk,18101
-nci_cidc_schemas-0.27.26.dist-info/licenses/LICENSE,sha256=zK77-w4rYCZBHAYJEGkcFuPXwKIsP7jMPZ2iQOXjzko,1072
-nci_cidc_schemas-0.27.26.dist-info/METADATA,sha256=uQrrscUf16IL4910ZSCzxHzC2l9SIrMeTt8-VD2zV0Q,4554
-nci_cidc_schemas-0.27.26.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
-nci_cidc_schemas-0.27.26.dist-info/entry_points.txt,sha256=kSyTzXeJQrJp_2ZX0GS_NnbJR8ceQKLBSgER46PM0hs,55
-nci_cidc_schemas-0.27.26.dist-info/top_level.txt,sha256=Wwb5Cu7QrnbmSJxI2d00e3-Mir36t0jTRnSulmfhi30,13
-nci_cidc_schemas-0.27.26.dist-info/RECORD,,
+nci_cidc_schemas-0.27.28.dist-info/licenses/LICENSE,sha256=zK77-w4rYCZBHAYJEGkcFuPXwKIsP7jMPZ2iQOXjzko,1072
+nci_cidc_schemas-0.27.28.dist-info/METADATA,sha256=TigK-2nNG0G6iJ2DJf1BJgmjqHH32gQymfeXPxmrYOk,5116
+nci_cidc_schemas-0.27.28.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
+nci_cidc_schemas-0.27.28.dist-info/entry_points.txt,sha256=kSyTzXeJQrJp_2ZX0GS_NnbJR8ceQKLBSgER46PM0hs,55
+nci_cidc_schemas-0.27.28.dist-info/top_level.txt,sha256=Wwb5Cu7QrnbmSJxI2d00e3-Mir36t0jTRnSulmfhi30,13
+nci_cidc_schemas-0.27.28.dist-info/RECORD,,