nci-cidc-schemas 0.28.3__py2.py3-none-any.whl → 0.28.13__py2.py3-none-any.whl

cidc_schemas/schemas/templates/assays/tcr_adaptive_template.json

@@ -19,10 +19,14 @@
             "merge_pointer": "0/sequencer_platform",
             "type_ref": "assays/components/ngs_assay_core.json#properties/sequencer_platform"
           },
-          "batch id": {
+          "CIMAC Batch ID": {
             "merge_pointer": "0/batch_id",
             "type_ref": "assays/tcr_assay.json#properties/batch_id"
           },
+          "CIDC Submission ID": {
+            "merge_pointer": "0/optional_id",
+            "type_ref": "assays/tcr_assay.json#properties/optional_id"
+          },
           "sequencing run date": {
             "merge_pointer": "0/sequencing_run_date",
             "type_ref": "assays/tcr_assay.json#properties/sequencing_run_date",
@@ -30,7 +34,7 @@
           },
           "sample sheet": {
             "merge_pointer": "0/sample_sheet",
-            "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/SampleSheet.csv",
+            "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/SampleSheet.csv",
             "is_artifact": 1,
             "type_ref": "assays/components/local_file.json#properties/file_path",
             "allow_empty": true
@@ -45,7 +49,7 @@
             },
             "tsv reads": {
               "merge_pointer": "0/tsv_file",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/{cimac id}/reads.tsv",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/{cimac id}/reads.tsv",
               "is_artifact": "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             }
@@ -60,7 +64,7 @@
             "merge_pointer": "3/protocol_identifier",
             "type_ref": "clinical_trial.json#properties/protocol_identifier"
           },
-          "batch id": {
+          "CIMAC Batch ID": {
             "merge_pointer": "0/batch_id",
             "type_ref": "assays/tcr_assay.json#properties/batch_id"
           }
@@ -74,7 +78,7 @@
             },
             "tsv reads": {
               "merge_pointer": "0/tsv_file",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/controls/{control id}/reads.tsv",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/controls/{control id}/reads.tsv",
               "is_artifact": "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             }

cidc_schemas/schemas/templates/assays/tcr_fastq_template.json

@@ -19,17 +19,21 @@
             "merge_pointer": "0/sequencer_platform",
             "type_ref": "assays/components/ngs_assay_core.json#properties/sequencer_platform"
           },
-          "batch id": {
+          "CIMAC Batch ID": {
             "merge_pointer": "0/batch_id",
             "type_ref": "assays/tcr_assay.json#properties/batch_id"
           },
+          "CIDC Submission ID": {
+            "merge_pointer": "0/optional_id",
+            "type_ref": "assays/tcr_assay.json#properties/optional_id"
+          },
           "sequencing run date": {
             "merge_pointer": "0/sequencing_run_date",
             "type_ref": "assays/tcr_assay.json#properties/sequencing_run_date"
           },
           "sample sheet": {
             "merge_pointer": "0/sample_sheet",
-            "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/SampleSheet.csv",
+            "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/SampleSheet.csv",
             "is_artifact": 1,
             "type_ref": "assays/components/local_file.json#properties/file_path"
           }
@@ -47,25 +51,25 @@
             },
             "read 1": {
               "merge_pointer": "0/r1/-",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/{cimac id}/replicate_{replicate id}/r1.fastq.gz",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/{cimac id}/replicate_{replicate id}/r1.fastq.gz",
               "is_artifact": "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             },
             "read 2": {
               "merge_pointer": "0/r2/-",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/{cimac id}/replicate_{replicate id}/r2.fastq.gz",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/{cimac id}/replicate_{replicate id}/r2.fastq.gz",
               "is_artifact" : "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             },
             "index 1": {
               "merge_pointer": "0/i1/-",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/{cimac id}/replicate_{replicate id}/i1.fastq.gz",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/{cimac id}/replicate_{replicate id}/i1.fastq.gz",
               "is_artifact": "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             },
             "index 2": {
               "merge_pointer": "0/i2/-",
-              "gcs_uri_format": "{protocol identifier}/tcr/{batch id}/{cimac id}/replicate_{replicate id}/i2.fastq.gz",
+              "gcs_uri_format": "{protocol identifier}/tcr/{cimac batch id}/{cimac id}/replicate_{replicate id}/i2.fastq.gz",
               "is_artifact" : "1",
               "type_ref": "assays/components/local_file.json#properties/file_path"
             },

cidc_schemas/schemas/templates/assays/tcrseq_rna_template.json

@@ -0,0 +1,59 @@
+{
+    "title": "TCR RNA assay template",
+    "description": "TCR RNA submission.",
+    "prism_template_root_object_schema": "assays/tcrseq_rna_assay.json",
+    "prism_template_root_object_pointer": "/assays/tcrseq_rna/0",
+    "properties": {
+        "worksheets": {
+            "TCR RNA": {
+                "prism_data_object_pointer": "/records/-",
+                "preamble_rows": {
+                    "protocol identifier": {
+                        "merge_pointer": "3/protocol_identifier",
+                        "type_ref": "clinical_trial.json#properties/protocol_identifier"
+                    },
+                    "CIMAC Batch ID": {
+                        "merge_pointer": "0/batch_id",
+                        "type_ref": "assays/mibi_assay.json#properties/batch_id"
+                    },
+                    "CIDC Submission ID": {
+                        "merge_pointer": "0/optional_id",
+                        "type_ref": "assays/mibi_assay.json#properties/optional_id"
+                    },
+                    "assay creator": {
+                        "merge_pointer": "0/assay_creator",
+                        "type_ref": "assays/components/assay_core.json#properties/assay_creator"
+                    },
+                    "sequencer platform": {
+                      "merge_pointer": "0/sequencer_platform",
+                      "type_ref": "assays/components/ngs_assay_core.json#properties/sequencer_platform"
+                    },
+                    "sequencing run date": {
+                      "merge_pointer": "0/sequencing_run_date",
+                      "type_ref": "assays/tcr_assay.json#properties/sequencing_run_date"
+                    }
+                },
+                "data_columns": {
+                    "Samples": {
+                        "cimac id": {
+                            "merge_pointer": "0/cimac_id",
+                            "type_ref": "sample.json#properties/cimac_id"
+                        },
+                        "alpha results file": {
+                            "merge_pointer": "0/alpha_results_file",
+                            "is_artifact": 1,
+                            "gcs_uri_format": "{protocol identifier}/tcrseq_rna/{cimac batch id}/{cimac id}/alpha.csv",
+                            "type_ref": "assays/components/local_file.json#properties/file_path"
+                        },
+                        "beta results file": {
+                            "merge_pointer": "0/beta_results_file",
+                            "is_artifact": 1,
+                            "gcs_uri_format": "{protocol identifier}/tcrseq_rna/{cimac batch id}/{cimac id}/beta.csv",
+                            "type_ref": "assays/components/local_file.json#properties/file_path"
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

cidc_schemas/schemas/templates/assays/visium_template.json

@@ -20,10 +20,14 @@
                         "merge_pointer": "0/assay_creator",
                         "type_ref": "assays/visium_assay.json#properties/assay_creator"
                     },
-                    "batch id": {
+                    "CIMAC Batch ID": {
                         "merge_pointer": "0/batch_id",
                         "type_ref": "assays/visium_assay.json#properties/batch_id"
                     },
+                    "CIDC Submission ID": {
+                        "merge_pointer": "0/optional_id",
+                        "type_ref": "assays/visium_assay.json#properties/optional_id"
+                    },
                     "azimuth reference": {
                         "merge_pointer": "0/azimuth_reference",
                         "type_ref": "assays/components/scrnaseq_preamble.json#properties/azimuth_reference",
@@ -46,7 +50,7 @@
                     },
                     "sample metadata csv": {
                         "merge_pointer": "0/samples_metadata_csv",
-                        "gcs_uri_format": "{protocol identifier}/visium/{batch id}/samples_metadata.csv",
+                        "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/samples_metadata.csv",
                         "is_artifact": 1,
                         "type_ref": "assays/components/local_file.json#properties/file_path"
                     }
@@ -68,19 +72,19 @@
                         "Read1 fastq gz": {
                             "merge_pointer": "0/details/read_1_fastq_gz",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/fastq/S1_L00{lane}_R1_001.fastq.gz",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/fastq/S1_L00{lane}_R1_001.fastq.gz",
                             "type_ref": "assays/components/local_file.json#properties/file_path"
                         },
                         "Read2 fastq gz": {
                             "merge_pointer": "0/details/read_2_fastq_gz",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/fastq/S1_L00{lane}_R2_001.fastq.gz",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/fastq/S1_L00{lane}_R2_001.fastq.gz",
                             "type_ref": "assays/components/local_file.json#properties/file_path"
                         },
                         "Loupe alignment file": {
                             "merge_pointer": "0/details/loupe_alignment_file",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/loupe_alignment_file.json",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/loupe_alignment_file.json",
                             "type_ref": "assays/components/local_file.json#properties/file_path",
                             "allow_empty": true
                         },
@@ -106,28 +110,28 @@
                         "brightfield image": {
                             "merge_pointer": "0/details/brightfield_image",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/brightfield.tiff",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/brightfield.tiff",
                             "type_ref": "assays/components/local_file.json#properties/file_path",
                             "allow_empty": true
                         },
                         "dark image": {
                             "merge_pointer": "0/details/dark_image",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/dark_image.tiff",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/dark_image.tiff",
                             "type_ref": "assays/components/local_file.json#properties/file_path",
                             "allow_empty": true
                         },
                         "colorized image": {
                             "merge_pointer": "0/details/colorized_image",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/colorized.tiff",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/colorized.tiff",
                             "type_ref": "assays/components/local_file.json#properties/file_path",
                             "allow_empty": true
                         },
                         "cytassist image": {
                             "merge_pointer": "0/details/cytassist_image",
                             "is_artifact": 1,
-                            "gcs_uri_format": "{protocol identifier}/visium/{batch id}/{cimac id}/cytassist.tiff",
+                            "gcs_uri_format": "{protocol identifier}/visium/{cimac batch id}/{cimac id}/cytassist.tiff",
                             "type_ref": "assays/components/local_file.json#properties/file_path",
                             "allow_empty": true
                         },

cidc_schemas/schemas/templates/assays/wes_bam_template.json

@@ -16,6 +16,14 @@
             "merge_pointer": "0/assay_creator",
             "type_ref": "assays/components/assay_core.json#properties/assay_creator"
           },
+          "CIMAC Batch ID": {
+            "merge_pointer": "0/batch_id",
+            "type_ref": "assays/wes_assay.json#properties/batch_id"
+          },
+          "CIDC Submission ID": {
+            "merge_pointer": "0/optional_id",
+            "type_ref": "assays/wes_assay.json#properties/optional_id"
+          },
           "sequencing protocol": {
             "merge_pointer": "0/sequencing_protocol",
             "type_ref": "assays/wes_assay.json#properties/sequencing_protocol"

cidc_schemas/schemas/templates/assays/wes_fastq_template.json

@@ -16,6 +16,14 @@
             "merge_pointer": "0/assay_creator",
             "type_ref": "assays/components/assay_core.json#properties/assay_creator"
           },
+          "CIMAC Batch ID": {
+            "merge_pointer": "0/batch_id",
+            "type_ref": "assays/wes_assay.json#properties/batch_id"
+          },
+          "CIDC Submission ID": {
+            "merge_pointer": "0/optional_id",
+            "type_ref": "assays/wes_assay.json#properties/optional_id"
+          },
           "sequencing protocol": {
             "merge_pointer": "0/sequencing_protocol",
             "type_ref": "assays/wes_assay.json#properties/sequencing_protocol",

cidc_schemas/template.py

@@ -912,10 +912,6 @@ class _FieldDef(NamedTuple):
                 f"Can't format destination gcs uri for {self.key_name!r}: {format}"
             )
 
-        # remove [ or ] in GCS URI because gsutils treats brackets as a character set
-        # and matches multiple file paths, which is not allowed for a target
-        gs_key = gs_key.replace("[", "").replace("]", "")
-
         # if no . in the GCS URI, don't check file extension as none specified
         if "." in self.gcs_uri_format:
             expected_extension = get_file_ext(gs_key)

cidc_schemas/unprism.py

@@ -72,10 +72,10 @@ def derive_files(context: DeriveFilesContext) -> Optional[DeriveFilesResult]:
             trial_metadata: dict
 
         None if context.upload_type does not have a defined file derivation
-        all prism.SUPPORTED_SHIPPING_MANIFESTS are supported via _shipping_manifest_derivation()
+        all prism.SUPPORTED_MANIFESTS are supported via _shipping_manifest_derivation()
         otherwise use wrapper @_register_derivation(upload_type: str)
     """
-    if context.upload_type in prism.SUPPORTED_SHIPPING_MANIFESTS:
+    if context.upload_type in prism.SUPPORTED_MANIFESTS:
         return _shipping_manifest_derivation(context)
 
     if context.upload_type in _upload_type_derivations:
@@ -353,7 +353,7 @@ def _cytof_analysis_derivation(context: DeriveFilesContext) -> DeriveFilesResult
             # and a single row of cell count data.
             df = df.set_index("CellSubset")
             df = df.drop(
-                columns="Unnamed: 0", axis=1
+                columns=["Unnamed: 0"]
             )  # Cell counts files contain an unnamed index column
             df = df.transpose()
 

{nci_cidc_schemas-0.28.3.dist-info → nci_cidc_schemas-0.28.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.28.3
+Version: 0.28.13
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -15,17 +15,17 @@ Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.13,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: argparse==1.4.0
-Requires-Dist: dateparser==1.2.2
-Requires-Dist: deepdiff==4.3.0
-Requires-Dist: jinja2==3.1.6
-Requires-Dist: jsonmerge==1.6.1
-Requires-Dist: jsonpointer==3.0.0
-Requires-Dist: jsonschema==3.2.0
-Requires-Dist: openpyxl==3.1.5
-Requires-Dist: pandas==2.3.1
-Requires-Dist: pyyaml==6.0.2
-Requires-Dist: xlsxwriter==3.2.5
+Requires-Dist: argparse~=1.4.0
+Requires-Dist: dateparser~=1.2.2
+Requires-Dist: deepdiff~=8.6.1
+Requires-Dist: jinja2~=3.1.6
+Requires-Dist: jsonmerge~=1.6.1
+Requires-Dist: jsonpointer~=3.0.0
+Requires-Dist: jsonschema~=3.2.0
+Requires-Dist: openpyxl~=3.1.5
+Requires-Dist: pandas~=3.0.0
+Requires-Dist: pyyaml~=6.0.3
+Requires-Dist: xlsxwriter~=3.2.9
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -131,11 +131,17 @@ python3 -m cidc_schemas.cli [args]
 
 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
+Preferably, look at scrnaseq 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.
+Once you update and update the version of this repo, update api-gae. You should only need to copy what scrnaseq
+did in api-gae in order for files to show up on the portal. Make sure to update the api-gae version. Update the api-gae version used
+in cloud-functions.
+
+Finally, make sure to update the cli tool to include the new assay.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so the
+practical advice is to follow an existing working template.
 
 Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.