acmc/main.py

@@ -58,7 +58,7 @@ def _phen_validate(args: argparse.Namespace):
 
 def _phen_map(args: argparse.Namespace):
     """Handle the `phen map` command."""
-    phen.map(args.phen_dir, args.target_coding)
+    phen.map(args.phen_dir, args.target_coding, args.not_translate, args.no_metadata)
 
 
 def _phen_export(args: argparse.Namespace):
@@ -78,7 +78,7 @@ def _phen_copy(args: argparse.Namespace):
 
 def _phen_diff(args: argparse.Namespace):
     """Handle the `phen diff` command."""
-    phen.diff(args.phen_dir, args.version, args.old_phen_dir, args.old_version)
+    phen.diff(args.phen_dir, args.version, args.old_phen_dir, args.old_version, args.not_check_config)
 
 
 def main():
@@ -217,6 +217,18 @@ def main():
         choices=parse.SUPPORTED_CODE_TYPES,
         help=f"Specify the target coding {parse.SUPPORTED_CODE_TYPES}",
     )
+    phen_map_parser.add_argument(
+        "--not-translate",
+        action='store_true',
+        default=False,
+        help="(Optional) Prevent any phenotype translation using NHS TRUD vocabularies.",
+    ) 
+    phen_map_parser.add_argument(
+        "--no-metadata",
+        action='store_true',
+        default=False,
+        help="(Optional) Prevent copying of metadata columns to output.",
+    ) 
     phen_map_parser.set_defaults(func=_phen_map)
 
     # phen export
@@ -323,6 +335,12 @@ def main():
         required=True,
         help="Old phenotype version to compare with the changed version",
     )
+    phen_diff_parser.add_argument(
+        "--not-check-config",
+        action='store_true',
+        default=False,
+        help="(Optional) Prevent loading and comparing config file, in the case where one does not exist",
+    )   
     phen_diff_parser.set_defaults(func=_phen_diff)
 
     # Parse arguments

acmc/parse.py

@@ -192,7 +192,7 @@ class Read2(Proto):
 
 class Read3(Proto):
     def __init__(self):
-        super().__init__("Read3", trud.PROCESSED_PATH / "read3.parquet")
+        super().__init__("read3", trud.PROCESSED_PATH / "read3.parquet")
 
         self.checks = [
             (
@@ -231,7 +231,7 @@ class Read3(Proto):
                             f"QA Alphanumeric Dot",
                             codes=codes,
                             codes_file=codes_file,
-                            check_regex=codes.str.match(r"^[a-zA-Z0-9.]+$"),
+                            mask=None,
                             code_type=self.name,
                         )
                     )
@@ -246,7 +246,7 @@ class Read3(Proto):
                             f"QA In Database",
                             codes=codes,
                             codes_file=codes_file,
-                            check_regex=self.in_database(codes, self.db, self.name),
+                            mask=None,
                             code_type=self.name,
                         )
                     )

docs/api/acmc/parse.html

@@ -760,7 +760,7 @@
                 <section id="SUPPORTED_CODE_TYPES">
                     <div class="attr variable">
             <span class="name">SUPPORTED_CODE_TYPES</span>        =
-<span class="default_value">{&#39;opcs4&#39;, &#39;icd10&#39;, &#39;atc&#39;, &#39;snomed&#39;, &#39;read2&#39;, &#39;read3&#39;}</span>
+<span class="default_value">{&#39;atc&#39;, &#39;read2&#39;, &#39;read3&#39;, &#39;opcs4&#39;, &#39;snomed&#39;, &#39;icd10&#39;}</span>
 
         
     </div>

docs/cli.md

@@ -111,6 +111,9 @@ The `phen` command is used phenotype-related operations.
 
   - `-t`, `--target-coding`: (Optional) Specify the target coding (e.g., `read2`, `read3`, `icd10`, `snomed`, `opcs4`).
   - `-d`, `--phen-dir`: (Optional) Local phenotype workspace directory (default is ./workspace/phen).
+  - `--not-translate`: (Optional) Prevent any phenotype translation using NHS TRUD vocabularies. Therefore only concepts in already in the traget coding will be mapped.
+    - `--no-metadata`: (Optional) Prevent copying of metadata columns to output.
+
 
 - **Publish Phenotype Configuration**
 

examples/config1.yml

@@ -8,9 +8,8 @@ phenotype:
     - "read2"
     - "read3"
   concept_sets:
-    - name: "ABDO_PAIN"
-      file:
-        path: "clinical-codes-org/Symptom code lists/Abdominal pain/res176-abdominal-pain.csv"
+  - name: "ABDO_PAIN"
+    files:
+      - path: "clinical-codes-org/Symptom code lists/Abdominal pain/res176-abdominal-pain.csv"
         columns:
           read2: "code"
-

examples/config2.yml

@@ -8,13 +8,13 @@ phenotype:
     - "read2"
     - "read3"    
   concept_sets:
-    - name: "CVD_EVENTS"
-      file: 
-        path: "clinical-codes-org/Cardiovascular events (ICD10)/res52-cardiovascular-events-icd10.csv"
+  - name: "CVD_EVENTS"
+    files:
+      - path: "clinical-codes-org/Cardiovascular events (ICD10)/res52-cardiovascular-events-icd10.csv"
         columns:
-          icd10: "code"
-    - name: "DID_NOT_ATTEND"
-      file: 
-        path: "clinical-codes-org/Non-attendance codes/res201-did-not-attend-appointment.csv"
+          icd10: "code"          
+  - name: "DID_NOT_ATTEND"
+    files: 
+      - path: "clinical-codes-org/Non-attendance codes/res201-did-not-attend-appointment.csv"
         columns:
           read2: "code"
\ No newline at end of file

examples/config3.yml

@@ -10,29 +10,29 @@ phenotype:
     - "snomed"       
   concept_sets:
     - name: "CVD_EVENTS"
-      file: 
-        path: "clinical-codes-org/Cardiovascular events (ICD10)/res52-cardiovascular-events-icd10.csv"
-        columns:
-          icd10: "code"
+      files: 
+        - path: "clinical-codes-org/Cardiovascular events (ICD10)/res52-cardiovascular-events-icd10.csv"
+          columns:
+            icd10: "code"
     - name: "DID_NOT_ATTEND"
-      file: 
-        path: "clinical-codes-org/Non-attendance codes/res201-did-not-attend-appointment.csv"
-        columns:
-          read2: "code"
+      files: 
+        - path: "clinical-codes-org/Non-attendance codes/res201-did-not-attend-appointment.csv"
+          columns:
+            read2: "code"
     - name: "HYPERTENSION"
-      file: 
-        path: "hanlon/Read_codes_for_diagnoses.csv"
-        columns:
-          read2: "Read Code"
-        category: "2"
-        actions:
-          divide_col: "MMCode"         
+      files: 
+        - path: "hanlon/Read_codes_for_diagnoses.csv"
+          columns:
+            read2: "Read Code"
+          category: "2"
+          actions:
+            divide_col: "MMCode"
     - name: "DEPRESSION"
-      file: 
-        path: "hanlon/Read_codes_for_diagnoses.csv"
-        columns:
-          read2: "Read Code"
-        category: "3"
-        actions:
-          divide_col: "MMCode"          
+      files: 
+        - path: "hanlon/Read_codes_for_diagnoses.csv"
+          columns:
+            read2: "Read Code"
+          category: "3"
+          actions:
+            divide_col: "MMCode"  
 

tests/test_acmc.py

@@ -128,26 +128,6 @@ def test_phen_workflow(tmp_dir, monkeypatch, caplog, config_file):
         main.main()
     assert "Phenotype published successfully" in caplog.text
 
-    # copy phenotype'
-    with caplog.at_level(logging.DEBUG):
-        monkeypatch.setattr(
-            sys,
-            "argv",
-            [
-                "main.py",
-                "phen",
-                "copy",
-                "-d",
-                str(phen_path.resolve()),
-                "-td",
-                str(tmp_dir.resolve()),
-                "-v",
-                "0.0.1",
-            ],
-        )
-        main.main()
-    assert "Phenotype copied successfully" in caplog.text
-
     # diff phenotype
     with caplog.at_level(logging.DEBUG):
         old_path = tmp_dir / "0.0.1"