feat!: parameterize normalize in translator (#361)

* feat!: parameterize normalize in translator * new kwarg (do_normalize) in translate_from methods. Set to determine if normalization should be performed * add test from spdi cassette
ga4gh · Mar 13, 2024 · cef704d · cef704d
1 parent 39fa484
commit cef704d
Show file tree

Hide file tree

Showing 15 changed files with 464 additions and 381 deletions.
diff --git a/src/ga4gh/vrs/extras/translator.py b/src/ga4gh/vrs/extras/translator.py
@@ -54,14 +54,12 @@ def __init__(
         self,
         data_proxy,
         default_assembly_name="GRCh38",
-        normalize=True,
         identify=True,
         rle_seq_limit: Optional[int] = 50
     ):
         self.default_assembly_name = default_assembly_name
         self.data_proxy = data_proxy
         self.identify = identify
-        self.normalize = normalize
         self.rle_seq_limit = rle_seq_limit
         self.hgvs_tools = None
         self.from_translators = {}
@@ -127,6 +125,8 @@ def translate_from(self, var, fmt=None, **kwargs):
                     To exclude `sequence` from the response, set to 0.
                     For no limit, set to `None`.
                     Defaults value set in instance variable, `rle_seq_limit`.
+                do_normalize (bool): `True` if fully justified normalization should be
+                    performed. `False` otherwise. Defaults to `True`
         """
         if fmt:
             try:
@@ -225,10 +225,10 @@ class AlleleTranslator(Translator):
     """Class for translating formats to and from VRS Alleles"""
 
     def __init__(
-        self, data_proxy, default_assembly_name="GRCh38", normalize=True, identify=True
+        self, data_proxy, default_assembly_name="GRCh38", identify=True
     ):
         """Initialize AlleleTranslator class"""
-        super().__init__(data_proxy, default_assembly_name, normalize, identify)
+        super().__init__(data_proxy, default_assembly_name, identify)
 
         self.from_translators = {
             "beacon": self._from_beacon,
@@ -253,6 +253,8 @@ def _from_beacon(self, beacon_expr, **kwargs):
                 To exclude `sequence` from the response, set to 0.
                 For no limit, set to `None`.
                 Defaults value set in instance variable, `rle_seq_limit`.
+            do_normalize (bool): `True` if fully justified normalization should be
+                performed. `False` otherwise. Defaults to `True`
 
         #>>> a = tlr.from_beacon("19 : 44908822 C > T")
         #>>> a.model_dump()
@@ -316,6 +318,8 @@ def _from_gnomad(self, gnomad_expr, **kwargs):
                 To exclude `sequence` from the response, set to 0.
                 For no limit, set to `None`.
                 Defaults value set in instance variable, `rle_seq_limit`.
+            do_normalize (bool): `True` if fully justified normalization should be
+                performed. `False` otherwise. Defaults to `True`
 
         #>>> a = tlr.from_gnomad("1-55516888-G-GA")
         #>>> a.model_dump()
@@ -378,6 +382,8 @@ def _from_hgvs(self, hgvs_expr: str, **kwargs):
                 To exclude `sequence` from the response, set to 0.
                 For no limit, set to `None`.
                 Defaults value set in instance variable, `rle_seq_limit`.
+            do_normalize (bool): `True` if fully justified normalization should be
+                performed. `False` otherwise. Defaults to `True`
 
         #>>> a = tlr.from_hgvs("NC_000007.14:g.55181320A>T")
         #>>> a.model_dump()
@@ -452,6 +458,8 @@ def _from_spdi(self, spdi_expr, **kwargs):
                 To exclude `sequence` from the response, set to 0.
                 For no limit, set to `None`.
                 Defaults value set in instance variable, `rle_seq_limit`.
+            do_normalize (bool): `True` if fully justified normalization should be
+                performed. `False` otherwise. Defaults to `True`
 
         #>>> a = tlr.from_spdi("NC_000013.11:32936731:1:C")
         #>>> a.model_dump()
@@ -626,8 +634,10 @@ def _post_process_imported_allele(self, allele, **kwargs):
                 normalization, this sets the limit for the length of the `sequence`.
                 To exclude `sequence` from the response, set to 0.
                 For no limit, set to `None`.
+            do_normalize (bool): `True` if fully justified normalization should be
+                performed. `False` otherwise. Defaults to `True`
         """
-        if self.normalize:
+        if kwargs.get("do_normalize", True):
             allele = normalize(
                 allele,
                 self.data_proxy,
@@ -654,10 +664,10 @@ class CnvTranslator(Translator):
     """Class for translating formats from format to VRS Copy Number"""
 
     def __init__(
-        self, data_proxy, default_assembly_name="GRCh38", normalize=True, identify=True
+        self, data_proxy, default_assembly_name="GRCh38", identify=True
     ):
         """Initialize CnvTranslator class"""
-        super().__init__(data_proxy, default_assembly_name, normalize, identify)
+        super().__init__(data_proxy, default_assembly_name, identify)
         self.from_translators = {
             "hgvs": self._from_hgvs,
         }

diff --git a/tests/extras/cassettes/test_from_spdi.yaml b/tests/extras/cassettes/test_from_spdi.yaml
@@ -0,0 +1,86 @@
+interactions:
+- request:
+    body: null
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      User-Agent:
+      - python-requests/2.31.0
+    method: GET
+    uri: http://localhost:5000/seqrepo/1/metadata/refseq:NC_000019.10
+  response:
+    body:
+      string: "{\n  \"added\": \"2016-08-24T08:19:02Z\",\n  \"aliases\": [\n    \"Ensembl:19\",\n
+        \   \"ensembl:19\",\n    \"GRCh38:19\",\n    \"GRCh38:chr19\",\n    \"GRCh38.p1:19\",\n
+        \   \"GRCh38.p1:chr19\",\n    \"GRCh38.p10:19\",\n    \"GRCh38.p10:chr19\",\n
+        \   \"GRCh38.p11:19\",\n    \"GRCh38.p11:chr19\",\n    \"GRCh38.p12:19\",\n
+        \   \"GRCh38.p12:chr19\",\n    \"GRCh38.p2:19\",\n    \"GRCh38.p2:chr19\",\n
+        \   \"GRCh38.p3:19\",\n    \"GRCh38.p3:chr19\",\n    \"GRCh38.p4:19\",\n    \"GRCh38.p4:chr19\",\n
+        \   \"GRCh38.p5:19\",\n    \"GRCh38.p5:chr19\",\n    \"GRCh38.p6:19\",\n    \"GRCh38.p6:chr19\",\n
+        \   \"GRCh38.p7:19\",\n    \"GRCh38.p7:chr19\",\n    \"GRCh38.p8:19\",\n    \"GRCh38.p8:chr19\",\n
+        \   \"GRCh38.p9:19\",\n    \"GRCh38.p9:chr19\",\n    \"MD5:b0eba2c7bb5c953d1e06a508b5e487de\",\n
+        \   \"NCBI:NC_000019.10\",\n    \"refseq:NC_000019.10\",\n    \"SEGUID:AHxM5/L8jIX08UhBBkKXkiO5rhY\",\n
+        \   \"SHA1:007c4ce7f2fc8c85f4f148410642979223b9ae16\",\n    \"VMC:GS_IIB53T8CNeJJdUqzn9V_JnRtQadwWCbl\",\n
+        \   \"sha512t24u:IIB53T8CNeJJdUqzn9V_JnRtQadwWCbl\",\n    \"ga4gh:SQ.IIB53T8CNeJJdUqzn9V_JnRtQadwWCbl\"\n
+        \ ],\n  \"alphabet\": \"ACGNT\",\n  \"length\": 58617616\n}\n"
+    headers:
+      Connection:
+      - close
+      Content-Length:
+      - '1035'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 12 Mar 2024 12:34:06 GMT
+      Server:
+      - Werkzeug/2.2.2 Python/3.10.4
+    status:
+      code: 200
+      message: OK
+- request:
+    body: null
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      User-Agent:
+      - python-requests/2.31.0
+    method: GET
+    uri: http://localhost:5000/seqrepo/1/metadata/refseq:NC_000013.11
+  response:
+    body:
+      string: "{\n  \"added\": \"2016-08-27T23:50:14Z\",\n  \"aliases\": [\n    \"GRCh38:13\",\n
+        \   \"GRCh38:chr13\",\n    \"GRCh38.p1:13\",\n    \"GRCh38.p1:chr13\",\n    \"GRCh38.p10:13\",\n
+        \   \"GRCh38.p10:chr13\",\n    \"GRCh38.p11:13\",\n    \"GRCh38.p11:chr13\",\n
+        \   \"GRCh38.p12:13\",\n    \"GRCh38.p12:chr13\",\n    \"GRCh38.p2:13\",\n
+        \   \"GRCh38.p2:chr13\",\n    \"GRCh38.p3:13\",\n    \"GRCh38.p3:chr13\",\n
+        \   \"GRCh38.p4:13\",\n    \"GRCh38.p4:chr13\",\n    \"GRCh38.p5:13\",\n    \"GRCh38.p5:chr13\",\n
+        \   \"GRCh38.p6:13\",\n    \"GRCh38.p6:chr13\",\n    \"GRCh38.p7:13\",\n    \"GRCh38.p7:chr13\",\n
+        \   \"GRCh38.p8:13\",\n    \"GRCh38.p8:chr13\",\n    \"GRCh38.p9:13\",\n    \"GRCh38.p9:chr13\",\n
+        \   \"MD5:a5437debe2ef9c9ef8f3ea2874ae1d82\",\n    \"NCBI:NC_000013.11\",\n
+        \   \"refseq:NC_000013.11\",\n    \"SEGUID:2oDBty0yKV9wHo7gg+Bt+fPgi5o\",\n
+        \   \"SHA1:da80c1b72d32295f701e8ee083e06df9f3e08b9a\",\n    \"VMC:GS__0wi-qoDrvram155UmcSC-zA5ZK4fpLT\",\n
+        \   \"sha512t24u:_0wi-qoDrvram155UmcSC-zA5ZK4fpLT\",\n    \"ga4gh:SQ._0wi-qoDrvram155UmcSC-zA5ZK4fpLT\"\n
+        \ ],\n  \"alphabet\": \"ACGKNTY\",\n  \"length\": 114364328\n}\n"
+    headers:
+      Connection:
+      - close
+      Content-Length:
+      - '1002'
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 12 Mar 2024 12:34:06 GMT
+      Server:
+      - Werkzeug/2.2.2 Python/3.10.4
+    status:
+      code: 200
+      message: OK
+version: 1
diff --git a/tests/extras/cassettes/test_hgvs[NC_000007.14:g.55181220del-expected2].yaml b/tests/extras/cassettes/test_hgvs[NC_000007.14:g.55181220del-expected2].yaml
@@ -9,7 +9,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: http://localhost:5000/seqrepo/1/sequence/ga4gh:SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul?start=55181219&end=55181220
   response:
@@ -23,7 +23,7 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Server:
       - Werkzeug/2.2.2 Python/3.10.4
     status:
@@ -39,7 +39,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: http://localhost:5000/seqrepo/1/sequence/ga4gh:SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul?start=55181218&end=55181219
   response:
@@ -53,7 +53,7 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Server:
       - Werkzeug/2.2.2 Python/3.10.4
     status:
@@ -69,7 +69,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: http://localhost:5000/seqrepo/1/sequence/ga4gh:SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul?start=55181220&end=55181221
   response:
@@ -83,7 +83,7 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Server:
       - Werkzeug/2.2.2 Python/3.10.4
     status:
@@ -99,7 +99,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: http://localhost:5000/seqrepo/1/sequence/ga4gh:SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul?start=55181219&end=55181219
   response:
@@ -113,7 +113,7 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Server:
       - Werkzeug/2.2.2 Python/3.10.4
     status:
@@ -129,7 +129,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: http://localhost:5000/seqrepo/1/sequence/ga4gh:SQ.F-LrLMe1SRpfUZHkQmvkVKFEGaoDeHul?start=55181220&end=55181220
   response:
@@ -143,7 +143,7 @@ interactions:
       Content-Type:
       - text/plain; charset=utf-8
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Server:
       - Werkzeug/2.2.2 Python/3.10.4
     status:
@@ -159,7 +159,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=NC_000007.14&rettype=fasta&seq_start=55181220&seq_stop=55181220&tool=bioutils&email=biocommons-dev@googlegroups.com
   response:
@@ -183,20 +183,20 @@ interactions:
       Content-Type:
       - text/plain
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:23 GMT
       Keep-Alive:
       - timeout=4, max=40
       NCBI-PHID:
-      - 322CF705C067C1A500004E8953DC8714.1.1.m_5
+      - 322CFCD26EC09885000045491929D908.1.1.m_5
       NCBI-SID:
-      - F908C0590198759C_1297SID
+      - CC70304937911EDE_9EBESID
       Referrer-Policy:
       - origin-when-cross-origin
       Server:
       - Finatra
       Set-Cookie:
-      - ncbi_sid=F908C0590198759C_1297SID; domain=.nih.gov; path=/; expires=Wed, 19
-        Feb 2025 07:31:18 GMT
+      - ncbi_sid=CC70304937911EDE_9EBESID; domain=.nih.gov; path=/; expires=Tue, 11
+        Mar 2025 21:21:23 GMT
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding:
@@ -224,7 +224,7 @@ interactions:
       Connection:
       - keep-alive
       User-Agent:
-      - python-requests/2.28.2
+      - python-requests/2.31.0
     method: GET
     uri: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=NC_000007.14&rettype=fasta&seq_start=55181220&seq_stop=55181240&tool=bioutils&email=biocommons-dev@googlegroups.com
   response:
@@ -249,20 +249,20 @@ interactions:
       Content-Type:
       - text/plain
       Date:
-      - Mon, 19 Feb 2024 07:31:18 GMT
+      - Mon, 11 Mar 2024 21:21:24 GMT
       Keep-Alive:
       - timeout=4, max=40
       NCBI-PHID:
-      - 322CF705C067C1A500003B8959035020.1.1.m_5
+      - 322CFCD26EC09885000059491D137F58.1.1.m_5
       NCBI-SID:
-      - 0FA55D02B01B7AFC_8F66SID
+      - 11F6059A8AEDFE53_CBBESID
       Referrer-Policy:
       - origin-when-cross-origin
       Server:
       - Finatra
       Set-Cookie:
-      - ncbi_sid=0FA55D02B01B7AFC_8F66SID; domain=.nih.gov; path=/; expires=Wed, 19
-        Feb 2025 07:31:19 GMT
+      - ncbi_sid=11F6059A8AEDFE53_CBBESID; domain=.nih.gov; path=/; expires=Tue, 11
+        Mar 2025 21:21:24 GMT
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding: