If model sequence and UniProtKB sequence do not match, go down the UniProtKB entrie's history

translate2modelcif.py

@@ -561,8 +561,8 @@ def _check_sequence(up_ac, sequence):
             )
 
 
-def _fetch_upkb_entry(up_ac):
-    """Fetch data for an UniProtKB entry."""
+def _get_n_parse_up_entry(up_ac, up_url):
+    """Get data for an UniProtKB entry and parse it."""
     # This is a simple parser for UniProtKB txt format, instead of breaking it
     # up into multiple functions, we just allow many many branches & statements,
     # here.
@@ -571,9 +571,7 @@ def _fetch_upkb_entry(up_ac):
     data["up_organism"] = ""
     data["up_sequence"] = ""
     data["up_ac"] = up_ac
-    rspns = requests.get(
-        f"https://rest.uniprot.org/uniprotkb/{up_ac}.txt", timeout=180
-    )
+    rspns = requests.get(up_url, timeout=180)
     for line in rspns.iter_lines(decode_unicode=True):
         if line.startswith("ID   "):
             sline = line.split()
@@ -615,6 +613,11 @@ def _fetch_upkb_entry(up_ac):
                 data["up_last_mod"] = datetime.datetime.strptime(
                     dt_flds[0], "%d-%b-%Y"
                 )
+            elif dt_flds[1].upper().startswith("ENTRY VERSION "):
+                data["up_entry_version"] = dt_flds[1][len("ENTRY VERSION ") :]
+                if data["up_entry_version"][-1] == ".":
+                    data["up_entry_version"] = data["up_entry_version"][:-1]
+                data["up_entry_version"] = int(data["up_entry_version"])
         elif line.startswith("GN   Name="):
             data["up_gn"] = line[len("GN   Name=") :].split(";")[0]
             data["up_gn"] = data["up_gn"].split("{")[0].strip()
@@ -648,14 +651,37 @@ def _fetch_upkb_entry(up_ac):
     return data
 
 
+def _fetch_upkb_entry(up_ac):
+    """Get an UniProtKB entry."""
+    return _get_n_parse_up_entry(
+        up_ac, f"https://rest.uniprot.org/uniprotkb/{up_ac}.txt"
+    )
+
+
+def _fetch_unisave_entry(up_ac, version):
+    """Get an UniSave entry, in contrast to an UniProtKB entry, that allows us
+    to specify a version."""
+    return _get_n_parse_up_entry(
+        up_ac,
+        f"https://rest.uniprot.org/unisave/{up_ac}?format=txt&"
+        + f"versions={version}",
+    )
+
+
 def _get_upkb_for_sequence(sqe, up_ac):
     """Get UniProtKB entry data for given sequence."""
     up_data = _fetch_upkb_entry(up_ac)
-    if sqe != up_data["up_sequence"]:
-        raise RuntimeError(
-            f"Sequences not equal from file: {sqe}, from UniProtKB: "
-            + f"{up_data['up_sequence']} ({up_ac})"
-        )
+    while sqe != up_data["up_sequence"]:
+        if up_data["up_entry_version"] > 1:
+            up_data = _fetch_unisave_entry(
+                up_ac, up_data["up_entry_version"] - 1
+            )
+        else:
+            raise RuntimeError(
+                f"Sequences not equal from file: {sqe}, from UniProtKB: "
+                f"{up_data['up_sequence']} ({up_ac}), checked entire entry "
+                "history."
+            )
     return up_data