Fix homoers and outdated UniProtKB sequences

projects/human-heterodimers-w-crosslinks/README.md

@@ -6,6 +6,9 @@
 
 This project consists of around 800 heterodimer models for the human reference proteome. Modelling was done with [ColabFold](https://colabfold.mmseqs.com)/ [LocalColabFold](https://github.com/YoshitakaMo/localcolabfold). Model selection is special in a sense that for some heterodimers experimental crosslinking data is available guiding the choice, otherwise top-ranking models are used.
 
+- special for this set: has a few homomers
+- special for this set: old versions of UniProtKB sequences are traced down to a matching version in the history/ using UniSave
+
 <how are the ModelCIF files created using this software>
 
 These models qualify as "de novo modelling".

projects/human-heterodimers-w-crosslinks/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://www.uniprot.org/uniprot/{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()
@@ -648,28 +651,64 @@ 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']}"
-        )
+    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
 
 
 def _get_entities(pdb_file, up_acs):
     """Gather data for the mmCIF (target) entities."""
     entities = []
-
     ost_ent = io.LoadPDB(pdb_file)
+    already_seen = []
     for i, chn in enumerate(ost_ent.chains):
         cif_ent = {}
         sqe = _get_sequence(chn)
+        try:
+            e_idx = already_seen.index(up_acs[i])
+        except ValueError:
+            pass
+        else:
+            if sqe != entities[e_idx]["pdb_sequence"]:
+                _abort_msg(
+                    "Sequences are different for two chains of the same "
+                    "UniProtKB AC. This case is not implemented, yet."
+                )
+            entities[e_idx]["pdb_chain_id"].append(chn.name)
+            continue
+        already_seen.append(up_acs[i])
         upkb = _get_upkb_for_sequence(sqe, up_acs[i])
         cif_ent["pdb_sequence"] = sqe
-        cif_ent["pdb_chain_id"] = chn.name
+        cif_ent["pdb_chain_id"] = [chn.name]
         cif_ent["description"] = (
             f"{upkb['up_organism']} {upkb['up_gn']} " f"({upkb['up_ac']})"
         )
@@ -712,7 +751,8 @@ def _get_modelcif_entities(target_ents, source, asym_units, system):
                 )
             ],
         )
-        asym_units[cif_ent["pdb_chain_id"]] = modelcif.AsymUnit(mdlcif_ent)
+        for pdb_chain_id in cif_ent["pdb_chain_id"]:
+            asym_units[pdb_chain_id] = modelcif.AsymUnit(mdlcif_ent)
         system.target_entities.append(mdlcif_ent)