Add authors and protocol to ModelCIF files

projects/novelfams/translate2modelcif.py

@@ -426,9 +426,6 @@ def _get_modelcif_protocol_data(data_label, target_entities, model):
     """Assemble data for a ModelCIF protocol step."""
     if data_label == "target_sequences":
         data = modelcif.data.DataGroup(target_entities)
-    elif data_label == "target_sequences_and_MSA":
-        data = modelcif.data.DataGroup(target_entities)
-        data.append(aln_data)
     elif data_label == "model":
         data = model
     else:
@@ -492,6 +489,29 @@ def _get_assoc_zip_file(fle_path, data_json):
     return zfile
 
 
+def _get_audit_authors():
+    """Return the list of authors that produced this model."""
+    return (
+        "Rodriguez del Rio, Alvaro",
+        "Giner-Lamia, Joaquin",
+        "Cantalapiedra, Carlo P.",
+        "Botas, Jorge",
+        "Deng, Ziqi",
+        "Hernandez-Plaza, Ana",
+        "Munar-Palmer, Marti",
+        "Santamaria-Hernando, Saray",
+        "Rodriguez-Herva, Jose J.",
+        "Ruscheweyh, Hans-Joachim",
+        "Paoli, Lucas",
+        "Schmidt, Thomas S.B.",
+        "Sunagawa, Shinichi",
+        "Bork, Peer",
+        "Lopez-Solanilla, Emilia",
+        "Pedro Coelho, Luis",
+        "Huerta-Cepas, Jaime",
+    )
+
+
 def _store_as_modelcif(
     data_json,
     ost_ent,
@@ -511,6 +531,9 @@ def _store_as_modelcif(
     asym_units = {}
     _get_modelcif_entities(data_json["target_entities"], asym_units, system)
 
+    # audit_authors
+    system.authors.extend(data_json["audit_authors"])
+
     # set up the model to produce coordinates
     model = _OST2ModelCIF(
         assembly=modelcif.Assembly(asym_units.values()),
@@ -543,6 +566,19 @@ def _store_as_modelcif(
         os.chdir(oldpwd)
 
 
+def _get_af2_software():
+    """Get AF2 as dictionary, suitable to create a modelcif software object."""
+    return {
+        "name": "AlphaFold",
+        "classification": "model building",
+        "description": "Structure prediction",
+        "citation": ihm.citations.alphafold2,
+        "location": "https://github.com/deepmind/alphafold",
+        "type": "package",
+        "version": None,
+    }
+
+
 def _get_protocol_steps_and_software_colabfold(config_data):
     """Get protocol steps for ColabFold models."""
     protocol = []
@@ -571,17 +607,7 @@ def _get_protocol_steps_and_software_colabfold(config_data):
             "version": None,
         }
     ]
-    step["software"].append(
-        {
-            "name": "AlphaFold",
-            "classification": "model building",
-            "description": "Structure prediction",
-            "citation": ihm.citations.alphafold2,
-            "location": "https://github.com/deepmind/alphafold",
-            "type": "package",
-            "version": None,
-        }
-    )
+    step["software"].append(_get_af2_software())
     step["software_parameters"] = None
     protocol.append(step)
 
@@ -595,11 +621,43 @@ def _get_config_colabfold():
     return {"description": description}
 
 
+def _get_config_alphafold():
+    """Get config variables for AlphaFold"""
+    description = "Model generation using AlphaFold."
+
+    return {"description": description}
+
+
+def _get_protocol_steps_and_software_alphafold(config_data):
+    """Get protocol steps for AF2 based models."""
+    protocol = []
+
+    # modelling step
+    step = {
+        "method_type": "modeling",
+        "name": None,
+        "details": config_data["description"],
+    }
+    # get input data
+    # Must refer to data already in the JSON, so we try keywords
+    step["input"] = "target_sequences"
+    # get output data
+    # Must refer to existing data, so we try keywords
+    step["output"] = "model"
+    # get software
+    step["software"] = [_get_af2_software()]
+    step["software_parameters"] = None
+    protocol.append(step)
+
+    return protocol
+
+
 def _get_protocol_steps_and_software(mdl_id, af2_lst):
     """Get protocol steps for this model, make a difference between AF2 and
     ColabFold models."""
     if mdl_id in af2_lst:
-        protocol = _get_protocol_steps_and_software_alphafold()
+        config_data = _get_config_alphafold()
+        protocol = _get_protocol_steps_and_software_alphafold(config_data)
     else:
         config_data = _get_config_colabfold()
         protocol = _get_protocol_steps_and_software_colabfold(config_data)
@@ -620,6 +678,7 @@ def _translate2modelcif_single(
 
     # gather data into JSON-like structure
     mdlcf_json = {}
+    mdlcf_json["audit_authors"] = _get_audit_authors()
     mdlcf_json["mdl_id"] = fam_name  # used for entry ID
     mdlcf_json["protocol"] = _get_protocol_steps_and_software(
         fam_name, af2_lst