diff --git a/.gitignore b/.gitignore
index a60f727325ff9d5e54be75aeec29ea1118ff5f8f..a81a1ca17283cda57e3c34be881874e31dea4384 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,4 @@
A0A1B0GTU1-O75152*
-.*~
\ No newline at end of file
+.*~
+.docker-bash-history
+.DS_Store
diff --git a/translate2modelcif.py b/translate2modelcif.py
index 6a3ded6411c754526fbd519e878ef39151aab906..4e9e9b2620a8c3d8058ad0fecd39f7f3b3da0be8 100644
--- a/translate2modelcif.py
+++ b/translate2modelcif.py
@@ -16,6 +16,7 @@ import modelcif
import modelcif.associated
import modelcif.dumper
import modelcif.model
+import modelcif.protocol
import modelcif.reference
from ost import io
@@ -218,6 +219,69 @@ def _get_audit_authors():
return ("Foo B", "Bar F")
+def _get_protocol_steps_and_software(trg_ents):
+ """Create the list of protocol steps with software and parameters used."""
+ protocol = []
+
+ # modelling step
+ step = {
+ "method_type": "modeling",
+ "name": "ma_protocol_step.step_name",
+ "details": "ma_protocol_step.details",
+ }
+ # 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"] = {
+ "name": "ColabFold",
+ "classification": "model building",
+ "description": "software.description",
+ "citation": {
+ "pmid": None,
+ "title": "ColabFold - Making protein folding accessible to all",
+ "journal": "bioRxiv",
+ "volume": None,
+ "page_range": None,
+ "year": 2022,
+ "authors": [
+ "Mirdita M",
+ "Schütze K",
+ "Moriwaki Y",
+ "Heo L",
+ "Ovchinnikov S",
+ "Steinegger M",
+ ],
+ "doi": "10.1101/2021.08.15.456425",
+ },
+ "location": "https://github.com/sokrypton/ColabFold",
+ "type": "package",
+ "version": "software.version",
+ }
+ # get parameters
+ step["software_parameters"] = {}
+ protocol.append(step)
+
+ # model selection step
+ # ToDo [input/ internal]: model selection step on a single model is a bit
+ # silly, how do we get a list of models?
+ step = {
+ "method_type": "model selection",
+ "name": "ma_protocol_step.step_name",
+ "details": "ma_protocol_step.details",
+ }
+ step["input"] = "model"
+ step["output"] = "model"
+ step["software"] = {}
+ step["software_parameters"] = {}
+ protocol.append(step)
+
+ return protocol
+
+
def _get_title():
"""Get a title for this modelling experiment."""
# ToDo [input]: Add title
@@ -379,28 +443,9 @@ def _get_scores(data, prfx):
data.update(scrs_json)
-def _store_as_modelcif(interaction_name, data_json, ost_ent, file_prfx):
- """Mix all the data into a ModelCIF file."""
- print(" generating ModelCIF objects...", end="")
- pstart = timer()
- # ToDo [internal]: Get protocol/ software
- # ToDo [internal]: Get QA metrics
- # create system to gather all the data
- system = modelcif.System(
- title=data_json["title"],
- id=interaction_name.upper(),
- model_details=data_json["model_details"],
- )
- # create target entities, references, source, asymmetric units & assembly
- # for source we assume all chains come from the same taxon
- source = ihm.source.Natural(
- ncbi_taxonomy_id=data_json["target_entities"][0]["up_ncbi_taxid"],
- scientific_name=data_json["target_entities"][0]["up_organism"],
- )
-
- # create an asymmetric unit and an entity per target sequence
- asym_units = {}
- for cif_ent in data_json["target_entities"]:
+def _get_modelcif_entities(target_ents, source, asym_units, system):
+ """Create ModelCIF entities and asymmetric units."""
+ for cif_ent in target_ents:
# ToDo [input]: Get entity description
mdlcif_ent = modelcif.Entity(
cif_ent["pdb_sequence"],
@@ -430,6 +475,31 @@ def _store_as_modelcif(interaction_name, data_json, ost_ent, file_prfx):
)
system.target_entities.append(mdlcif_ent)
+
+def _store_as_modelcif(interaction_name, data_json, ost_ent, file_prfx):
+ """Mix all the data into a ModelCIF file."""
+ print(" generating ModelCIF objects...", end="")
+ pstart = timer()
+ # ToDo [internal]: Get protocol/ software
+ # create system to gather all the data
+ system = modelcif.System(
+ title=data_json["title"],
+ id=interaction_name.upper(),
+ model_details=data_json["model_details"],
+ )
+ # create target entities, references, source, asymmetric units & assembly
+ # for source we assume all chains come from the same taxon
+ source = ihm.source.Natural(
+ ncbi_taxonomy_id=data_json["target_entities"][0]["up_ncbi_taxid"],
+ scientific_name=data_json["target_entities"][0]["up_organism"],
+ )
+
+ # create an asymmetric unit and an entity per target sequence
+ asym_units = {}
+ _get_modelcif_entities(
+ data_json["target_entities"], source, asym_units, system
+ )
+
# ToDo [input]: Get Assembly name
assembly = modelcif.Assembly(
asym_units.values(), name="ma_struct_assembly_details.assembly_name"
@@ -460,6 +530,56 @@ def _store_as_modelcif(interaction_name, data_json, ost_ent, file_prfx):
)
system.model_groups.append(model_group)
+ # Add protocol
+ protocol = modelcif.protocol.Protocol()
+ for js_step in data_json["protocol"]:
+ sftwre = None
+ # ToDo [input]: Turn into software group if parameters are available
+ # ToDo [input]: Get software.description
+ # ToDo [input]: Get software.version
+ if js_step["software"]:
+ sftwre = modelcif.Software(
+ js_step["software"]["name"],
+ js_step["software"]["classification"],
+ js_step["software"]["description"],
+ js_step["software"]["location"],
+ js_step["software"]["type"],
+ js_step["software"]["version"],
+ citation=ihm.Citation(
+ pmid=js_step["software"]["citation"]["pmid"],
+ title=js_step["software"]["citation"]["title"],
+ journal=js_step["software"]["citation"]["journal"],
+ volume=js_step["software"]["citation"]["volume"],
+ page_range=js_step["software"]["citation"]["page_range"],
+ year=js_step["software"]["citation"]["year"],
+ authors=js_step["software"]["citation"]["authors"],
+ doi=js_step["software"]["citation"]["doi"],
+ ),
+ )
+ if js_step["input"] == "target_sequences":
+ input_data = modelcif.data.DataGroup(system.target_entities)
+ elif js_step["input"] == "model":
+ input_data = model
+ else:
+ raise RuntimeError(f"Unknown protocol input: '{js_step['input']}'")
+ if js_step["output"] == "model":
+ output_data = model
+ else:
+ raise RuntimeError(
+ f"Unknown protocol output: '{js_step['output']}'"
+ )
+ protocol.steps.append(
+ modelcif.protocol.Step(
+ input_data=input_data,
+ output_data=output_data,
+ name=js_step["name"],
+ details=js_step["details"],
+ software=sftwre,
+ )
+ )
+ protocol.steps[-1].method_type = js_step["method_type"]
+ system.protocols.append(protocol)
+
# write modelcif System to file
print(" write to disk...", end="", flush=True)
pstart = timer()
@@ -484,6 +604,7 @@ def _create_model_json(data, pdb_file, up_acs):
"""Create a dictionary (mimicking JSON) that contains all the data."""
data["target_entities"], ost_ent = _get_entities(pdb_file, up_acs)
+ data["protocol"] = _get_protocol_steps_and_software(data["target_entities"])
return ost_ent