Skip to content
Snippets Groups Projects
Commit fa3473b8 authored by B13nch3n's avatar B13nch3n
Browse files

Draft of protocol

parent a7f1fdfe
Branches
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Showing
with 131 additions and 48 deletions
translate2modelcif.py
+ 131
− 48
View file @ fa3473b8
...@@ -240,7 +240,10 @@ def _get_protocol_steps_and_software(cnfg_file): ...@@ -240,7 +240,10 @@ def _get_protocol_steps_and_software(cnfg_file):
step = { step = {
"method_type": "modeling", "method_type": "modeling",
"name": "ma_protocol_step.step_name", "name": "ma_protocol_step.step_name",
"details": "ma_protocol_step.details", "details": "Model using AlphaFold-Multimer (AlphaFold v2.2.0), "
+ "without amber relaxation and producing 5 models with up to 3 "
+ "recycles each, starting from paired and unparied MSAs for the "
+ "dimers using MMseqs2.",
} }
# get input data # get input data
# Must refer to data already in the JSON, so we try keywords # Must refer to data already in the JSON, so we try keywords
...@@ -249,31 +252,99 @@ def _get_protocol_steps_and_software(cnfg_file): ...@@ -249,31 +252,99 @@ def _get_protocol_steps_and_software(cnfg_file):
# Must refer to existing data, so we try keywords # Must refer to existing data, so we try keywords
step["output"] = "model" step["output"] = "model"
# get software # get software
step["software"] = { step["software"] = [
"name": "ColabFold", {
"classification": "model building", "name": "ColabFold",
"description": "software.description", "classification": "model building",
"citation": { # ToDo: Get description for ColabFold
"pmid": None, "description": "software.description",
"title": "ColabFold - Making protein folding accessible to all", "citation": {
"journal": "bioRxiv", "pmid": None,
"volume": None, "title": "ColabFold - Making protein folding accessible to all",
"page_range": None, "journal": "bioRxiv",
"year": 2022, "volume": None,
"authors": [ "page_range": None,
"Mirdita M", "year": 2022,
"Schütze K", "authors": [
"Moriwaki Y", "Mirdita M",
"Heo L", "Schütze K",
"Ovchinnikov S", "Moriwaki Y",
"Steinegger M", "Heo L",
], "Ovchinnikov S",
"doi": "10.1101/2021.08.15.456425", "Steinegger M",
],
"doi": "10.1101/2021.08.15.456425",
},
"location": "https://github.com/sokrypton/ColabFold",
"type": "package",
"version": "1.2.0",
}, },
"location": "https://github.com/sokrypton/ColabFold", {
"type": "package", "name": "MMseqs2",
"version": "1.2.0", "classification": "data collection",
} "description": "Many-against-Many sequence searching",
"citation": {
"pmid": "30615063",
"title": "MMseqs2 desktop and local web server app for fast, "
+ "interactive sequence searches",
"journal": "Bioinformatics",
"volume": 35,
"page_range": (2856, 2858),
"year": 2019,
"authors": [
"Mirdita M",
"Steinegger M",
"Söding J",
],
"doi": "10.1093/bioinformatics/bty1057",
},
"location": "https://github.com/soedinglab/mmseqs2",
"type": "package",
"version": None,
},
{
"name": "AlphaFold-Multimer",
"classification": "model building",
"description": "Structure prediction",
"citation": {
"pmid": None,
"title": "Protein complex prediction with "
+ "AlphaFold-Multimer.",
"journal": "bioRxiv",
"volume": None,
"page_range": None,
"year": 2021,
"authors": [
"Evans R",
"O'Neill M",
"Pritzel A",
"Antropova N",
"Senior A",
"Green T",
"Žídek A",
"Bates R",
"Blackwell S",
"Yim J",
"Ronneberger O",
"Bodenstein S",
"Zielinski M",
"Bridgland A",
"Potapenko A",
"Cowie A",
"Tunyasuvunakool K",
"Jain R",
"Clancy E",
"Kohli P",
"Jumper J",
"Hassabis D",
],
"doi": "10.1101/2021.10.04.463034",
},
"location": "https://github.com/deepmind/alphafold",
"type": "package",
"version": "2.1.1",
},
]
# get parameters # get parameters
with open(cnfg_file, encoding="utf8") as jfh: with open(cnfg_file, encoding="utf8") as jfh:
step["software_parameters"] = json.load(jfh) step["software_parameters"] = json.load(jfh)
...@@ -285,11 +356,14 @@ def _get_protocol_steps_and_software(cnfg_file): ...@@ -285,11 +356,14 @@ def _get_protocol_steps_and_software(cnfg_file):
step = { step = {
"method_type": "model selection", "method_type": "model selection",
"name": "ma_protocol_step.step_name", "name": "ma_protocol_step.step_name",
"details": "ma_protocol_step.details", "details": "Select best model, which is either the top-ranked model "
+ "as determined by the ColabFold pipeline "
+ "(iptmscore*0.8+ptmscore*0.2), or else the model with best "
+ "congruence with crosslinks reported in the related study.",
} }
step["input"] = "model" step["input"] = "model"
step["output"] = "model" step["output"] = "model"
step["software"] = {} step["software"] = []
step["software_parameters"] = {} step["software_parameters"] = {}
protocol.append(step) protocol.append(step)
...@@ -504,37 +578,46 @@ def _get_modelcif_entities(target_ents, source, asym_units, system): ...@@ -504,37 +578,46 @@ def _get_modelcif_entities(target_ents, source, asym_units, system):
system.target_entities.append(mdlcif_ent) system.target_entities.append(mdlcif_ent)
def _assemble_modelcif_software(soft_dict):
"""Create a modelcif.Software instance from dictionary."""
return modelcif.Software(
soft_dict["name"],
soft_dict["classification"],
soft_dict["description"],
soft_dict["location"],
soft_dict["type"],
soft_dict["version"],
citation=ihm.Citation(
pmid=soft_dict["citation"]["pmid"],
title=soft_dict["citation"]["title"],
journal=soft_dict["citation"]["journal"],
volume=soft_dict["citation"]["volume"],
page_range=soft_dict["citation"]["page_range"],
year=soft_dict["citation"]["year"],
authors=soft_dict["citation"]["authors"],
doi=soft_dict["citation"]["doi"],
),
)
def _get_modelcif_protocol(protocol_steps, target_entities, model): def _get_modelcif_protocol(protocol_steps, target_entities, model):
"""Create the protocol for the ModelCIF file.""" """Create the protocol for the ModelCIF file."""
protocol = modelcif.protocol.Protocol() protocol = modelcif.protocol.Protocol()
for js_step in protocol_steps: for js_step in protocol_steps:
sftwre = None sftwre = None
# ToDo [input]: Turn into software group if parameters are available # ToDo [input]: Turn into software group if parameters are available
# ToDo [input]: Get software.description
if js_step["software"]: if js_step["software"]:
sftwre = modelcif.Software( if len(js_step["software"]) == 1:
js_step["software"]["name"], sftwre = _assemble_modelcif_software(js_step["software"][0])
js_step["software"]["classification"], else:
js_step["software"]["description"], sftwre = []
js_step["software"]["location"], for sft in js_step["software"]:
js_step["software"]["type"], sftwre.append(_assemble_modelcif_software(sft))
js_step["software"]["version"], sftwre = modelcif.SoftwareGroup(elements=sftwre)
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['software_parameters']: # if js_step['software_parameters']:
# params = [] # params = []
# # ToDo [internal]: handle lists! # # ToDo [internal]: handle lists!
# for k, v in js_step['software_parameters'].items(): # for k, v in js_step['software_parameters'].items():
# print(k, v.__class__)
# params.append( # params.append(
# modelcif.SoftwareParameter(k, v) # modelcif.SoftwareParameter(k, v)
# ) # )
...@@ -711,4 +794,4 @@ if __name__ == "__main__": ...@@ -711,4 +794,4 @@ if __name__ == "__main__":
# LocalWords: mdlcf mdlcif asym AsymUnit init kwargs atm pos het hetatom pTM # LocalWords: mdlcf mdlcif asym AsymUnit init kwargs atm pos het hetatom pTM
# LocalWords: biso ujson GlobalPTM pLDDT ptm jfh numpy np GlobalPLDDT lDDT # LocalWords: biso ujson GlobalPTM pLDDT ptm jfh numpy np GlobalPLDDT lDDT
# LocalWords: plddt LocalPLDDT timeit PAE MetricType LocalPairwisePAE lpae # LocalWords: plddt LocalPLDDT timeit PAE MetricType LocalPairwisePAE lpae
# LocalWords: nd pae qa pstart # LocalWords: nd pae qa pstart ColabFold
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment