def _migrate_proc_tool(project: Project, old_paths: OldPaths, tool: str):
_log(f"MIGRATE PROC TOOL {tool} RESULTS")
tool_dir = "xdsxscale" if tool == "xds" else tool
for dset in _dbg_cutoff(project.get_datasets()):
src_dir = Path(old_paths.process_dir, dset.crystal.id, dset.name,
tool_dir)
if not src_dir.is_dir():
# no tool results found for this dataset
continue
dest_dir = Path(project.get_dataset_process_dir(dset), tool)
_log(f"{src_dir} -> {dest_dir}")
_copytree(src_dir, dest_dir)
update_proc_tool_status(project, tool, dset)
def get_refine_datasets(project: Project, filter: str, refine_tool: str):
"""
perform datasets filtering for 'structure refinement' jobs
filters supported:
'ALL' - all of the project's datasets
'NEW' - datasets that have not been processes with specified refinement tool yet
otherwise the filter is expected to be a comma separated list of dataset names
"""
if filter == "ALL":
return project.get_datasets()
if filter == "NEW":
return _no_results_datasets(project, refine_tool)
return _dataset_by_ids(project, filter)
def get_proc_datasets(project: Project, filter: str, tool: str):
"""
perform datasets filtering for 'data processing' jobs
filters supported:
'ALL' - all of the project's datasets
'NEW' - datasets that have not been processes yet with specified tool
otherwise the filter is expected to be a comma separated list of dataset IDs
"""
if filter == "ALL":
return project.get_datasets()
if filter == "NEW":
return _no_results_datasets(project, tool)
return _dataset_by_ids(project, filter)
def _migrate_refine(project: Project, old_paths: OldPaths):
_log("MIGRATE REFINE RESULTS")
for dset in _dbg_cutoff(project.get_datasets()):
for proc_tool in ["xds", "xdsapp", "dials"]:
proc_dir = "xdsxscale" if proc_tool == "xds" else proc_tool
src_dir = Path(old_paths.results_dir, dset.name, proc_dir)
if not src_dir.is_dir():
# no tool results found for this dataset
continue
dest_dir = Path(project.get_dataset_results_dir(dset), proc_tool)
_log(f"{src_dir} -> {dest_dir}")
# note, we can't use ignore_dangling_symlinks=True
# here due to https://bugs.python.org/issue38523
_copytree(src_dir, dest_dir)
for tool in REFINE_TOOLS:
update_refine_tool_status(project, tool, dset)
for tool in LIGFIT_TOOLS:
_maybe_resync_ligfit_tool(project, tool, dset)
def _get_best_results(project: Project, proc_tool, refine_tool):
if proc_tool == "frag":
proc_tool = None
if refine_tool == "plex":
refine_tool = None
for dataset in project.get_datasets():
refine_results = _get_refine_results(project, dataset, proc_tool, refine_tool)
# sort refine results by R-work, R-free and resolution,
# the result with lowest value(s) is the 'best' one
best_result = refine_results.order_by(
lambda r: (r.r_work, r.r_free, r.resolution)
).first()
if best_result is None:
# no refine results with request proc/refine tool combination
continue
yield best_result
def get_ligfit_datasets(project: Project, filter: str,
ligfit_tool: Optional[str]):
"""
perform datasets filtering for 'ligand fitting' jobs
filters supported:
'ALL' - all of the project's datasets
'NEW' - datasets that have not been processes with specified ligand fitting tools yet
otherwise the filter is expected to be a comma separated list of dataset names
"""
if filter == "ALL":
return project.get_datasets()
if filter == "NEW":
assert ligfit_tool is not None
return _no_results_datasets(project, ligfit_tool)
return _dataset_by_ids(project, filter)
def _no_results_datasets(project: Project, tool: str):
for dataset in project.get_datasets():
res = dataset.result.select(tool=tool).first()
if res is None:
yield dataset