Skip to content

Structure format #101

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jdmartinez24 merged 3 commits into from
Jan 14, 2026
Merged

Structure format #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d6cfb21
Set structure format from file extension if provided
jdmartinez24 Jan 13, 2026
b588aff
add parameter for structure_format and add exception to create CIFdic…
jdmartinez24 Jan 13, 2026
6b88da4
Return empty list if pdb/cif does not contain protein names
jdmartinez24 Jan 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/vlab4mic/experiments.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
class ExperimentParametrisation:
experiment_id: str = "vLab4mic_experiment"
structure_id: str = "1XI5"
structure_format: str = "CIF"
configuration_path: str = ""
structure_label: str = "NHS_ester"
fluorophore_id: str = "AF647"
Expand Down Expand Up @@ -194,6 +195,7 @@ def select_structure(self, structure_id="1XI5", build=True, structure_path:str =
if structure_path is not None:
self.structure_path = structure_path
self.structure_id = structure_id
self.structure_format = structure_path.split(".")[-1].upper()
else:
self.structure_id = structure_id
if build:
Expand Down Expand Up @@ -450,7 +452,7 @@ def _build_structure(self, keep=True):
"""
if self.structure_id and self.structure_path:
struct, struct_param = load_structure(
self.structure_id, self.configuration_path, self.structure_path
self.structure_id, self.configuration_path, self.structure_path, self.structure_format
)
self.structure = struct
self.objects_created["structure"] = True
Expand Down
106 changes: 57 additions & 49 deletions src/vlab4mic/generate/molecular_structure.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,11 @@ def list_protein_names(self):
list of str
List of protein names.
"""
return list(self.protein_names.keys())
if self.protein_names is not None:
if len(list(self.protein_names.keys())) > 0:
return list(self.protein_names.keys())
else:
return []

def _random_substring(string, size=5):
"""
Expand Down Expand Up @@ -254,57 +258,61 @@ def generate_assemmbly_operations(self):
"""
Parse the rotation/translation operations needed to construct a molecular assembly from an asymmetric unit.
"""
if self.CIFdictionary is None: # check if already created
self.generate_MMCIF_dictionary()
if "AlphaFoldDB" in self.CIFdictionary["_database_2.database_id"]:
if self.format == "PDB":
print("Assembly operations are only defined for CIF format files.")
self.assymetric_defined = False
else:
# get to know how many transformations there are
transformation_ids = self.CIFdictionary["_pdbx_struct_oper_list.id"]
# each element of the list is pair of matrix-vector needed to transform data
# iterate over each of the transformations
assembly_transformations = []
for tr in range(len(transformation_ids)):
row1 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][3]"][tr],
]

row2 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][3]"][tr],
]

row3 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][3]"][tr],
]
rotation_matrix = np.array([row1, row2, row3], dtype="float")

vector = np.array(
[
self.CIFdictionary["_pdbx_struct_oper_list.vector[1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.vector[2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.vector[3]"][tr],
],
dtype="float",
)
assembly_transformations.append([rotation_matrix, vector])
struct_oper_dictionary = dict(zip(transformation_ids, assembly_transformations))
if len(transformation_ids) > 1:
self.assymetric_defined = True
# print(
# "This model is defined with more than one symmetric transformation.
# Will consider the assembly as assymetric defined"
# )
else:
# when no assembly unit exist, there is only 1 transform expected
if self.CIFdictionary is None: # check if already created
self.generate_MMCIF_dictionary()
if "AlphaFoldDB" in self.CIFdictionary["_database_2.database_id"]:
self.assymetric_defined = False
# print("This model is defined with only one symmetric transformation")
self.assembly_operations = struct_oper_dictionary
else:
# get to know how many transformations there are
transformation_ids = self.CIFdictionary["_pdbx_struct_oper_list.id"]
# each element of the list is pair of matrix-vector needed to transform data
# iterate over each of the transformations
assembly_transformations = []
for tr in range(len(transformation_ids)):
row1 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[1][3]"][tr],
]

row2 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[2][3]"][tr],
]

row3 = [
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.matrix[3][3]"][tr],
]
rotation_matrix = np.array([row1, row2, row3], dtype="float")

vector = np.array(
[
self.CIFdictionary["_pdbx_struct_oper_list.vector[1]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.vector[2]"][tr],
self.CIFdictionary["_pdbx_struct_oper_list.vector[3]"][tr],
],
dtype="float",
)
assembly_transformations.append([rotation_matrix, vector])
struct_oper_dictionary = dict(zip(transformation_ids, assembly_transformations))
if len(transformation_ids) > 1:
self.assymetric_defined = True
# print(
# "This model is defined with more than one symmetric transformation.
# Will consider the assembly as assymetric defined"
# )
else:
# when no assembly unit exist, there is only 1 transform expected
self.assymetric_defined = False
# print("This model is defined with only one symmetric transformation")
self.assembly_operations = struct_oper_dictionary

def generate_assembly_reference_point(self):
"""
Expand Down
6 changes: 3 additions & 3 deletions src/vlab4mic/workflows.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
from .utils.data_format.structural_format import label_builder_format
from pathlib import Path

def load_structure(structure_id: str = None, config_dir=None, structure_path=None):
def load_structure(structure_id: str = None, config_dir=None, structure_path=None, structure_format="CIF"):
"""
Initialise a BioPython object for the PDB/CIF ID and retrieve available information about specific labelling.

Expand All @@ -47,10 +47,10 @@ def load_structure(structure_id: str = None, config_dir=None, structure_path=Non
if structure_path is not None:
print("Loading structure from local file")
structure = build_structure_cif(
cif_file=structure_path, struct_title="", cif_id=structure_id
cif_file=structure_path, struct_title="", cif_id=structure_id, format_type=structure_format
)
structure_params = dict(
model = {"ID": structure_id, "format": "CIF", "title": "", "database": ""},
model = {"ID": structure_id, "format": structure_format, "title": "", "database": ""},
)
print("Structure Loaded!")
return structure, structure_params
Expand Down