def getLigandResIds(ligchemid: str, struct: Structure) -> List[Residue]:
"""Returns a list of dictionaries specifying each _ligand_ of type @ligchemid as a biopython-residue inside a given @struct."""
"""*ligchemids are of type https://www.rcsb.org/ligand/IDS"""
ligandResidues: List[Residue] = list(
filter(lambda x: x.get_resname() == ligchemid,
list(struct.get_residues())))
return ligandResidues
def featurize(structure: Structure) -> list[Any]:
"""
Calculates 3D ML features from the `structure`.
"""
structure1 = freesasa.Structure(pdbpath)
result = freesasa.calc(structure1)
area_classes = freesasa.classifyResults(result, structure1)
Total_area = []
Total_area.append(result.totalArea())
Polar_Apolar = []
for key in area_classes:
# print( key, ": %.2f A2" % area_classes[key])
Polar_Apolar.append(area_classes[key])
# get all the residues
residues = [res for res in structure.get_residues()]
seq_length = []
seq_length.append(len(residues))
# calculate some random 3D features (you should be smarter here!)
protein_length = residues[1]["CA"] - residues[-2]["CA"]
angle = calc_dihedral(
residues[1]["CA"].get_vector(),
residues[2]["CA"].get_vector(),
residues[-3]["CA"].get_vector(),
residues[-2]["CA"].get_vector(),
)
# create the feature vector
features = [Total_area, Polar_Apolar, protein_length, seq_length, angle]
return features
def get_ptc_residues(struct: Structure, pdbid: str,
conserved_nucleotides: List[int]) -> List[Residue]:
ECOLI_PTC_CONSERVED_NUCLEOTIDES = [
'2055', '2451', '2452', '2504', '2505', '2506', '2507'
]
def belongs_to_ptc(x: Residue):
return int(x.get_id()[1]) in conserved_nucleotides
PTC_residues = filter(belongs_to_ptc, [*struct.get_residues()])
return [*PTC_residues]
def featurize(structure: Structure) -> list[Any]:
"""
Calculates 3D ML features from the `structure`.
"""
# get all the residues
residues = [res for res in structure.get_residues()]
# calculate some random 3D features (you should be smarter here!)
protein_length = residues[1]["CA"] - residues[-2]["CA"]
angle = calc_dihedral(
residues[1]["CA"].get_vector(),
residues[2]["CA"].get_vector(),
residues[-3]["CA"].get_vector(),
residues[-2]["CA"].get_vector(),
)
# create the feature vector
features = [protein_length, angle]
return features
def getLigandResIds(ligchemid:str, struct: Structure, dict_or_res:bool='dict')->List[ResidueFullIdDict]:
"""Returns a list of dictionaries specifying each ligand as a residue inside a given struct."""
ligandResidues: List[Residue] = list(filter(lambda x: x.get_resname() == ligchemid, list( struct.get_residues() )))
if dict_or_res == 'dict':
return [ ResidueFullIdDict(res) for res in ligandResidues ]
else:
return ligandResidues
def getLigandsResIds(ligChemIds:List[str], struct: Structure)->List[ResidueFullIdDict]:
"""Returns a list of dictionaries specifying each ligand as a residue inside a given struct."""
ligandResidues: List[Residue] = list(filter(lambda x: x.get_resname() in ligChemIds, list( struct.get_residues() )))
return [ ResidueFullIdDict(res) for res in ligandResidues ]
class PyRyStructure(object):
"""
class represents structure as entity (very wide definition)
used for storing information about structures,
creating BIO.pdb structures,
saving structure files etc.
"""
def __init__(self, structure=None):
if structure: self.struct = structure
else: self.struct = None
self.sequence = '' # sequence taken from structure
#----------------will decide on one of these 3 ----------------------------
self.center_of_mass = [] # [x,y,z] coords of center of mass
self.geometric_center = [] # geometric centre
self.center = None # actual center of given complex component
#--------------------------------------------------------------------------
self.chain = '' # chain name from structure file
self.moltype = '' # protein, DNA, RNA
def __str__(self):
return "%s %s %s %s %s"%(self.struct, self.chain, self.center_of_mass,\
self.moltype, self.sequence)
def add_chain_to_struct(self, chain_id):
"""
adds another model to BIO.pdb structure object
Parameters:
-----------
chain_id : chain name
Returns:
---------
self.struct : Bio.PDB structure with new chain
"""
chain = Chain(chain_id)
self.struct[0].add(chain)
def add_residues_to_structure(self, struct, chain_id, chain2_id):
"""
adds residues from struct to a given structure (self.structure)
Parameters:
-----------
struct : template structure object with residues which will
be added to self.structure object
chain_id : name of template chain
chain2_id : name of new chain in self.struct
Returns:
---------
self.stuct : with extra residues
"""
residues = struct[0][chain_id].child_list
[self.struct[0][chain2_id].add(res) for res in residues]
def calculate_atom_atom_distance(self, atom1, atom2):
"""
calculates distance between two atoms
Parameters:
-----------
atom1, atom2 : Bio.PDB.Atom entities
Returns:
---------
distance from atom1 to atom2 in 3D space
Raises:
-------
PyRyStructureError if parameters are not Bio.PDB.Atom entities
"""
if is_structure(): return atom1 - atom2
def calculate_centre_of_mass(self, entity=None, geometric=False):
"""
calculates centre of mass for given structure
Returns gravitic or geometric center of mass of an Entity.
Geometric assumes all masses are equal (geometric=True)
Defaults to Gravitic.
Parameters:
-----------
geometric : optional
Returns:
---------
centre of mass coordinates as [x,y,z] list
Raises:
-------
ValueError : if wrong object is given as a target
PyRyStructureError : no PyRyStructure object
"""
#if self.struct == None: raise PyRyStructureError("You haven't provided \
# any structure to PyRyStructure class")
if isinstance(self.struct,
Entity.Entity): # Structure, Model, Chain, Residue
atom_list = self.struct.get_atoms()
elif hasattr(entity, '__iter__') and filter(lambda x: x.level ==\
'A', entity): # List of Atoms
atom_list = entity
else: # Some other weirdo object
raise ValueError('Center of Mass can only be calculated from \n\
the following objects:Structure, Model, Chain, Residue, list of Atoms.'
)
new_centre = [0., 0., 0.]
whole_mass = 0
for atom in atom_list:
atom_centre = array([
float(atom.coord[0]),
float(atom.coord[1]),
float(atom.coord[2])
])
whole_mass += atom.molweight
new_centre += atom_centre * atom.molweight
new_centre /= whole_mass
self.center_of_mass = new_centre
return self.center_of_mass
def create_PDB_obj(self, id, filename):
"""
creates Bio.PDB object from pdb file
Parameters:
-----------
id : name of structure
filename : file name
"""
parser = PDBParser()
self.struct = parser.get_structure(str(id), filename)
def create_new_structure(self, name, chain_id):
"""
creates new Bio.PDB structure object
Parameters:
-----------
name : structure name
chain_id : chain name (e.g. A, B, C)
Returns:
---------
self.struct : Bio.PDB object with model and chain inside
"""
self.struct = Structure(name)
my_model = Model(0)
my_chain = Chain(chain_id)
self.struct.add(my_model)
self.struct[0].add(my_chain)
def get_chainname(self):
"""
returns name of given structures chain
"""
self.chain = list(self.struct.get_chains())[0].id
def get_mol_sequence(self):
"""
retrieves struct sequence as one letter code
Parameters:
-----------
self.struct : structure object
Returns:
---------
self.sequence : sequence of given structure in one letter code
"""
##----must be included in tests!!!--------------------
for resi in self.struct.get_residues():
resi_name = resi.resname.strip().upper()
#add one letter nucleotide names
if len(resi_name) == 1 and resi_name in RESNAMES.values():
self.sequence += resi_name
#add hetatms with modifications
elif resi_name in to_one_letter_code:
self.sequence += to_one_letter_code[resi_name]
#do not add ions and ligands into sequence
elif resi_name in LIGANDS:
pass
#if antyhing else appeared include as X
else:
self.sequence += "X"
return self.sequence
def get_moltype(self):
"""
based on component's sequence determines if a certain
component is DNA, RNA or protein
Raises:
-------
PyRyStructureError if resnames are incorrect
"""
res = list(self.struct.get_residues())[0]
if len(res.resname.strip()) == 3:
if res.resname.strip() in AMINOACIDS.values():
self.moltype = 'protein'
else:
if res.resname.strip() in RESNAMES.keys(): pass
else:
raise PyRyStructureError("Wrong 3letter name",
res.resname.strip())
else:
for at in res:
if at.fullname.strip() == "CA":
self.moltype = 'protein'
break
elif at.fullname.strip() == "C4'" or at.fullname.strip(
) == "C4*":
for atom in res.child_list:
if atom.fullname.strip() == "O2'":
self.moltype = "RNA"
break
if self.moltype == "":
self.moltype = "DNA"
return self.moltype
def is_structure(self):
"""
checks if a given structure is Bio.PDB structure object
Raises:
------
PyRyStructureError : if self.struct is not Bio.PDB object
"""
if isinstance(self.struct,
Entity.Entity): # Structure, Model, Chain, Residue
return True
else:
raise PyRyStructureError('%s should be one of\n\
the following objects:Structure, Model, Chain, Residue, \n\
list of Atoms.' %
(self.struct))
def set_chain_name(self, chain):
self.chain = chain
def set_moltype(self, moltype):
"""
"""
self.moltype = moltype
def set_structure(self, struct):
self.struct = struct
def set_pyrystructure(self, structure=None):
"""
sets structure as PyRyStructure atrribute
Parameters:
-----------
structure : Bio.PDB structure object
"""
if self.struct == None: self.struct = structure
if self.sequence == '': self.get_mol_sequence()
self.get_chainname()
self.get_moltype()
def set_sequence(self, seq):
"""
"""
self.sequence = seq
def write_structure(self, filename):
"""
Writting structure to the pdb_file, saving changed coordinated
Parameters:
-----------
filename : final name of structure file
"""
out = PDBIO()
out.set_structure(self.struct)
out.save(filename)