def featurize_contacts_ecfp(
frag1: Tuple,
frag2: Tuple,
pairwise_distances: np.ndarray = None,
cutoff: float = 4.5,
ecfp_degree: int = 2) -> Tuple[Dict[int, str], Dict[int, str]]:
"""Computes ECFP dicts for pairwise interaction between two molecular fragments.
Parameters
----------
frag1: Tuple
A tuple of (coords, mol) returned by `load_molecule`.
frag2: Tuple
A tuple of (coords, mol) returned by `load_molecule`.
pairwise_distances: np.ndarray
Array of pairwise fragment-fragment distances (Angstroms)
cutoff: float
Cutoff distance for contact consideration
ecfp_degree: int
ECFP radius
Returns
-------
Tuple of dictionaries of ECFP contact fragments
"""
if pairwise_distances is None:
pairwise_distances = compute_pairwise_distances(frag1[0], frag2[0])
# contacts is of form (x_coords, y_coords), a tuple of 2 lists
contacts = np.nonzero((pairwise_distances < cutoff))
# contacts[0] is the x_coords, that is the frag1 atoms that have
# nonzero contact.
frag1_atoms = set([int(c) for c in contacts[0].tolist()])
# contacts[1] is the y_coords, the frag2 atoms with nonzero contacts
frag2_atoms = set([int(c) for c in contacts[1].tolist()])
frag1_ecfp_dict = compute_all_ecfp(frag1[1],
indices=frag1_atoms,
degree=ecfp_degree)
frag2_ecfp_dict = compute_all_ecfp(frag2[1],
indices=frag2_atoms,
degree=ecfp_degree)
return (frag1_ecfp_dict, frag2_ecfp_dict)
def compute_splif_features_in_range(frag1: Tuple,
frag2: Tuple,
pairwise_distances: np.ndarray,
contact_bin: List,
ecfp_degree: int = 2) -> Dict:
"""Computes SPLIF features for close atoms in molecular complexes.
Finds all frag1 atoms that are > contact_bin[0] and <
contact_bin[1] away from frag2 atoms. Then, finds the ECFP
fingerprints for the contacting atoms. Returns a dictionary
mapping (frag1_index_i, frag2_index_j) --> (frag1_ecfp_i,
frag2_ecfp_j)
Parameters
----------
frag1: Tuple
A tuple of (coords, mol) returned by `load_molecule`.
frag2: Tuple
A tuple of (coords, mol) returned by `load_molecule`.
contact_bins: np.ndarray
Ranges of pair distances which are placed in separate bins.
pairwise_distances: np.ndarray
Array of pairwise fragment-fragment distances (Angstroms)
ecfp_degree: int
ECFP radius
"""
contacts = np.nonzero((pairwise_distances > contact_bin[0])
& (pairwise_distances < contact_bin[1]))
frag1_atoms = set([int(c) for c in contacts[0].tolist()])
contacts = zip(contacts[0], contacts[1])
frag1_ecfp_dict = compute_all_ecfp(frag1[1],
indices=frag1_atoms,
degree=ecfp_degree)
frag2_ecfp_dict = compute_all_ecfp(frag2[1], degree=ecfp_degree)
splif_dict = {
contact: (frag1_ecfp_dict[contact[0]], frag2_ecfp_dict[contact[1]])
for contact in contacts
}
return splif_dict