deepfold.eval package

Submodules

deepfold.eval.cell_lists module

class deepfold.eval.cell_lists.CellLists(box_size: ndarray, num_particles: int, cutoff_distance: float)

Bases: object

add_particle(particle: Particle) → None

calculate_neighbor_offsets()

clear()

get_index(pos: ndarray)

get_neighbors(pos: ndarray) → List[Particle]

static optimal_cell_size(box_size, num_particles, cutoff_distance)

class deepfold.eval.cell_lists.Particle(pos: numpy.ndarray = array([0., 0., 0.]), sig: Any | None = None)

Bases: object

pos: ndarray = array([0., 0., 0.])

sig: Any | None = None

deepfold.eval.contact module

class deepfold.eval.contact.Atom(atom_type: int, rid: int, residue_index: int, chain_index: int)

Bases: object

atom_type: int

chain_index: int

residue_index: int

rid: int

deepfold.eval.contact.contact_map(prot: Protein, cutoff: float) → ndarray

deepfold.eval.distogram module

deepfold.eval.distogram.bin_edges_np(min_bin: float, max_bin: float, num_bins: int) → ndarray

deepfold.eval.distogram.calculate_bin_centers_np(boundaries: ndarray) → ndarray

deepfold.eval.distogram.compute_distogram(pts: ndarray, min_bin: float = 2.2325, max_bin: float = 21.6875, num_bins: int = 64) → ndarray

deepfold.eval.distogram.compute_predicted_distogram(logits: ndarray, min_bin: float = 2.2325, max_bin: float = 21.6875, num_bins: int = 64) → ndarray

deepfold.eval.distogram.undigitize(indices: ndarray, bins: ndarray, right: bool = False) → ndarray

deepfold.eval.msa module

deepfold.eval.msa.compute_neff_v1(msa: ndarray, cutoff: float = 0.62, eps: float = 1e-06) → float

deepfold.eval.msa.compute_neff_v2(msa: ndarray, cutoff: float = 0.62, eps: float = 1e-10) → float

deepfold.eval.plot module

deepfold.eval.plot.find_cluster_boundaries(a: ndarray) → List[Tuple[int, int, int]]

deepfold.eval.plot.plot_distogram(outputs: dict, asym_id: ndarray | None = None, ncols: int = 5, sort: bool = False, fig_kwargs: dict = {}) → Figure

deepfold.eval.plot.plot_msa(feature_dict: Dict[str, ndarray], sort_lines: bool = True, dpi: float = 150.0, scale_with_len: bool = False) → Figure

deepfold.eval.plot.plot_plddt(outputs: dict, asym_id: ndarray | None = None, scale_with_len: bool = False, fig_kwargs: dict = {}) → Figure

deepfold.eval.plot.plot_predicted_alignment_error(outputs: dict, asym_id: ndarray | None = None, fig_kwargs: dict = {}) → Figure

deepfold.eval.pseudo_3d module

deepfold.eval.pseudo_3d.kabsch(a: ndarray, b: ndarray, weights: ndarray | None = None) → Tuple[ndarray, ndarray]

deepfold.eval.pseudo_3d.plot_protein(protein: Protein | None = None, pos: ndarray | None = None, plddt: ndarray | None = None, ls: ndarray | None = None, dpi: float = 150.0, best_view: bool = True, linewidth: float = 2.0) → Figure

deepfold.eval.pseudo_3d.plot_protein_bb(pos: ndarray, plddt: ndarray | None = None, axes: Axes | None = None, coloring: str = 'plddt', ls: ndarray | None = None, best_view: bool = True, linewidth: float = 2.0)

Module contents