MCPcopy Create free account

hub / github.com/DeepGraphLearning/S3F / functions

Functions80 in github.com/DeepGraphLearning/S3F

↓ 5 callersMethod__init__
(self, in_dims, out_dims, h_dim=None, activations=(F.relu, torch.sigmoid), vector_gate=False)
s3f/gvp_layer.py:102
↓ 5 callersFunctionsoft_distances
Computes a soft distance function to the atom centers of a protein. Implements Eq. (1) of the paper in a fast and numerically stable way. Ar
s3f/surface.py:156
↓ 4 callersFunctiontuple_index
Indexes into a tuple (s, V) along the first dimension. :param idx: any object which can be used to index into a `torch.Tensor`
s3f/gvp_layer.py:32
↓ 3 callersFunction_norm_no_nan
L2 norm of tensor clamped above a minimum value `eps`. :param sqrt: if `False`, returns the square of the L2 norm
s3f/gvp_layer.py:55
↓ 3 callersFunctionrbf
(d, d_min=0.0, d_max=20.0, dim=16)
s3f/gvp.py:14
↓ 3 callersFunctiontuple_sum
Sums any number of tuples (s, V) elementwise.
s3f/gvp_layer.py:11
↓ 2 callersFunctiondiagonal_ranges
Encodes the block-diagonal structure associated to a batch vector.
s3f/surface.py:30
↓ 2 callersFunctiongraph_concat
(graphs)
script/evaluate.py:47
↓ 2 callersFunctionranges_slices
Helper function for the diagonal ranges function.
s3f/surface.py:13
↓ 1 callersMethod__init__
(self, node_in_dim, node_h_dim, edge_in_dim, edge_h_dim, readout="sum", num
s3f/gvp.py:185
↓ 1 callersFunction_make_standard_atom_mask
Returns [num_res_types, num_atom_types] mask array.
s3f/residue_constants.py:76
↓ 1 callersFunction_merge
Merges a tuple (s, V) into a single `torch.Tensor`, where the vector channels are flattened and appended to the scalar channels. Should b
s3f/gvp_layer.py:79
↓ 1 callersFunction_split
Splits a merged representation of (s, V) back into a tuple. Should be used only with `_merge(s, V)` and only if the tuple representatio
s3f/gvp_layer.py:65
↓ 1 callersMethodassign_structure
(self, sequence_graph, structure_graph)
s3f/dataset.py:102
↓ 1 callersFunctioncurvatures
( vertices, triangles=None, scales=[1.0], batch=None, normals=None, reg=1e-10 )
s3f/surface.py:415
↓ 1 callersFunctiondetect_variables
(cfg_file)
util.py:67
↓ 1 callersFunctionevaluate
(pred, target)
script/evaluate.py:28
↓ 1 callersFunctionget_optimal_window
(mutation_position_relative, seq_len_wo_special, model_window)
script/evaluate.py:68
↓ 1 callersFunctionget_prob
(seq_prob, mutations, offsets)
script/evaluate.py:96
↓ 1 callersMethodinference
(self, batch)
s3f/task.py:75
↓ 1 callersFunctionload_dataset
(csv_file, protein)
script/evaluate.py:126
↓ 1 callersFunctionload_protein
(file)
script/preload_dataset.py:12
↓ 1 callersFunctionload_protein
(data_dict)
s3f/dataset.py:140
↓ 1 callersFunctionload_surface
(surf_dict)
s3f/dataset.py:177
↓ 1 callersFunctionmesh_normals_areas
(vertices, triangles=None, scale=[1.0], batch=None, normals=None)
s3f/surface.py:347
↓ 1 callersFunctionmutation_site
(x)
script/evaluate.py:140
↓ 1 callersFunctionpredict
(cfg, task, dataset)
script/evaluate.py:80
↓ 1 callersMethodpreprocess
(self, train_set, valid_set, test_set)
s3f/task.py:24
↓ 1 callersFunctionprocess
(input_dir, output_dir, pkl_file)
script/process_surface.py:19
↓ 1 callersMethodresidue2surface
(self, graph, surf_graph)
s3f/gvp.py:97
↓ 1 callersFunctionsubsample
Subsamples the point cloud using a grid (cubic) clustering scheme. The function returns one average sample per cell, as described in Fig. 3.e)
s3f/surface.py:107
↓ 1 callersMethodsurface_feature_init
(self, graph, surf_graph, input)
s3f/gvp.py:102
↓ 1 callersFunctiontangent_vectors
(normals)
s3f/surface.py:404
↓ 1 callersMethodto_dict
(self)
s3f/protein.py:68
↓ 1 callersFunctiontrain_and_validate
(cfg, solver)
script/pretrain.py:18
↓ 1 callersMethodtruncate
(self, sequence_graph, structure_graph, surface_graph=None)
s3f/dataset.py:82
↓ 1 callersMethodtruncate
(self, data_dict, surf_dict=None)
s3f/dataset.py:211
↓ 1 callersFunctiontuple_cat
Concatenates any number of tuples (s, V) elementwise. :param dim: dimension along which to concatenate when viewed as th
s3f/gvp_layer.py:18
Method__getitem__
(self, index)
s3f/dataset.py:110
Method__init__
(self, model, mask_rate=0.15, dropout=0.5, graph_construction_model=None, plddt_threshold=None)
s3f/task.py:13
Method__init__
(self, node_in_dim, node_h_dim, edge_in_dim, edge_h_dim, surf_in_dim, surf_edge_in_dim,
s3f/gvp.py:27
Method__init__
(self, path, csv_file)
s3f/dataset.py:59
Method__init__
(self, mutated_sequences, wild_type, surf_graph=None, transform=None)
s3f/dataset.py:73
Method__init__
(self, path, max_length=None, surf_path=None, transform=None)
s3f/dataset.py:200
Method__init__
(self, drop_rate)
s3f/gvp_layer.py:161
Method__init__
(self, drop_rate)
s3f/gvp_layer.py:185
Method__init__
(self, dims)
s3f/gvp_layer.py:207
Method__init__
(self, in_dims, out_dims, edge_dims, n_layers=3, module_list=None, aggr="mean",
s3f/gvp_layer.py:246
Method__init__
(self, node_dims, edge_dims, n_message=3, n_feedforward=2, drop_rate=.1, aut
s3f/gvp_layer.py:314
Method__init__
(self, sequence_model, structure_model)
s3f/model.py:78
Method__len__
(self)
s3f/dataset.py:79
Method__len__
(self)
s3f/dataset.py:257
Method__post_init__
(self)
s3f/protein.py:62
Method__repr__
(self)
s3f/dataset.py:260
Functionatoms_to_points_normals
Turns a collection of atoms into an oriented point cloud. Sampling algorithm for protein surfaces, described in Fig. 3 of the paper. Args:
s3f/surface.py:223
Functionbio_load_pdb
(pdb)
s3f/dataset.py:26
Functionbuild_solver
(cfg, dataset)
util.py:86
Functioncompute_HKS
(eigen_vecs, eigen_vals, num_t, t_min=0.1, t_max=1000, scale=1000)
s3f/surface.py:76
Functioncompute_curvatures
(xyz, normals, batch, curvature_scales)
s3f/surface.py:92
Functioncompute_eigens
(n_verts, xyz, min_n_eigs, eigs_ratio)
s3f/surface.py:63
Functioncreate_working_directory
(cfg)
util.py:35
Methodforward
(self, graph, input, surf_graph, all_loss=None, metric=None)
s3f/gvp.py:124
Methodforward
(self, graph, input, all_loss=None, metric=None)
s3f/gvp.py:222
Methodforward
:param x: tuple (s, V) of `torch.Tensor`, or (if vectors_in is 0), a single `torch.Tensor` :return: tuple (s, V) o
s3f/gvp_layer.py:120
Methodforward
:param x: `torch.Tensor` corresponding to vector channels
s3f/gvp_layer.py:166
Methodforward
:param x: tuple (s, V) of `torch.Tensor`, or single `torch.Tensor` (will be assumed to be scalar channel
s3f/gvp_layer.py:190
Methodforward
:param x: tuple (s, V) of `torch.Tensor`, or single `torch.Tensor` (will be assumed to be scalar channel
s3f/gvp_layer.py:212
Methodforward
:param x: tuple (s, V) of `torch.Tensor` :param edge_index: array of shape [2, n_edges] :param edge_attr: tuple (s, V) of `to
s3f/gvp_layer.py:273
Methodforward
:param x: tuple (s, V) of `torch.Tensor` :param edge_index: array of shape [2, n_edges] :param edge_attr: tuple (s, V) of `to
s3f/gvp_layer.py:339
Methodforward
Compute the residue representations and the graph representation(s). Parameters: graph (Protein): :math:`n` protein(s)
s3f/model.py:15
Methodforward
(self, graph, input, all_loss=None, metric=None, batch=None)
s3f/model.py:84
Functionfrom_pdb_string
Takes a PDB string and constructs a Protein object. WARNING: All non-standard residue types will be converted into UNK. All non-standard atoms
s3f/protein.py:72
Methodget_item
(self, idx)
s3f/dataset.py:234
Functionget_root_logger
(file=True)
util.py:22
Functionknn_atoms
(x, y, k, batch_x=None, batch_y=None)
s3f/surface.py:43
Functionload_config
(cfg_file, context=None)
util.py:76
Methodmessage
(self, s_i, v_i, s_j, v_j, edge_attr)
s3f/gvp_layer.py:285
Functionparse_args
()
util.py:116
Methodpredict_and_target
(self, batch, all_loss=None, metric=None)
s3f/task.py:27
Functionrandn
Returns random tuples (s, V) drawn elementwise from a normal distribution. :param n: number of data points :param dims: tuple of dim
s3f/gvp_layer.py:41