File size: 16,124 Bytes
1fcde9f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
"""Utilities for converting Graphein Networks to Geometric Deep Learning formats.
"""
# %%
# Graphein
# Author: Kexin Huang, Arian Jamasb <[email protected]>
# License: MIT
# Project Website: https://github.com/a-r-j/graphein
# Code Repository: https://github.com/a-r-j/graphein
from __future__ import annotations

from typing import List, Optional

import networkx as nx
import numpy as np
import torch

try:
    from graphein.utils.dependencies import import_message
except ImportError:
    raise Exception('You need to install graphein from source in addition to DSSP to use this model please refer to https://github.com/a-r-j/graphein and https://ssbio.readthedocs.io/en/latest/instructions/dssp.html')

try:
    import torch_geometric
    from torch_geometric.data import Data
except ImportError:
    import_message(
        submodule="graphein.ml.conversion",
        package="torch_geometric",
        pip_install=True,
        conda_channel="rusty1s",
    )

try:
    import dgl
except ImportError:
    import_message(
        submodule="graphein.ml.conversion",
        package="dgl",
        pip_install=True,
        conda_channel="dglteam",
    )

try:
    import jax.numpy as jnp
except ImportError:
    import_message(
        submodule="graphein.ml.conversion",
        package="jax",
        pip_install=True,
        conda_channel="conda-forge",
    )
try:
    import jraph
except ImportError:
    import_message(
        submodule="graphein.ml.conversion",
        package="jraph",
        pip_install=True,
        conda_channel="conda-forge",
    )


SUPPORTED_FORMATS = ["nx", "pyg", "dgl", "jraph"]
"""Supported conversion formats.

``"nx"``: NetworkX graph

``"pyg"``: PyTorch Geometric Data object

``"dgl"``: DGL graph

``"Jraph"``: Jraph GraphsTuple
"""

SUPPORTED_VERBOSITY = ["gnn", "default", "all_info"]
"""Supported verbosity levels for preserving graph features in conversion."""


class GraphFormatConvertor:
    """
    Provides conversion utilities between NetworkX Graphs and geometric deep learning library destination formats.
    Currently, we provide support for converstion from ``nx.Graph`` to ``dgl.DGLGraph`` and ``pytorch_geometric.Data``. Supported conversion
    formats can be retrieved from :const:`~graphein.ml.conversion.SUPPORTED_FORMATS`.

    :param src_format: The type of graph you'd like to convert from. Supported formats are available in :const:`~graphein.ml.conversion.SUPPORTED_FORMATS`
    :type src_format: Literal["nx", "pyg", "dgl", "jraph"]
    :param dst_format: The type of graph format you'd like to convert to. Supported formats are available in:
        ``graphein.ml.conversion.SUPPORTED_FORMATS``
    :type dst_format:  Literal["nx", "pyg", "dgl", "jraph"]
    :param verbose: Select from ``"gnn"``, ``"default"``, ``"all_info"`` to determine how much information is preserved (features)
        as some are unsupported by various downstream frameworks
    :type verbose: graphein.ml.conversion.SUPPORTED_VERBOSITY
    :param columns: List of columns in the node features to retain
    :type columns: List[str], optional
    """

    def __init__(
        self,
        src_format: str,
        dst_format: str,
        verbose: SUPPORTED_VERBOSITY = "gnn",
        columns: Optional[List[str]] = None,
    ):
        if (src_format not in SUPPORTED_FORMATS) or (
            dst_format not in SUPPORTED_FORMATS
        ):
            raise ValueError(
                "Please specify from supported format, "
                + "/".join(SUPPORTED_FORMATS)
            )
        self.src_format = src_format
        self.dst_format = dst_format

        # supported_verbose_format = ["gnn", "default", "all_info"]
        if (columns is None) and (verbose not in SUPPORTED_VERBOSITY):
            raise ValueError(
                "Please specify the supported verbose mode ("
                + "/".join(SUPPORTED_VERBOSITY)
                + ") or specify column names!"
            )

        if columns is None:
            if verbose == "gnn":
                columns = [
                    "edge_index",
                    "coords",
                    "dist_mat",
                    "name",
                    "node_id",
                ]
            elif verbose == "default":
                columns = [
                    "b_factor",
                    "chain_id",
                    "coords",
                    "dist_mat",
                    "edge_index",
                    "kind",
                    "name",
                    "node_id",
                    "residue_name",
                ]
            elif verbose == "all_info":
                columns = [
                    "atom_type",
                    "b_factor",
                    "chain_id",
                    "chain_ids",
                    "config",
                    "coords",
                    "dist_mat",
                    "edge_index",
                    "element_symbol",
                    "kind",
                    "name",
                    "node_id",
                    "node_type",
                    "pdb_df",
                    "raw_pdb_df",
                    "residue_name",
                    "residue_number",
                    "rgroup_df",
                    "sequence_A",
                    "sequence_B",
                ]
        self.columns = columns

        self.type2form = {
            "atom_type": "str",
            "b_factor": "float",
            "chain_id": "str",
            "coords": "np.array",
            "dist_mat": "np.array",
            "element_symbol": "str",
            "node_id": "str",
            "residue_name": "str",
            "residue_number": "int",
            "edge_index": "torch.tensor",
            "kind": "str",
        }

    def convert_nx_to_dgl(self, G: nx.Graph) -> dgl.DGLGraph:
        """
        Converts ``NetworkX`` graph to ``DGL``

        :param G: ``nx.Graph`` to convert to ``DGLGraph``
        :type G: nx.Graph
        :return: ``DGLGraph`` object version of input ``NetworkX`` graph
        :rtype: dgl.DGLGraph
        """
        g = dgl.DGLGraph()
        node_id = list(G.nodes())
        G = nx.convert_node_labels_to_integers(G)

        ## add node level feat

        node_dict = {}
        for i, (_, feat_dict) in enumerate(G.nodes(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    node_dict[str(key)] = (
                        [value] if i == 0 else node_dict[str(key)] + [value]
                    )

        string_dict = {}
        node_dict_transformed = {}
        for i, j in node_dict.items():
            if i == "coords":
                node_dict_transformed[i] = torch.Tensor(np.asarray(j)).type(
                    "torch.FloatTensor"
                )
            elif i == "dist_mat":
                node_dict_transformed[i] = torch.Tensor(
                    np.asarray(j[0].values)
                ).type("torch.FloatTensor")
            elif self.type2form[i] == "str":
                string_dict[i] = j
            elif self.type2form[i] in ["float", "int"]:
                node_dict_transformed[i] = torch.Tensor(np.array(j))
        g.add_nodes(
            len(node_id),
            node_dict_transformed,
        )

        edge_dict = {}
        edge_index = torch.LongTensor(list(G.edges)).t().contiguous()

        # add edge level features
        for i, (_, _, feat_dict) in enumerate(G.edges(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    edge_dict[str(key)] = (
                        list(value)
                        if i == 0
                        else edge_dict[str(key)] + list(value)
                    )

        edge_transform_dict = {}
        for i, j in node_dict.items():
            if self.type2form[i] == "str":
                string_dict[i] = j
            elif self.type2form[i] in ["float", "int"]:
                edge_transform_dict[i] = torch.Tensor(np.array(j))
        g.add_edges(edge_index[0], edge_index[1], edge_transform_dict)

        # add graph level features
        graph_dict = {
            str(feat_name): [G.graph[feat_name]]
            for feat_name in G.graph
            if str(feat_name) in self.columns
        }

        return g

    def convert_nx_to_pyg(self, G: nx.Graph) -> Data:
        """
        Converts ``NetworkX`` graph to ``pytorch_geometric.data.Data`` object. Requires ``PyTorch Geometric`` (https://pytorch-geometric.readthedocs.io/en/latest/) to be installed.

        :param G: ``nx.Graph`` to convert to PyTorch Geometric ``Data`` object
        :type G: nx.Graph
        :return: ``Data`` object containing networkx graph data
        :rtype: pytorch_geometric.data.Data
        """

        # Initialise dict used to construct Data object & Assign node ids as a feature
        data = {"node_id": list(G.nodes())}
        G = nx.convert_node_labels_to_integers(G)

        # Construct Edge Index
        edge_index = torch.LongTensor(list(G.edges)).t().contiguous()

        # Add node features
        for i, (_, feat_dict) in enumerate(G.nodes(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    data[str(key)] = (
                        [value] if i == 0 else data[str(key)] + [value]
                    )

        # Add edge features
        for i, (_, _, feat_dict) in enumerate(G.edges(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    data[str(key)] = (
                        list(value) if i == 0 else data[str(key)] + list(value)
                    )

        # Add graph-level features
        for feat_name in G.graph:
            if str(feat_name) in self.columns:
                data[str(feat_name)] = [G.graph[feat_name]]

        if "edge_index" in self.columns:
            data["edge_index"] = edge_index.view(2, -1)

        data = Data.from_dict(data)
        data.num_nodes = G.number_of_nodes()
        return data

    @staticmethod
    def convert_nx_to_nx(G: nx.Graph) -> nx.Graph:
        """
        Converts NetworkX graph (``nx.Graph``) to NetworkX graph (``nx.Graph``) object. Redundant - returns itself.

        :param G: NetworkX Graph
        :type G: nx.Graph
        :return: NetworkX Graph
        :rtype: nx.Graph
        """
        return G

    @staticmethod
    def convert_dgl_to_nx(G: dgl.DGLGraph) -> nx.Graph:
        """
        Converts a DGL Graph (``dgl.DGLGraph``) to a NetworkX (``nx.Graph``) object. Preserves node and edge attributes.

        :param G: ``dgl.DGLGraph`` to convert to ``NetworkX`` graph.
        :type G: dgl.DGLGraph
        :return: NetworkX graph object.
        :rtype: nx.Graph
        """
        node_attrs = G.node_attr_schemes().keys()
        edge_attrs = G.edge_attr_schemes().keys()
        return dgl.to_networkx(G, node_attrs, edge_attrs)

    @staticmethod
    def convert_pyg_to_nx(G: Data) -> nx.Graph:
        """Converts PyTorch Geometric ``Data`` object to NetworkX graph (``nx.Graph``).

        :param G: Pytorch Geometric Data.
        :type G: torch_geometric.data.Data
        :returns: NetworkX graph.
        :rtype: nx.Graph
        """
        return torch_geometric.utils.to_networkx(G)

    def convert_nx_to_jraph(self, G: nx.Graph) -> jraph.GraphsTuple:
        """Converts NetworkX graph (``nx.Graph``) to Jraph GraphsTuple graph. Requires ``jax`` and ``Jraph``.

        :param G: Networkx graph to convert.
        :type G: nx.Graph
        :return: Jraph GraphsTuple graph.
        :rtype: jraph.GraphsTuple
        """
        G = nx.convert_node_labels_to_integers(G)

        n_node = len(G)
        n_edge = G.number_of_edges()
        edge_list = list(G.edges())
        senders, receivers = zip(*edge_list)
        senders, receivers = jnp.array(senders), jnp.array(receivers)

        # Add node features
        node_features = {}
        for i, (_, feat_dict) in enumerate(G.nodes(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    # node_features[str(key)] = (
                    #    [value]
                    #    if i == 0
                    #    else node_features[str(key)] + [value]
                    # )
                    feat = (
                        [value]
                        if i == 0
                        else node_features[str(key)] + [value]
                    )
                    try:
                        feat = torch.tensor(feat)
                        node_features[str(key)] = feat
                    except TypeError:
                        node_features[str(key)] = feat

        # Add edge features
        edge_features = {}
        for i, (_, _, feat_dict) in enumerate(G.edges(data=True)):
            for key, value in feat_dict.items():
                if str(key) in self.columns:
                    edge_features[str(key)] = (
                        list(value)
                        if i == 0
                        else edge_features[str(key)] + list(value)
                    )

        # Add graph features
        global_context = {
            str(feat_name): [G.graph[feat_name]]
            for feat_name in G.graph
            if str(feat_name) in self.columns
        }

        return jraph.GraphsTuple(
            nodes=node_features,
            senders=senders,
            receivers=receivers,
            edges=edge_features,
            n_node=n_node,
            n_edge=n_edge,
            globals=global_context,
        )

    def __call__(self, G: nx.Graph):
        nx_g = eval("self.convert_" + self.src_format + "_to_nx(G)")
        dst_g = eval("self.convert_nx_to_" + self.dst_format + "(nx_g)")
        return dst_g


# def convert_nx_to_pyg_data(G: nx.Graph) -> Data:
#     # Initialise dict used to construct Data object
#     data = {"node_id": list(G.nodes())}

#     G = nx.convert_node_labels_to_integers(G)

#     # Construct Edge Index
#     edge_index = torch.LongTensor(list(G.edges)).t().contiguous()

#     # Add node features
#     for i, (_, feat_dict) in enumerate(G.nodes(data=True)):
#         for key, value in feat_dict.items():
#             data[str(key)] = [value] if i == 0 else data[str(key)] + [value]

#     # Add edge features
#     for i, (_, _, feat_dict) in enumerate(G.edges(data=True)):
#         for key, value in feat_dict.items():
#             data[str(key)] = (
#                 list(value) if i == 0 else data[str(key)] + list(value)
#             )

#     # Add graph-level features
#     for feat_name in G.graph:
#         data[str(feat_name)] = [G.graph[feat_name]]

#     data["edge_index"] = edge_index.view(2, -1)
#     data = Data.from_dict(data)
#     data.num_nodes = G.number_of_nodes()

#     return data
def convert_nx_to_pyg_data(G: nx.Graph) -> Data:
    # Initialise dict used to construct Data object
    data = {"node_id": list(G.nodes())}

    G = nx.convert_node_labels_to_integers(G)

    # Construct Edge Index
    edge_index = torch.LongTensor(list(G.edges)).t().contiguous()

    # Add node features
    for i, (_, feat_dict) in enumerate(G.nodes(data=True)):
        for key, value in feat_dict.items():
            data[str(key)] = [value] if i == 0 else data[str(key)] + [value]


    # Add edge features
    for i, (_, _, feat_dict) in enumerate(G.edges(data=True)):
        for key, value in feat_dict.items():
            if key == 'distance':
                data[str(key)] = (
                    [value] if i == 0 else data[str(key)] + [value]
                )
            else:
                data[str(key)] = (
                    [list(value)] if i == 0 else data[str(key)] + [list(value)]
                )

    # Add graph-level features
    for feat_name in G.graph:
        data[str(feat_name)] = [G.graph[feat_name]]

    data["edge_index"] = edge_index.view(2, -1)
    data = Data.from_dict(data)
    data.num_nodes = G.number_of_nodes()

    return data