File size: 13,620 Bytes
55d9b0c |
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 |
# Requriments - transformers, tokenizers
# Right now, the Smiles Tokenizer uses an exiesting vocab file from rxnfp that is fairly comprehensive and from the USPTO dataset.
# The vocab may be expanded in the near future
# Code taken from here: https://github.com/deepchem/deepchem/blob/2.4.0/deepchem/feat/smiles_tokenizer.py#L39-L282
import collections
import os
import re
import pkg_resources
from typing import List
from transformers import BertTokenizer
from logging import getLogger
logger = getLogger(__name__)
"""
SMI_REGEX_PATTERN: str
SMILES regex pattern for tokenization. Designed by Schwaller et. al.
References
.. [1] Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A. Hunter, Costas Bekas, and Alpha A. Lee
ACS Central Science 2019 5 (9): Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
1572-1583 DOI: 10.1021/acscentsci.9b00576
"""
SMI_REGEX_PATTERN = r"""(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=|#|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])"""
# add vocab_file dict
VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
def get_default_tokenizer():
default_vocab_path = pkg_resources.resource_filename(
"deepchem", "feat/tests/vocab.txt"
)
return SmilesTokenizer(default_vocab_path)
class SmilesTokenizer(BertTokenizer):
"""
Creates the SmilesTokenizer class. The tokenizer heavily inherits from the BertTokenizer
implementation found in Huggingface's transformers library. It runs a WordPiece tokenization
algorithm over SMILES strings using the tokenisation SMILES regex developed by Schwaller et. al.
Please see https://github.com/huggingface/transformers
and https://github.com/rxn4chemistry/rxnfp for more details.
Examples
--------
>>> from deepchem.feat.smiles_tokenizer import SmilesTokenizer
>>> current_dir = os.path.dirname(os.path.realpath(__file__))
>>> vocab_path = os.path.join(current_dir, 'tests/data', 'vocab.txt')
>>> tokenizer = SmilesTokenizer(vocab_path)
>>> print(tokenizer.encode("CC(=O)OC1=CC=CC=C1C(=O)O"))
[12, 16, 16, 17, 22, 19, 18, 19, 16, 20, 22, 16, 16, 22, 16, 16, 22, 16, 20, 16, 17, 22, 19, 18, 19, 13]
References
----------
.. [1] Schwaller, Philippe; Probst, Daniel; Vaucher, Alain C.; Nair, Vishnu H; Kreutter, David;
Laino, Teodoro; et al. (2019): Mapping the Space of Chemical Reactions using Attention-Based Neural
Networks. ChemRxiv. Preprint. https://doi.org/10.26434/chemrxiv.9897365.v3
Notes
----
This class requires huggingface's transformers and tokenizers libraries to be installed.
"""
vocab_files_names = VOCAB_FILES_NAMES
def __init__(
self,
# unk_token="[UNK]",
# sep_token="[SEP]",
# pad_token="[PAD]",
# cls_token="[CLS]",
# mask_token="[MASK]",
**kwargs
):
"""Constructs a SmilesTokenizer.
Parameters
----------
vocab_file: str
Path to a SMILES character per line vocabulary file.
Default vocab file is found in deepchem/feat/tests/data/vocab.txt
"""
vocab_file = os.path.join(os.path.dirname(__file__), "data", "vocab.txt")
super().__init__(vocab_file, **kwargs)
self.sos = "[SOS]"
self.eos = "[EOS]"
if not os.path.isfile(vocab_file):
raise ValueError("Can't find a vocab file at path '{}'.".format(vocab_file))
self.vocab = load_vocab(vocab_file)
self.highest_unused_index = max(
[i for i, v in enumerate(self.vocab.keys()) if v.startswith("[unused")]
)
self.ids_to_tokens = collections.OrderedDict(
[(ids, tok) for tok, ids in self.vocab.items()]
)
self.basic_tokenizer = BasicSmilesTokenizer()
@property
def vocab_size(self):
return len(self.vocab)
@property
def vocab_list(self):
return list(self.vocab.keys())
def _tokenize(self, text: str):
"""
Tokenize a string into a list of tokens.
Parameters
----------
text: str
Input string sequence to be tokenized.
"""
split_tokens = [token for token in self.basic_tokenizer.tokenize(text)]
return split_tokens
def _convert_token_to_id(self, token):
"""
Converts a token (str/unicode) in an id using the vocab.
Parameters
----------
token: str
String token from a larger sequence to be converted to a numerical id.
"""
return self.vocab.get(token, self.vocab.get(self.unk_token))
def _convert_id_to_token(self, index):
"""
Converts an index (integer) in a token (string/unicode) using the vocab.
Parameters
----------
index: int
Integer index to be converted back to a string-based token as part of a larger sequence.
"""
return self.ids_to_tokens.get(index, self.unk_token)
def convert_tokens_to_string(self, tokens: List[str]):
"""Converts a sequence of tokens (string) in a single string.
Parameters
----------
tokens: List[str]
List of tokens for a given string sequence.
Returns
-------
out_string: str
Single string from combined tokens.
"""
out_string: str = " ".join(tokens).replace(" ##", "").strip()
return out_string
def add_special_tokens_ids_single_sequence(self, token_ids: List[int]):
"""
Adds special tokens to the a sequence for sequence classification tasks.
A BERT sequence has the following format: [CLS] X [SEP]
Parameters
----------
token_ids: list[int]
list of tokenized input ids. Can be obtained using the encode or encode_plus methods.
"""
return [self.cls_token_id] + token_ids + [self.sep_token_id]
def add_special_tokens_single_sequence(self, tokens: List[str]):
"""
Adds special tokens to the a sequence for sequence classification tasks.
A BERT sequence has the following format: [CLS] X [SEP]
Parameters
----------
tokens: List[str]
List of tokens for a given string sequence.
"""
return [self.cls_token] + tokens + [self.sep_token]
def add_special_tokens_ids_sequence_pair(
self, token_ids_0: List[int], token_ids_1: List[int]
) -> List[int]:
"""
Adds special tokens to a sequence pair for sequence classification tasks.
A BERT sequence pair has the following format: [CLS] A [SEP] B [SEP]
Parameters
----------
token_ids_0: List[int]
List of ids for the first string sequence in the sequence pair (A).
token_ids_1: List[int]
List of tokens for the second string sequence in the sequence pair (B).
"""
sep = [self.sep_token_id]
cls = [self.cls_token_id]
return cls + token_ids_0 + sep + token_ids_1 + sep
def add_padding_tokens(
self, token_ids: List[int], length: int, right: bool = True
) -> List[int]:
"""
Adds padding tokens to return a sequence of length max_length.
By default padding tokens are added to the right of the sequence.
Parameters
----------
token_ids: list[int]
list of tokenized input ids. Can be obtained using the encode or encode_plus methods.
length: int
right: bool (True by default)
Returns
----------
token_ids :
list of tokenized input ids. Can be obtained using the encode or encode_plus methods.
padding: int
Integer to be added as padding token
"""
padding = [self.pad_token_id] * (length - len(token_ids))
if right:
return token_ids + padding
else:
return padding + token_ids
def save_vocabulary(
self, vocab_path: str
): # -> tuple[str]: doctest issue raised with this return type annotation
"""
Save the tokenizer vocabulary to a file.
Parameters
----------
vocab_path: obj: str
The directory in which to save the SMILES character per line vocabulary file.
Default vocab file is found in deepchem/feat/tests/data/vocab.txt
Returns
----------
vocab_file: :obj:`Tuple(str)`:
Paths to the files saved.
typle with string to a SMILES character per line vocabulary file.
Default vocab file is found in deepchem/feat/tests/data/vocab.txt
"""
index = 0
if os.path.isdir(vocab_path):
vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES["vocab_file"])
else:
vocab_file = vocab_path
with open(vocab_file, "w", encoding="utf-8") as writer:
for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
if index != token_index:
logger.warning(
"Saving vocabulary to {}: vocabulary indices are not consecutive."
" Please check that the vocabulary is not corrupted!".format(
vocab_file
)
)
index = token_index
writer.write(token + "\n")
index += 1
return (vocab_file,)
class BasicSmilesTokenizer(object):
"""
Run basic SMILES tokenization using a regex pattern developed by Schwaller et. al. This tokenizer is to be used
when a tokenizer that does not require the transformers library by HuggingFace is required.
Examples
--------
>>> from deepchem.feat.smiles_tokenizer import BasicSmilesTokenizer
>>> tokenizer = BasicSmilesTokenizer()
>>> print(tokenizer.tokenize("CC(=O)OC1=CC=CC=C1C(=O)O"))
['C', 'C', '(', '=', 'O', ')', 'O', 'C', '1', '=', 'C', 'C', '=', 'C', 'C', '=', 'C', '1', 'C', '(', '=', 'O', ')', 'O']
References
----------
.. [1] Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A. Hunter, Costas Bekas, and Alpha A. Lee
ACS Central Science 2019 5 (9): Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
1572-1583 DOI: 10.1021/acscentsci.9b00576
"""
def __init__(self, regex_pattern: str = SMI_REGEX_PATTERN):
"""Constructs a BasicSMILESTokenizer.
Parameters
----------
regex: string
SMILES token regex
"""
self.regex_pattern = regex_pattern
self.regex = re.compile(self.regex_pattern)
def tokenize(self, text):
"""Basic Tokenization of a SMILES."""
tokens = [token for token in self.regex.findall(text)]
return tokens
def load_vocab(vocab_file):
"""Loads a vocabulary file into a dictionary."""
vocab = collections.OrderedDict()
with open(vocab_file, "r", encoding="utf-8") as reader:
tokens = reader.readlines()
for index, token in enumerate(tokens):
token = token.rstrip("\n")
vocab[token] = index
return vocab
class BasicSmilesTokenizer(object):
"""
Run basic SMILES tokenization using a regex pattern developed by Schwaller et. al. This tokenizer is to be used
when a tokenizer that does not require the transformers library by HuggingFace is required.
Examples
--------
>>> from deepchem.feat.smiles_tokenizer import BasicSmilesTokenizer
>>> tokenizer = BasicSmilesTokenizer()
>>> print(tokenizer.tokenize("CC(=O)OC1=CC=CC=C1C(=O)O"))
['C', 'C', '(', '=', 'O', ')', 'O', 'C', '1', '=', 'C', 'C', '=', 'C', 'C', '=', 'C', '1', 'C', '(', '=', 'O', ')', 'O']
References
----------
.. [1] Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A. Hunter, Costas Bekas, and Alpha A. Lee
ACS Central Science 2019 5 (9): Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
1572-1583 DOI: 10.1021/acscentsci.9b00576
"""
def __init__(self, regex_pattern: str = SMI_REGEX_PATTERN):
"""Constructs a BasicSMILESTokenizer.
Parameters
----------
regex: string
SMILES token regex
"""
self.regex_pattern = regex_pattern
self.regex = re.compile(self.regex_pattern)
def tokenize(self, text):
"""Basic Tokenization of a SMILES."""
tokens = [token for token in self.regex.findall(text)]
return tokens
def load_vocab(vocab_file):
"""Loads a vocabulary file into a dictionary."""
vocab = collections.OrderedDict()
with open(vocab_file, "r", encoding="utf-8") as reader:
tokens = reader.readlines()
for index, token in enumerate(tokens):
token = token.rstrip("\n")
vocab[token] = index
return vocab
if __name__ == "__main__":
current_dir = os.path.dirname(os.path.realpath(__file__))
vocab_path = os.path.join(current_dir, "tests/data", "vocab.txt")
tokenizer = SmilesTokenizer()
tokens = tokenizer.encode(
"CN1CC[C@]23[C@@H]4[C@H]1CC5=C2C(=C(C=C5)O)O[C@H]3[C@H](C=C4)O"
)
print([tokenizer._convert_id_to_token(t) for t in tokens])
enc = tokenizer.encode("CC=O")
print(enc)
print(tokenizer.decode(enc, skip_special_tokens=True).replace(" ", ""))
|