aboutsummaryrefslogtreecommitdiff
path: root/lstm_chem
diff options
context:
space:
mode:
Diffstat (limited to 'lstm_chem')
-rw-r--r--[-rwxr-xr-x]lstm_chem/__init__.py0
-rw-r--r--[-rwxr-xr-x]lstm_chem/data_loader.py2
-rw-r--r--[-rwxr-xr-x]lstm_chem/finetuner.py5
-rw-r--r--[-rwxr-xr-x]lstm_chem/generator.py2
-rw-r--r--[-rwxr-xr-x]lstm_chem/model.py2
-rw-r--r--[-rwxr-xr-x]lstm_chem/trainer.py3
-rw-r--r--[-rwxr-xr-x]lstm_chem/utils/config.py0
-rw-r--r--[-rwxr-xr-x]lstm_chem/utils/dirs.py0
-rw-r--r--[-rwxr-xr-x]lstm_chem/utils/smiles_tokenizer.py9
-rw-r--r--[-rwxr-xr-x]lstm_chem/utils/smiles_tokenizer2.py (renamed from lstm_chem/utils/smiles_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py)64
10 files changed, 33 insertions, 54 deletions
diff --git a/lstm_chem/__init__.py b/lstm_chem/__init__.py
index 8b13789..8b13789 100755..100644
--- a/lstm_chem/__init__.py
+++ b/lstm_chem/__init__.py
diff --git a/lstm_chem/data_loader.py b/lstm_chem/data_loader.py
index 86ddbba..243f7e6 100755..100644
--- a/lstm_chem/data_loader.py
+++ b/lstm_chem/data_loader.py
@@ -3,7 +3,7 @@ import os
import numpy as np
from tqdm import tqdm
from tensorflow.keras.utils import Sequence
-from lstm_chem.utils.smiles_tokenizer import SmilesTokenizer
+from lstm_chem.utils.smiles_tokenizer2 import SmilesTokenizer
class DataLoader(Sequence):
diff --git a/lstm_chem/finetuner.py b/lstm_chem/finetuner.py
index 904958b..24f26ce 100755..100644
--- a/lstm_chem/finetuner.py
+++ b/lstm_chem/finetuner.py
@@ -1,4 +1,4 @@
-from lstm_chem.utils.smiles_tokenizer import SmilesTokenizer
+from lstm_chem.utils.smiles_tokenizer2 import SmilesTokenizer
from lstm_chem.generator import LSTMChemGenerator
@@ -14,7 +14,8 @@ class LSTMChemFinetuner(LSTMChemGenerator):
self.model.compile(optimizer=self.config.optimizer,
loss='categorical_crossentropy')
- history = self.model.fit_generator(
+# history = self.model.fit_generator(
+ history = self.model.fit(
self.finetune_data_loader,
steps_per_epoch=self.finetune_data_loader.__len__(),
epochs=self.config.finetune_epochs,
diff --git a/lstm_chem/generator.py b/lstm_chem/generator.py
index 498f864..4f80e9f 100755..100644
--- a/lstm_chem/generator.py
+++ b/lstm_chem/generator.py
@@ -1,6 +1,6 @@
from tqdm import tqdm
import numpy as np
-from lstm_chem.utils.smiles_tokenizer import SmilesTokenizer
+from lstm_chem.utils.smiles_tokenizer2 import SmilesTokenizer
class LSTMChemGenerator(object):
diff --git a/lstm_chem/model.py b/lstm_chem/model.py
index 079589a..368a834 100755..100644
--- a/lstm_chem/model.py
+++ b/lstm_chem/model.py
@@ -4,7 +4,7 @@ from tensorflow.keras import Sequential
from tensorflow.keras.models import model_from_json
from tensorflow.keras.layers import LSTM, Dense
from tensorflow.keras.initializers import RandomNormal
-from lstm_chem.utils.smiles_tokenizer import SmilesTokenizer
+from lstm_chem.utils.smiles_tokenizer2 import SmilesTokenizer
class LSTMChem(object):
diff --git a/lstm_chem/trainer.py b/lstm_chem/trainer.py
index 4e8057e..0ed608a 100755..100644
--- a/lstm_chem/trainer.py
+++ b/lstm_chem/trainer.py
@@ -32,7 +32,8 @@ class LSTMChemTrainer(object):
))
def train(self):
- history = self.model.fit_generator(
+# history = self.model.fit_generator(
+ history = self.model.fit(
self.train_data_loader,
steps_per_epoch=self.train_data_loader.__len__(),
epochs=self.config.num_epochs,
diff --git a/lstm_chem/utils/config.py b/lstm_chem/utils/config.py
index fff7359..fff7359 100755..100644
--- a/lstm_chem/utils/config.py
+++ b/lstm_chem/utils/config.py
diff --git a/lstm_chem/utils/dirs.py b/lstm_chem/utils/dirs.py
index bcd2a49..bcd2a49 100755..100644
--- a/lstm_chem/utils/dirs.py
+++ b/lstm_chem/utils/dirs.py
diff --git a/lstm_chem/utils/smiles_tokenizer.py b/lstm_chem/utils/smiles_tokenizer.py
index d15d625..f998c4a 100755..100644
--- a/lstm_chem/utils/smiles_tokenizer.py
+++ b/lstm_chem/utils/smiles_tokenizer.py
@@ -1,8 +1,5 @@
-import copy
import numpy as np
-import time
-
class SmilesTokenizer(object):
def __init__(self):
@@ -30,7 +27,7 @@ class SmilesTokenizer(object):
'S',
'K',
'V',
- 'I',
+ 'I'
]
special = [
'(', ')', '[', ']', '=', '#', '%', '0', '1', '2', '3', '4', '5',
@@ -51,8 +48,6 @@ class SmilesTokenizer(object):
N = len(smiles)
i = 0
token = []
-
- timeout = time.time() + 5 # 5 seconds from now
while (i < N):
for j in range(self.table_len):
symbol = self.table[j]
@@ -60,8 +55,6 @@ class SmilesTokenizer(object):
token.append(symbol)
i += len(symbol)
break
- if time.time() > timeout:
- break
return token
def one_hot_encode(self, tokenized_smiles):
diff --git a/lstm_chem/utils/smiles_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py b/lstm_chem/utils/smiles_tokenizer2.py
index d15d625..29575ba 100755..100644
--- a/lstm_chem/utils/smiles_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py
+++ b/lstm_chem/utils/smiles_tokenizer2.py
@@ -1,36 +1,11 @@
-import copy
import numpy as np
-import time
-
class SmilesTokenizer(object):
def __init__(self):
atoms = [
- 'Li',
- 'Na',
- 'Al',
- 'Si',
- 'Cl',
- 'Sc',
- 'Zn',
- 'As',
- 'Se',
- 'Br',
- 'Sn',
- 'Te',
- 'Cn',
- 'H',
- 'B',
- 'C',
- 'N',
- 'O',
- 'F',
- 'P',
- 'S',
- 'K',
- 'V',
- 'I',
+ 'Al', 'As', 'B', 'Br', 'C', 'Cl', 'F', 'H', 'I', 'K', 'Li', 'N',
+ 'Na', 'O', 'P', 'S', 'Se', 'Si', 'Te'
]
special = [
'(', ')', '[', ']', '=', '#', '%', '0', '1', '2', '3', '4', '5',
@@ -39,29 +14,38 @@ class SmilesTokenizer(object):
padding = ['G', 'A', 'E']
self.table = sorted(atoms, key=len, reverse=True) + special + padding
- self.table_len = len(self.table)
+ table_len = len(self.table)
+
+ self.table_2_chars = list(filter(lambda x: len(x) == 2, self.table))
+ self.table_1_chars = list(filter(lambda x: len(x) == 1, self.table))
self.one_hot_dict = {}
for i, symbol in enumerate(self.table):
- vec = np.zeros(self.table_len, dtype=np.float32)
+ vec = np.zeros(table_len, dtype=np.float32)
vec[i] = 1
self.one_hot_dict[symbol] = vec
def tokenize(self, smiles):
+ smiles = smiles + ' '
N = len(smiles)
- i = 0
token = []
-
- timeout = time.time() + 5 # 5 seconds from now
+ i = 0
while (i < N):
- for j in range(self.table_len):
- symbol = self.table[j]
- if symbol == smiles[i:i + len(symbol)]:
- token.append(symbol)
- i += len(symbol)
- break
- if time.time() > timeout:
- break
+ c1 = smiles[i]
+ c2 = smiles[i:i + 2]
+
+ if c2 in self.table_2_chars:
+ token.append(c2)
+ i += 2
+ continue
+
+ if c1 in self.table_1_chars:
+ token.append(c1)
+ i += 1
+ continue
+
+ i += 1
+
return token
def one_hot_encode(self, tokenized_smiles):
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-10 05:59:48 +0000