From e80badd278f54e8cde64243aa56687f8e6e32cc2 Mon Sep 17 00:00:00 2001
From: Navan Chauhan <navanchauhan@gmail.com>
Date: Sat, 1 Aug 2020 15:34:22 +0530
Subject: added alpha model
---
lstm_chem/utils/config.py | 0
lstm_chem/utils/dirs.py | 0
lstm_chem/utils/smiles_tokenizer.py | 9 +--
...okenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py | 72 ----------------------
lstm_chem/utils/smiles_tokenizer2.py | 56 +++++++++++++++++
5 files changed, 57 insertions(+), 80 deletions(-)
mode change 100755 => 100644 lstm_chem/utils/config.py
mode change 100755 => 100644 lstm_chem/utils/dirs.py
mode change 100755 => 100644 lstm_chem/utils/smiles_tokenizer.py
delete mode 100755 lstm_chem/utils/smiles_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py
create mode 100644 lstm_chem/utils/smiles_tokenizer2.py
(limited to 'lstm_chem/utils')
diff --git a/lstm_chem/utils/config.py b/lstm_chem/utils/config.py
old mode 100755
new mode 100644
diff --git a/lstm_chem/utils/dirs.py b/lstm_chem/utils/dirs.py
old mode 100755
new mode 100644
diff --git a/lstm_chem/utils/smiles_tokenizer.py b/lstm_chem/utils/smiles_tokenizer.py
old mode 100755
new mode 100644
index d15d625..f998c4a
--- 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_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py
deleted file mode 100755
index d15d625..0000000
--- a/lstm_chem/utils/smiles_tokenizer.py.4faeffb638548d04ca4415dfe32cf8c7.py
+++ /dev/null
@@ -1,72 +0,0 @@
-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',
- ]
- special = [
- '(', ')', '[', ']', '=', '#', '%', '0', '1', '2', '3', '4', '5',
- '6', '7', '8', '9', '+', '-', 'se', 'te', 'c', 'n', 'o', 's'
- ]
- padding = ['G', 'A', 'E']
-
- self.table = sorted(atoms, key=len, reverse=True) + special + padding
- self.table_len = len(self.table)
-
- self.one_hot_dict = {}
- for i, symbol in enumerate(self.table):
- vec = np.zeros(self.table_len, dtype=np.float32)
- vec[i] = 1
- self.one_hot_dict[symbol] = vec
-
- def tokenize(self, smiles):
- 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]
- if symbol == smiles[i:i + len(symbol)]:
- token.append(symbol)
- i += len(symbol)
- break
- if time.time() > timeout:
- break
- return token
-
- def one_hot_encode(self, tokenized_smiles):
- result = np.array(
- [self.one_hot_dict[symbol] for symbol in tokenized_smiles],
- dtype=np.float32)
- result = result.reshape(1, result.shape[0], result.shape[1])
- return result
diff --git a/lstm_chem/utils/smiles_tokenizer2.py b/lstm_chem/utils/smiles_tokenizer2.py
new file mode 100644
index 0000000..29575ba
--- /dev/null
+++ b/lstm_chem/utils/smiles_tokenizer2.py
@@ -0,0 +1,56 @@
+import numpy as np
+
+
+class SmilesTokenizer(object):
+ def __init__(self):
+ atoms = [
+ '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',
+ '6', '7', '8', '9', '+', '-', 'se', 'te', 'c', 'n', 'o', 's'
+ ]
+ padding = ['G', 'A', 'E']
+
+ self.table = sorted(atoms, key=len, reverse=True) + special + padding
+ 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(table_len, dtype=np.float32)
+ vec[i] = 1
+ self.one_hot_dict[symbol] = vec
+
+ def tokenize(self, smiles):
+ smiles = smiles + ' '
+ N = len(smiles)
+ token = []
+ i = 0
+ while (i < N):
+ 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):
+ result = np.array(
+ [self.one_hot_dict[symbol] for symbol in tokenized_smiles],
+ dtype=np.float32)
+ result = result.reshape(1, result.shape[0], result.shape[1])
+ return result
--
cgit v1.2.3