4 files changed, 159 insertions, 0 deletions
diff --git a/lstm_chem/utils/config.py b/lstm_chem/utils/config.py
new file mode 100644
index 0000000..fff7359
--- /dev/null
+++ b/lstm_chem/utils/config.py
@@ -0,0 +1,26 @@
+import os
+import time
+import json
+from bunch import Bunch
+
+
+def get_config_from_json(json_file):
+    with open(json_file, 'r') as config_file:
+        config_dict = json.load(config_file)
+    config = Bunch(config_dict)
+    return config
+
+
+def process_config(json_file):
+    config = get_config_from_json(json_file)
+    config.config_file = json_file
+    config.exp_dir = os.path.join(
+        'experiments', time.strftime('%Y-%m-%d/', time.localtime()),
+        config.exp_name)
+    config.tensorboard_log_dir = os.path.join(
+        'experiments', time.strftime('%Y-%m-%d/', time.localtime()),
+        config.exp_name, 'logs/')
+    config.checkpoint_dir = os.path.join(
+        'experiments', time.strftime('%Y-%m-%d/', time.localtime()),
+        config.exp_name, 'checkpoints/')
+    return config
diff --git a/lstm_chem/utils/dirs.py b/lstm_chem/utils/dirs.py
new file mode 100644
index 0000000..bcd2a49
--- /dev/null
+++ b/lstm_chem/utils/dirs.py
@@ -0,0 +1,12 @@
+import os
+import sys
+
+
+def create_dirs(dirs):
+    try:
+        for dir_ in dirs:
+            if not os.path.exists(dir_):
+                os.makedirs(dir_)
+    except Exception as err:
+        print(f'Creating directories error: {err}')
+        sys.exit()
diff --git a/lstm_chem/utils/smiles_tokenizer.py b/lstm_chem/utils/smiles_tokenizer.py
new file mode 100644
index 0000000..f998c4a
--- /dev/null
+++ b/lstm_chem/utils/smiles_tokenizer.py
@@ -0,0 +1,65 @@
+import numpy as np
+
+
+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 = []
+        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
+        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