Delete utils

utils/__init__.py

@@ -1,3 +0,0 @@
-from .main_model import ChemicalConverter
-from .rdkit_utils import validate_smiles2iupac, plot_mol
-from .login import login

utils/login.py

@@ -1,18 +0,0 @@
-import hashlib
-
-def hash_password(access_code):
-    """Hash a password for storing."""
-    sha256 = hashlib.sha256()
-    sha256.update(access_code.encode('utf-8'))
-    return sha256.hexdigest()
-
-
-def login(access_code):
-    if access_code is None:
-        return False
-    hashed_code = hash_password(access_code.replace(" ", ""))
-    with open("hashed_codes.txt") as file:
-        for line in file:
-            if hashed_code in line:
-                return True
-    return False

utils/main_model.py

@@ -1,52 +0,0 @@
-from modeling import MT5ForConditionalGeneration
-from transformers import AutoTokenizer
-import os
-
-
-class ChemicalConverter:
-    def __init__(self, mode: str):
-        self.mode = mode
-        model_directory = os.path.abspath("models")
-        model_path = os.path.join(model_directory, mode)
-        
-        if mode == "SMILES2IUPAC":
-            model_path = "knowledgator/SMILES2IUPAC-canonical-base"
-        else:
-            model_path = "knowledgator/IUPAC2SMILES-canonical-small"
-            
-        self.model = MT5ForConditionalGeneration.from_pretrained(model_path)
-        self.smiles_tokenizer = AutoTokenizer.from_pretrained("knowledgator/SMILES-FAST-TOKENIZER")
-        self.iupac_tokenizer = AutoTokenizer.from_pretrained("knowledgator/IUPAC-FAST-TOKENIZER")
-        self.smiles_max_len = 128
-        self.iupac_max_len = 156
-
-    def convert(self, input):
-        input = input.replace(" ", "")
-        if self.mode == "SMILES2IUPAC":
-            tokenizer = self.smiles_tokenizer
-            reverse_tokenizer = self.iupac_tokenizer
-            max_length = self.smiles_max_len
-        else:
-            tokenizer = self.iupac_tokenizer
-            reverse_tokenizer = self.smiles_tokenizer
-            max_length = self.iupac_max_len
-
-        encoding = tokenizer(input,
-                             return_tensors='pt',
-                             padding="max_length",
-                             truncation=True,
-                             max_length=max_length)
-        # Move the input tensor to GPU
-        encoding = {key: value.to(self.model.device) for key, value in encoding.items()}
-
-        # Generate  names
-        output = self.model.generate(input_ids=encoding['input_ids'],
-                                     attention_mask=encoding['attention_mask'],
-                                     max_new_tokens=156,
-                                     num_beams=1,
-                                     num_return_sequences=1)
-
-        # Decode names
-        output = [reverse_tokenizer.decode(ids, skip_special_tokens=True) for ids in output]
-
-        return output[0]

utils/rdkit_utils.py

@@ -1,39 +0,0 @@
-from rdkit import DataStructs, Chem
-from rdkit.Chem import AllChem
-from rdkit.Chem import Draw
-from PIL import Image
-import io
-from .main_model import ChemicalConverter
-
-def validate_smiles2iupac(input_smiles, predicted_iupac):
-    converter = ChemicalConverter(mode="IUPAC2SMILES")
-    predicted_smiles = converter.convert(predicted_iupac)
-
-    ms = [Chem.MolFromSmiles(input_smiles), Chem.MolFromSmiles(predicted_smiles[6:])]
-
-    if None in ms:
-        return None
-
-    fpgen = AllChem.GetRDKitFPGenerator()
-    fps = [fpgen.GetFingerprint(x) for x in ms]
-
-    return DataStructs.TanimotoSimilarity(fps[0], fps[1])
-
-def plot_mol(smiles):
-    # Convert the SMILES string to an RDKit molecule object
-    mol = Chem.MolFromSmiles(smiles)
-
-    # Use RDKit to draw the molecule to an image, with original intended size
-    img = Draw.MolToImage(mol, size=(185, 185))
-
-    # Create a new, blank image with the desired final size (800x190 pixels) with a white background
-    final_img = Image.new('RGB', (890, 185), 'white')
-
-    # Calculate the position to paste the original image onto the blank image to keep it centered
-    left = (890 - 185) // 2
-    top = (185 - 185) // 2  # This will be zero in this case but included for clarity
-
-    # Paste the original image onto the blank image
-    final_img.paste(img, (left, top))
-
-    return final_img