Create app.py

app.py

@@ -0,0 +1,29 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load the pre-trained model and tokenizer
+model_name = "khanfs/ChemSolubilityBERTa"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Define the prediction function
+def predict_solubility(smiles_string):
+    inputs = tokenizer(smiles_string, return_tensors='pt', truncation=True, padding='max_length', max_length=128)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    solubility = outputs.logits.item()
+    return f"Predicted Solubility: {solubility:.4f} log mol/L"
+
+# Gradio interface
+iface = gr.Interface(
+    fn=predict_solubility,
+    inputs="text",
+    outputs="text",
+    title="ChemSolubilityBERTa",
+    description="Enter a SMILES string to predict its aqueous solubility using ChemSolubilityBERTa.",
+    examples=[["CCO"], ["CC(C)=O"], ["C1=CC=CC=C1"]]  # Example SMILES strings for ethanol, acetone, and benzene
+)
+
+# Launch the app
+iface.launch()