Chemistry Tags

<SMILES> CCO </SMILES>

query = "What is the molecular formula of <SMILES> CC(C)Cl </SMILES>?"

<IUPAC> aspirin </IUPAC>

query = "Provide the SMILES for <IUPAC> 4-ethyl-4-methyloxolan-2-one </IUPAC>."

<MOLFORMULA> C9H8O4 </MOLFORMULA>

Query: "What is the molecular formula of <IUPAC> aspirin </IUPAC>?"
Response: "<MOLFORMULA> C9H8O4 </MOLFORMULA>"

<NUMBER> -1.41 </NUMBER>

Query: "How soluble is <SMILES> CC(C)Cl </SMILES>?"
Response: "Its log solubility is <NUMBER> -1.41 </NUMBER> mol/L."

<BOOLEAN> Yes </BOOLEAN>

<BOOLEAN> No </BOOLEAN>

Query: "Is <SMILES> COC[C@@H](NC(C)=O)C(=O)NCC1=CC=CC=C1 </SMILES> toxic?"
Response: "<BOOLEAN> No </BOOLEAN>"

@tool
def structure_chem_prompt(original_prompt):
    """Structure and tag IUPAC or SMILES chemical information."""
    response = client.beta.chat.completions.parse(
        model="gpt-4o",
        messages=[{
            "role": "system",
            "content": SYSTEM_TAG_PROMPT,
        }, {
            "role": "user",
            "content": f"Structure the input query: {original_prompt}",
        }],
        response_format=StructuredPrompt,
    )
    return {"new_prompt": simplified_prompt.get("new_prompt")}

SYSTEM_TAG_PROMPT = """
You are an EXPERT chemical information tagger. Your task is to format the input query 
based on the information below. You MUST return ONLY the formatted input query!

When processing chemical information, use only two tags in the input query: 
<SMILES> for SMILES representations and <IUPAC> for IUPAC names.

Tag Definitions:
SMILES: <SMILES> ... </SMILES> for chemical structure in SMILES notation.
IUPAC: <IUPAC> ... </IUPAC> for the IUPAC name of the compound.

Instructions:
1. In the input query, use only the <SMILES> and <IUPAC> tags to wrap the appropriate information.
2. Ensure no extra characters or spaces are present within the tags.
"""

# All represent ethanol
"CCO"     # Start from carbon
"OCC"     # Start from oxygen  
"C(O)C"   # Explicit branching

from rdkit import Chem

mol = Chem.MolFromSmiles("OCC")
canonical = Chem.MolToSmiles(mol)
print(canonical)  # Output: "CCO"

def canonicalize_smiles_in_text(text: str) -> str:
    """Find <SMILES> tags and canonicalize their contents."""
    pattern = r'<SMILES>\s*([^<]+)\s*</SMILES>'
    
    def replace_smiles(match):
        smiles = match.group(1).strip()
        mol = Chem.MolFromSmiles(smiles)
        if mol is None:
            return match.group(0)  # Keep original if invalid
        canonical = Chem.MolToSmiles(mol)
        return f"<SMILES> {canonical} </SMILES>"
    
    return re.sub(pattern, replace_smiles, text)

class StructuredPrompt(BaseModel):
    new_prompt: str  # Must contain properly closed tags

@tool
def validate_smiles_rdkit(smiles_string: str) -> dict:
    """Validate SMILES with detailed error reporting."""
    parsing_details = parse_smiles(smiles_string)
    return {
        "valid": parsing_details["valid"],
        "error_message": parsing_details["validity_vector"],
    }

import re

def extract_smiles(response: str) -> str:
    """Extract SMILES from tagged response."""
    match = re.search(r'<SMILES>\s*([^<]+)\s*</SMILES>', response)
    return match.group(1).strip() if match else ""

query = "What is the SMILES for aspirin?"
# LlaSMol won't know "aspirin" is a chemical name

query = "What is the SMILES for <IUPAC> aspirin </IUPAC>?"

query = "Formula of < SMILES > CCO < /SMILES >?"
# Tag parser will fail

query = "Formula of <SMILES> CCO </SMILES>?"

query = "What is the IUPAC name of <IUPAC> CCO </IUPAC>?"
# CCO is SMILES, not IUPAC

query = "What is the IUPAC name of <SMILES> CCO </SMILES>?"

query = "Is <SMILES> CC(C)Cl toxic?"
# Missing closing tag

query = "Is <SMILES> CC(C)Cl </SMILES> toxic?"