Utility Classes

class MoleculeEntry:
    def __init__(self, smiles, score=0, **kwargs)

mol1 = MoleculeEntry("CCO")
mol2 = MoleculeEntry("OCC")  # Same molecule, different SMILES
print(mol1 == mol2)  # True (after canonicalization)

mol1 = MoleculeEntry("CCO", score=0.8)
mol2 = MoleculeEntry("CC", score=0.9)
print(mol1 < mol2)  # True

mol_set = {MoleculeEntry("CCO"), MoleculeEntry("CC")}

mol = MoleculeEntry("CCO", score=0.85)
print(mol)  # "smiles: CCO, score: 0.85"

from chemlactica.mol_opt.utils import MoleculeEntry

# Create a molecule
mol = MoleculeEntry(
    smiles="CC(=O)Oc1ccccc1C(=O)O",  # Aspirin
    score=0.92
)

print(mol.smiles)       # Canonical SMILES
print(mol.score)        # 0.92
print(mol.fingerprint)  # Morgan fingerprint

# Add similar molecules
similar = MoleculeEntry("CC(=O)OC1=CC=CC=C1")
mol.similar_mol_entries = [similar]

# Additional properties
mol_with_props = MoleculeEntry(
    smiles="CCO",
    logP=0.5,
    mw=46.07
)
print(mol_with_props.add_props)  # {'logP': 0.5, 'mw': 46.07}

class OptimEntry:
    def __init__(self, last_entry, mol_entries)

entry = OptimEntry(
    last_entry=MoleculeEntry("CCO", score=0.8),
    mol_entries=[MoleculeEntry("CC", score=0.7)]
)

config = {
    "strategy": ["rej-sample-v2"],
    "eos_token": "</s>",
    "sim_range": [0.3, 0.7]
}

# Generation prompt
gen_prompt = entry.to_prompt(
    is_generation=True,
    include_oracle_score=True,
    config=config,
    max_score=0.85
)

# Training prompt
train_prompt = entry.to_prompt(
    is_generation=False,
    include_oracle_score=True,
    config=config,
    max_score=0.85
)

entry = OptimEntry(None, [MoleculeEntry("CCO")])
new_mol = MoleculeEntry("CCO")
print(entry.contains_entry(new_mol))  # True

class Pool:
    def __init__(self, size, validation_perc)

pool = Pool(size=100, validation_perc=0.1)

# Add entries
entries = [
    OptimEntry(MoleculeEntry("CCO", score=0.9), []),
    OptimEntry(MoleculeEntry("CC", score=0.8), [])
]
pool.add(entries)

print(len(pool))  # 2

train, valid = pool.get_train_valid_entries()
print(f"Training: {len(train)}, Validation: {len(valid)}")

pool = Pool(size=100, validation_perc=0.1)
# ... add entries ...

# Sample 10 random entries for prompting
subset = pool.random_subset(10)

pool = Pool(size=100, validation_perc=0.1)
print(len(pool))  # 0

from chemlactica.mol_opt.utils import Pool, OptimEntry, MoleculeEntry

# Create pool
pool = Pool(size=50, validation_perc=0.2)  # 20% validation

# Generate and add molecules
for i in range(100):
    mol = MoleculeEntry(f"C" * (i + 1), score=i / 100)
    entry = OptimEntry(mol, [])
    pool.add([entry])

print(f"Pool size: {len(pool)}")  # 50 (max size)

# Get train/valid split
train, valid = pool.get_train_valid_entries()
print(f"Train: {len(train)}, Valid: {len(valid)}")  # ~40, ~10

# Sample for generation
subset = pool.random_subset(5)
for entry in subset:
    print(entry.last_entry)

from chemlactica.mol_opt.utils import canonicalize

smiles = "OCC"
canonical = canonicalize(smiles)
print(canonical)  # "CCO"

from chemlactica.mol_opt.utils import get_morgan_fingerprint
from rdkit import Chem

mol = Chem.MolFromSmiles("CCO")
fp = get_morgan_fingerprint(mol)

from chemlactica.mol_opt.utils import get_maccs_fingerprint
from rdkit import Chem

mol = Chem.MolFromSmiles("CCO")
fp = get_maccs_fingerprint(mol)

from chemlactica.mol_opt.utils import tanimoto_dist_func

mol1 = MoleculeEntry("CCO")
mol2 = MoleculeEntry("CCCO")
similarity = tanimoto_dist_func(mol1.fingerprint, mol2.fingerprint)
print(f"Similarity: {similarity:.3f}")

from chemlactica.mol_opt.utils import set_seed

set_seed(42)

from chemlactica.mol_opt.utils import generate_random_number

# Generate random SAS score
sas = generate_random_number(2.0, 3.0)

from chemlactica.mol_opt.utils import create_prompt_with_similars, MoleculeEntry

mol = MoleculeEntry("CCO", score=0.85)
mol.similar_mol_entries = [
    MoleculeEntry("CCCO", score=0.80),
    MoleculeEntry("CC(C)O", score=0.75)
]

prompt = create_prompt_with_similars(mol, sim_range=[0.4, 0.7])
# Generates prompt with [SIMILAR]CCCO 0.65[/SIMILAR][SIMILAR]CC(C)O 0.58[/SIMILAR]