Lära Filtering Libraries for Virtual Screening | Virtual Screening and Compound Ranking

Virtual screening is a key step in computational drug discovery, allowing you to rapidly evaluate large libraries of compounds to identify promising candidates for further study. Before you begin virtual screening, it is essential to filter your compound library to focus on molecules with properties consistent with successful drugs. This filtering process increases the efficiency of screening and reduces the likelihood of pursuing compounds that are unlikely to succeed due to poor drug-likeness.

Definition

Lipinski's Rule of Five is a set of criteria used to evaluate whether a compound is likely to be an orally active drug in humans. The rule states that, in general, an orally active drug has no more than one violation of the following: not more than 5 hydrogen bond donors, not more than 10 hydrogen bond acceptors, a molecular weight under 500 daltons, and a logP value under 5.


              12345678910111213141516171819202122232425262728293031323334
            
import pandas as pd
from rdkit import Chem
from rdkit.Chem import Descriptors

def passes_lipinski(mol):
    mw = Descriptors.MolWt(mol)
    logp = Descriptors.MolLogP(mol)
    h_donors = Descriptors.NumHDonors(mol)
    h_acceptors = Descriptors.NumHAcceptors(mol)
    return (
        mw <= 500 and
        logp <= 5 and
        h_donors <= 5 and
        h_acceptors <= 10
    )

# Example SMILES
smiles_list = [
    "CC(=O)OC1=CC=CC=C1C(=O)O",  # Aspirin
    "CCN(CC)CCCC(C)NC1=C2C=CC(=CC2=NC=C1)Cl",  # Chlorpromazine
    "C1=CC=CC=C1",  # Benzene (not drug-like)
]

results = []
for smi in smiles_list:
    mol = Chem.MolFromSmiles(smi)
    if mol:
        results.append({
            "smiles": smi,
            "passes_lipinski": passes_lipinski(mol)
        })

df = pd.DataFrame(results)
print(df)

Lipinski's Rule of Five is a widely used guideline to assess the drug-likeness of small molecules. According to this rule, a compound is more likely to be orally active if it meets the following criteria:

Molecular weight is less than or equal to 500 daltons;
LogP (octanol-water partition coefficient) is less than or equal to 5;
No more than 5 hydrogen bond donors (sum of OH and NH groups);
No more than 10 hydrogen bond acceptors (sum of N and O atoms).

Each of these rules is designed to ensure that a molecule has the right balance of size, solubility, and permeability, which are critical for oral bioavailability. Violating more than one of these rules suggests a compound may have poor absorption or permeation properties.


              123456789101112131415161718192021222324252627282930313233
            
from rdkit import RDLogger
RDLogger.DisableLog('rdApp.*')  # Suppress RDKit warnings

compound_data = [
    {"name": "Aspirin", "smiles": "CC(=O)OC1=CC=CC=C1C(=O)O"},
    {"name": "Chlorpromazine", "smiles": "CCN(CC)CCCC(C)NC1=C2C=CC(=CC2=NC=C1)Cl"},
    {"name": "Benzene", "smiles": "C1=CC=CC=C1"},
    {"name": "Amoxicillin", "smiles": "CC1(C)SCC(N1C(=O)NC2=CC=CC=C2)C(=O)O"},
]

def passes_lipinski(mol):
    from rdkit.Chem import Descriptors
    mw = Descriptors.MolWt(mol)
    logp = Descriptors.MolLogP(mol)
    h_donors = Descriptors.NumHDonors(mol)
    h_acceptors = Descriptors.NumHAcceptors(mol)
    return (
        mw <= 500 and
        logp <= 5 and
        h_donors <= 5 and
        h_acceptors <= 10
    )

from rdkit import Chem
filtered = []
for compound in compound_data:
    mol = Chem.MolFromSmiles(compound["smiles"])
    if mol and passes_lipinski(mol):
        filtered.append(compound["name"])

print("Drug-like compounds passing Lipinski's Rule of Five:")
for name in filtered:
    print(name)

Filtering compound libraries using drug-likeness rules such as Lipinski's Rule of Five has a significant impact on the outcomes of virtual screening. By removing compounds that are unlikely to be orally bioavailable, you reduce the number of false positives and focus your computational and experimental resources on candidates with a higher chance of success. However, over-filtering may exclude novel or unconventional drug candidates, so it is important to balance strictness with the goals of your screening project.

Study More

To learn more and get more hands-on practice with the Pandas library, we recommend taking the Introduction to Pandas course.

Var allt tydligt?

Tack för dina kommentarer!

Avsnitt 3. Kapitel 1

Fråga AI

Fråga vad du vill eller prova någon av de föreslagna frågorna för att starta vårt samtal

Suggested prompts:

Can you explain what virtual screening is used for in drug discovery?

What are some other drug-likeness rules besides Lipinski's Rule of Five?

How strict should I be when filtering compounds for virtual screening?

Svep för att visa menyn