Pharmalyzer 0.1.0

Cheminformatics toolkit for property calculation, filtering, and QSAR modeling

Pharmalyzer

Pharmalyzer is a Python package for data preprocessing, screening, and early-stage analysis of chemical datasets. It provides a set of rule-based and RDKit-powered tools for screening, filtering, and assessing compounds' ADME properties.It enables fast and reliable computation of physicochemical and pharmacokinetic properties from SMILES strings, supporting cheminformatics and drug discovery workflows.

Features

• Physicochemical Properties: MW, LogP, TPSA, H-bond donors/acceptors, etc.
• ADME Prediction: GI absorption, BBB permeability, logKp, excretion
• Rule-Based Filtering: Lipinski, Veber, Ghose, PAINS, Brenk filters
• QSAR Modeling Tools: Encoding, feature selection, scaling, outlier detection
• Similarity & Integration: Compound comparison, data merging
• ChEMBL Integration: Fetch data directly from the ChEMBL database

Installation

pip install Pharmalyzer-0.1-py3-none-any.whl

---

## 🧪 Quickstart Example

```python
from Pharmalyzer import cleaner, Drug_rules, ADME

# Load a sample CSV file containing SMILES
import pandas as pd
df = pd.read_csv("Pharmalyzer/Pharmalyzer/sample_data.csv")

# Clean the data
df_clean = cleaner.clean_smiles(df, smiles_col="SMILES")

# Apply Lipinski rule filter
df_lipinski = Drug_rules.lipinski_filter(df_clean)

# Calculate ADME properties
df_adme = ADME.calculate_properties(df_lipinski)

print(df_adme.head())

---

🧰 Module Overview

Module	Description
cleaner.py	Standardizes, removes salts, and cleans SMILES strings
Drug_rules.py	Filters compounds using rules like Lipinski, Ghose, PAINS
ADME.py	Computes key ADME properties and predictions
toxicity.py	Predicts potential toxicity risks
qsar.py	Builds and evaluates QSAR models
encoder.py, scaler.py	Preprocessing tools for ML pipelines
chembl_client.py	Fetches compound data from ChEMBL
feature_selection.py	Feature reduction and selection techniques
filtering.py, outliers.py	Additional data cleaning tools
integrate.py, similarity.py	Merging datasets, Tanimoto similarity calculations

---

🖼️ Before vs After Cleaning (Example Visualization)

(Replace with actual plot)

from Pharmalyzer import cleaner
import matplotlib.pyplot as plt

# Before cleaning
df = pd.read_csv("sample_data.csv")
print("Before:", len(df))

# After cleaning
df_clean = cleaner.clean_smiles(df)
print("After:", len(df_clean))

---

License

MIT License

Author

Created by [Your Name]
📧 [e-mail] & [e-mail]