Patterns in Genomes

Academic project developed as part of my Bioinformatics / Machine Learning course at Sorbonne Université

A bioinformatics analysis system for identifying and studying patterns in genomic sequences, combining classical sequence analysis techniques with machine learning models. The project explores motif detection, genome composition analysis, and predictive classification on biological data.

🛠️ Tech Stack

• Core Technologies: Python 3, Jupyter Notebook
• Libraries: NumPy, Pandas, scikit-learn, Biopython, Matplotlib / Seaborn

📦 Installation & Setup

Prerequisites

• Python 3.9+
• Jupyter Notebook or JupyterLab

pip install numpy pandas scikit-learn biopython matplotlib seaborn jupyter

Instructions

# 1. Clone the repository
git clone https://github.com/Tinshea/Patterns-In-Genomes.git
cd Patterns-In-Genomes

# 2. Launch Jupyter
jupyter notebook

🔬 Key Features

• Motif detection — identification of recurring sequence patterns (k-mers, consensus motifs)
• Genome composition analysis — GC content, codon usage, nucleotide frequency distributions
• Machine learning classification — supervised models to predict genome properties or species from sequence features
• Visualization — sequence logos, frequency plots, confusion matrices

🗂️ Project Structure

Patterns-In-Genomes/
├── notebooks/          # Jupyter notebooks (analysis pipeline)
├── data/               # Genomic datasets (FASTA, CSV)
├── models/             # Trained ML models
└── utils/              # Helper functions

👤 Author

Malek Bouzarkouna & Sevag Boboyan — Sorbonne Université

📄 License

No license specified.