I am a Bioinformatician and Postdoctoral Researcher at Collège de France (CIRB – Denis Duboule Lab), working on chromatin organization and developmental gene regulation using large-scale 2D/3D multi-omics datasets.

I recently completed my PhD in Applied Mathematics at Université de Bourgogne Franche-Comté, where I combined Python, machine learning, deep learning, and mathematical modeling to study keloid disease dynamics and medical image classification.

My work sits at the intersection of bioinformatics, Python-based data science, machine learning, mathematical modeling, and computational biology, with a strong focus on reproducible, scalable, and automated Python pipelines.

• Chromatin organization and developmental gene regulation (Hi-C, RNA-seq, multi-omics) in Python & R
• Administration and maintenance of a local Galaxy server
• Building and integrating custom Python-based workflows into Galaxy
• DevOps for research: Ansible, Docker, Singularity, Git/GitHub
• Data analysis, visualization, and automation in Python, R, and Bash
• Creating reproducible and scalable Python pipelines for lab research

• Advanced multi-omics analysis in Python
• Variant effect prediction with Python (e.g. DNABERT2)
• Workflow automation in Python (Nextflow, Snakemake, Galaxy)
• HPC & cloud-based Python computing
• Scientific visualization & dashboarding (Dash, Plotly, Power BI)

• Developed Python pipelines to interpret BRCA1 and BRCA2 variants
• Generated mutated FASTA sequences from CDS references in Python
• Designed algorithms in Python for mutation injection with correct positional shifts
• Implemented window-based mutation extraction (500–1000 bp) in Python
• Applied machine learning in Python using DNABERT2 for variant classification

• Built Python-based deep learning models for keloid classification
• Conducted numerical simulations using FEniCS (Python)
• Created ML pipelines with Python (TensorFlow, Keras, scikit-learn)
• Deployed Python models using Streamlit and FastAPI
• Developed Python simulations for local and non-local wound healing models

Primary Language

• ✅ Python (Expert)

Data Science & Machine Learning (Python)

• Python, scikit-learn, TensorFlow, PyTorch, Keras, NumPy, Pandas

Bioinformatics & Omics (Python)

• Hi-C, RNA-Seq, multi-omics, Galaxy, runHiC, HPC

Workflow & DevOps

• Snakemake (Python), Nextflow, Ansible, SLURM
• Docker, Singularity, Git/GitHub

Visualization (Python & R)

• Matplotlib, Seaborn, Plotly, Dash, Power BI, ParaView, ggplot2

Other Languages

• Bash, R, MATLAB, C/C++, SQL

Operating Systems

• Linux/Unix, Windows, MacOS

Cloud Platforms

• AWS, GCP

• Condition number for finite element discretisation of nonlocal PDE systems (arXiv, 2025)
• Deep learning approaches for classifying images of keloids, Diagnostics (2025)
• Analytical investigation of a non-local wound healing model, DCDS-B (2024)
• Mathematical investigation of wound healing dynamics, MBE (2023)
• Modelling keloid dynamics, Bulletin of Mathematical Biology (2023)

• AfriGen-D IBT 2025 – University of Cape Town
• PhD Scholarship – Université de Bourgogne Franche-Comté (ANR-PRCI)
• MathMods Consortium Scholarship (EU)
• Artificial Intelligence Engineer – Simplilearn
• Deep Learning & Machine Learning – Simplilearn & Coursera
• Data Science with Python – Coursera (IBM)

• Python-based bioinformatics projects
• Multi-omics & systems biology pipelines in Python
• Machine learning & deep learning (Python)
• Computational biology & genomics
• R&D roles in academia or industry
• Open-source Python scientific projects

• Python for bioinformatics & genomics
• Hi-C / RNA-seq / multi-omics analysis
• Mathematical modeling in Python
• Deep learning in Python (TensorFlow / PyTorch)
• Galaxy, Snakemake & Nextflow workflows
• Scientific computing & reproducibility with Python

• Email: olusegun.adebayo@college-de-france.fr
• LinkedIn: https://www.linkedin.com/in/olusegunekundayoadebayo
• Google Scholar: https://scholar.google.com/citations?user=E31gAaEAAAAJ

Python is the main language behind almost all my research — from mathematical modeling and simulations to bioinformatics pipelines and deep learning for medical applications.