Building computational tools at the intersection of physics, AI, and kidney disease research.
I'm a System Programmer at the University of Lagos and a Data Science Lecturer at Rome Business School, Nigeria. I hold a BSc and MSc in Physics from the University of Lagos.
My independent research focuses on applying AI and physics-based computation to medical problems - specifically kidney disease and urinary health. I'm working toward a PhD in Computational Biology or Health Data Science.
- 🔬 Research focus: Scientific Machine Learning (SciML), Physics-Informed Neural Networks, Quantum-Classical hybrid methods, and Generative AI for drug discovery.
- 🧑🏫 Teaching: Neural Networks, Reinforcement Learning, and applied ML to postgraduate students.
- 🎓 Seeking: PhD/Research opportunities in Computational Biology, Biomedical Physics, or Health Data Science.
- ☁️ Certified: AWS Solutions Architect.
- pinn-glomerular-filtration
- A 2D PINN that models glomerular solute transport under hypertensive conditions by embedding Poiseuille flow and convection-diffusion-reaction PDEs directly into the loss function.
- Achieved <2.5% relative L2 error against the analytical solution.
- 📄 Preprint: Zenodo
- hybrid-vqe-drug-discovery
- A VQE-based pipeline using PennyLane and PyTorch - a classical MLP reduces dimensionality before embedding features into a 4-qubit hardware-efficient ansatz for ground-state energy estimation.
- 📄 Preprint: Zenodo
- Tox21-GNN-Property-Prediction
- A Message Passing Neural Network (MPNN) built with PyTorch Geometric for multi-label toxicity prediction across 12 Tox21 assays, with custom handling for class imbalance and missing targets.
- SMILES-VAE-Generative-Design
- A GRU-based Variational Autoencoder for generating novel, chemically valid molecular structures from SMILES representations, with RDKit validation.
- CKD-Mendelian-Randomization-Pilot
- An R-based Mendelian Randomization analysis exploring causal relationships in Chronic Kidney Disease using GWAS summary statistics.
- AI & SciML: PyTorch, PyTorch Geometric, TensorFlow, Scikit-Learn, PINNs.
- Domain: RDKit (Cheminformatics), PennyLane/Qiskit (Quantum), R (Biostatistics).
- Infrastructure: AWS, Docker, Git, Linux.
- 💼 LinkedIn: linkedin.com/in/abiodun-sojobi
- 📧 Email: asojobi@unilag.edu.ng
- 🏫 Faculty Profile: Rome Business School
"A physics-trained approach to medical discovery."