Computational biomedical researcher working at the intersection of AI-driven drug discovery, digital twin modelling, and verifiable scientific workflows.
I'm a biochemistry-trained researcher who has just completed a Master of Engineering in ICT Convergence Engineering at Kumoh National Institute of Technology, South Korea, on a K-GKS scholarship. My path into computation began with wet-lab biochemistry at the University of Lagos, where I worked on protein biology and antioxidant chemistry, and it has since grown into a programme of work on machine learning, digital twin modelling, and blockchain-verified workflows for drug discovery.
I'm most interested in the moments where biology, machine learning, and reproducibility meet. I build systems that make structure-based virtual screening faster and more trustworthy, and I care deeply about the question of how we know that a model's prediction — or a pipeline's result — actually means what it claims to mean. Much of my recent work sits under that umbrella: consensus AI-docking, deterministic binding-site analysis, and tamper-evident provenance for biomedical data.
Looking ahead, my doctoral interest is in trustworthy AI digital twins for stem-cell-derived Parkinson's disease models — integrating multi-omics measurements, perturbation prediction, and auditable data and model provenance, so that a forecast about how a cell will differentiate can be inspected as carefully as it is made.
Outside the lab, I've taught biology and chemistry to more than a hundred students in Nigeria, facilitated entrepreneurial leadership programmes across Nigerian universities, and worked in product research and business development. I like building things that are rigorous and legible — to collaborators, to reviewers, and to the people whose lives the work eventually touches.
Consensus AI–docking pipelines that combine learned scoring with target-dependent optimisation, aiming at screening libraries that are both more accurate and more verifiable than single-scorer approaches.
Deterministic workflows for protein structure preparation and binding-pocket detection, with an emphasis on reproducibility and cross-tool consistency.
Molecular activity prediction, lead optimisation, and scaffold analysis — including physics-informed and federated formulations for settings where data cannot move.
Proteomics-integrated state-space and transformer-based digital twins for dopaminergic stem-cell differentiation forecasting, with leakage-safe benchmarking — building toward trustworthy AI models of stem-cell-derived Parkinson’s disease.
Blockchain-integrated provenance for biomedical pipelines, credentialing of biomaterials and certificates, and tamper-evident data management across PDB, UniProt, and IoT-sourced biomedical signals.
M.Eng. thesis · defended 21 May 2026
How biomolecular computational workflows can be engineered as verifiable systems — combining tamper-evident provenance, deterministic output verification, and policy-enforced validity for multi-party exchange.
Research Lead
AI-enabled virtual screening and protein-focused drug discovery workflow integrating computational modelling and predictive analysis. Target-dependent screening, protein structure and binding-site analysis, reproducible workflow design.
Research Lead
Blockchain-secured framework for biomedical and scientific workflow provenance, integrating PDB and UniProt to support reproducible computational biology pipelines. Published in PeerJ Computer Science.
Tech Lead
Secure collaborative LaTeX writing tool built on the lab's Purechain network. Focused on multi-author integrity and verifiable document history.
Tech Lead
Blockchain abstraction platform designed to lower the integration cost of adopting Purechain across lab applications.
Technical Paper Lead
Certificate protection and tampering-verification system via blockchain, with a policy-enforced credential architecture.
Bioinformatics Intern
Investigated protein targets of Mycobacterium tuberculosis and potential drug candidates using molecular docking and bioinformatics tooling.
Thesis: Blockchain-Enabled Trust Infrastructure for Verifiable Biomolecular Computational Workflows. Studied on a K-GKS full-ride scholarship from the Korean Government.
Facilitated sessions on Empathy & Feedback, Identity & Mental Models, Proactivity, and Leading Change for fellows selected from 102 universities across Nigeria.
Prepared over 100 students for national secondary school and university entrance examinations, maintaining an approximate 90% pass rate.
Supported the programme facilitator in preparing teaching and training materials for ELP lecturers at Elizade University, Ondo State.
I'm happy to hear from collaborators, students, and groups interested in AI for drug discovery or verifiable scientific workflows. Email is the fastest way to reach me.