A graduate who builds relentlessly — turning biological data into decisions that matter, from single-cell genomes to machine-learning pipelines.
Projects that moved real numbers
Each build taken from raw data to a decision a stakeholder could act on — spanning single-cell genomics, deep learning, healthcare analytics, and applied ML.
Single-Cell RNA-seq Classification & Pipeline Modernisation
Reproduced and extended an end-to-end scRNA-seq classification workflow across 734 single-cell libraries, then re-engineered the legacy alignment pipeline — STAR, Salmon, scran normalisation, Seurat/Leiden clustering — for a dramatic speedup while improving QC sensitivity. Cells were classified into progenitor, neuronal, and zonal subpopulations and surfaced through an interactive R Shiny portal.
View code on GitHubMicro-Analysis of Eye Movements with Deep Learning
My dissertation: an end-to-end pipeline bridging RITnet deep-learning eye segmentation with classical computer-vision irisometry to measure ocular torsion and pupillometry — auto-seeding between DL and CV methods and streaming results into an interactive dashboard. Active, ongoing work.
View work-in-progressAdvanced Sequence Motif Finder
A deployed motif-search tool for DNA / RNA / protein sequence analysis — exact and fuzzy matching, interactive Plotly visualisations, and PDF report generation, built on Biopython and live in the browser.
Open the live appTelco Customer Churn Intelligence
An end-to-end XGBoost pipeline for customer risk stratification — engineered 40+ features and selected the top 10 by importance, with cross-validated training and statistical validation, delivered to non-technical stakeholders through a Power BI decision-support dashboard.
View on GitHubNHS Real-Time Drug Spend Analytics
An ETL pipeline over 109M+ prescriptions and £878M of spend — integrating multi-source clinical records, resolving data-quality issues, and surfacing prescribing signals in an interactive Power BI dashboard with a Streamlit prototype.
Additional tools & experiments
DNA Composition Finder
A Streamlit app for analysing nucleotide composition and sequence statistics.
Primer Designing Tool In development
A browser-based tool for designing and validating PCR primers.
Everything else on GitHub
Coursework, experiments, and works-in-progress across genomics and data science.
What I build with
A stack spanning statistical rigour, production data engineering, and genomics-specific tooling.
🧬Bioinformatics & Genomics
🤖ML & Languages
📊Data & BI
📐Statistics & Validation
⚙️Infrastructure
🎓Certifications
At the intersection of research and application
I'm an MSc Bioinformatics candidate at the University of Leicester (graduating Sep 2026), specialising in single-cell genomics, statistical validation, and large-scale computational workflows.
My work blends bioinformatics research with AI-driven data analysis — from exploring gene-expression datasets to building machine-learning models for precision medicine. What drives me is translating complex biological data into decisions that non-technical stakeholders can act on.
I'm curious and relentless by default. I like living where research meets application: building the pipeline, validating it properly, and making the result something a person can actually use. I'm early in my career and pushing hard to prove it.
Details
Languages
Experience & education
Let's build something worth measuring.
Open to full-time roles in bioinformatics, data science, and ML. If you're working on genomics, healthcare, or hard data problems — let's talk.