AI Engineer & Bioinformatician
I build models, pipelines, and tools at the intersection of artificial intelligence and the life sciences — turning complex biological data into reproducible, actionable insight.
I'm a researcher and engineer with a background in both computational biology and deep learning. My work spans genomics, single-cell analysis, and building ML models that address real biological questions.
I care about reproducible science, well-documented code, and tools that other researchers can actually run. Most of my work is open source and lives on GitHub.
A transformer-based model trained on bulk RNA-seq data to predict cell type from raw gene expression profiles. Achieves state-of-the-art accuracy on benchmark datasets with a lightweight, interpretable architecture. Includes attention visualisation to highlight biologically meaningful genes.
End-to-end single-cell RNA sequencing pipeline using Scanpy and custom clustering modules. Handles QC, normalisation, dimensionality reduction, and differential expression out of the box.
Gradient-boosted classifier that predicts the functional impact of genomic variants using sequence-derived features and population frequency data.
R package for genome-wide differential methylation analysis on WGBS data. Implements smoothing splines and mixed-effects models with publication-ready visualisations via ggplot2. Available on GitHub and Bioconductor.
Open to research collaborations, open-source contributions, and interesting problems at the intersection of AI and biology.