Non-Coding Driver Mutations
Investigating the 98% non-coding genome to find regulatory mutations that drive breast cancer progression, using more than 5,000 whole genomes from TCGA and ICGC.
Research
Seeing cancer in the genome's dark matter.
I build the computational tools to read the 98% of the genome that doesn't code for proteins, hunting the non-coding driver mutations behind breast cancer.
Research focus
Threads I'm pulling.
Where the epigenome, machine learning and a little curiosity meet cancer medicine.
Deep Learning for Genomics
Developing CNNs, GNNs, MLPs and Hidden Markov Models to predict chromatin accessibility and prioritise candidate driver mutations from multi-omics data.
3D Regulatory Mapping
Building breast tissue-specific regulatory maps by integrating single-cell ATAC-seq, spatial transcriptomics and ENCODE regulatory elements.
Surgical Robotics & Embedded AI
Exploring Arduino and ESP32 prototyping as a practical bridge from machine learning research into surgical robotics and autonomy workflows.
Currently exploringWhy this work matters
Most disease variants hide in the non-coding genome.
Almost every common cancer-risk variant lives in the 98% we used to call junk. If we can finally read it, we can find the mutations that rewire a healthy cell into a tumour, and the vulnerabilities that could treat it. That's the bet my whole PhD is built on.
Publications
Research & publications.
2026
Deciphering the Non-coding Cancer Genome through Deep Learning and Multiomic Integration
Submitted to npj Genomic Medicine
📝 Under review
Let's talk
Let's decode something.
Collaborations, questions, or just curious about the non-coding genome? My inbox is open.