Personal Statement
I am a Senior Data Scientist and Bioinformatician at the University of Liverpool, specialising in spatial transcriptomics, multi-omics data integration and machine learning for biomedical target discovery. My training is in musculoskeletal disease, particularly osteoarthritis, and I now work across a broader range of tissues and diseases through collaborative projects spanning joint development, reproductive medicine and inflammatory skin disease.

My work runs from primary analysis through to prediction. I analyse and integrate bulk RNA-seq, proteomics, miRNA-seq, ATAC-seq, single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics data, working with both 10x Visium and NanoString GeoMx platforms, and I build the network-based methods, reproducible bioinformatics pipelines and curated knowledge bases needed to interpret them. Harmonised, FAIR data of this kind supports machine learning for patient stratification, biomarker discovery and therapeutic target prioritisation. I am currently applying large language models (LLMs) to metadata curation and the interpretation of omics results, and building biomedical knowledge graphs as a scaffold for machine learning.

See Research for details of my software and data resources, including the SkeletalVis database of skeletal transcriptomics data, the OATargets osteoarthritis knowledge base, and the PhenomeExpress network analysis algorithm.

I enjoy learning new areas of biology and welcome collaboration with experimental groups generating single-cell or spatial data, and with clinical and industry partners interested in omics integration or target identification. Software and analysis code are released openly at github.com/soulj. Publications are listed on Google Scholar and ORCID.