Lead Data Scientist
Life Sciences
Sensyne Health Plc, Oxford, UK

Develops and applies the next generation of data science, artificial intelligence, and machine learning to big anonymised patient data from multiple sources to accelerate drug discovery and improve patient care. I am particularly interested in the area of bioinformatics and multiomics.


Research vision

Enormous amounts of biological data of various types have been and are increasingly being generated; yet, there is currently little or no development in methods that leverage datasets from multiple data-types collectively in biological research. Therefore, I am passionate about developing and applying state-of-the-art data science, artificial intelligence, machine learning, and bioinformatics to big anonymised patient data from multiple sources to accelerate drug discovery and improve patient care. This will not only lead to breakthroughs in computational methods; it will also enable breakthroughs in medical and biological applications such as drug target and trait signature discoveries, gene-trait associations, gene-gene interactions, and many other timely applications.

Current research

I work in the Translational Medicine Division at Sensyne Health Plc (Oxford, UK) within a team of scientists to develop and apply bioinformatics, artificial intelligence, and data science to large and unique anonymised patient data in collaboration with the UK NHS and the University of Oxford to accelerate the discovery of new medicines and to improve patient care. I have particular interest in the area of genomic and multiomic data analysis, an area in which I lead developments.

Previous research

Bioinformatic methods development: I developed and advanced a number of bioinformatic methods for gene expression clustering. My current state-of-the-art framework is called clust (Abu-Jamous & Kelly, Genome Biology, In Press). Clust extracts optimal and complete clusters automatically from one or more heterogeneous gene expression datasets collectively, it outperforms mainstream clustering algorithms with minimal manual intervention, and is available freely as an easy-to-use package on https://github.com/BaselAbujamous/clust. A web-based front-end will be released soon!

Applications in biology: I actively employ my bioinformatic methods and other methods to drive discoveries in biology. For instance, while working in Dr Steve Kelly’s laboratory at the Department of Plant Sciences, the University of Oxford (2016-2019), I identified key engineering targets to improve photosynthesis in the rice crop. These targets have been validated and are in the process of being incorporated into engineered crops. Before that, while being in Professor Asoke Nandi’s group at Brunel University London (2013-2016), I identified a counter-intuitive transcriptomic signature in breast cancer cell-lines with a prognostic value in collaboration with Professor Adrian Harris and Dr Francesca Buffa (Department of Oncology, the University of Oxford). I also participated in defining the dynamics of distinct genetic programmes during human erythropoiesis (red blood production) in collaboration with Professor David Roberts and colleagues (Radcliffe Department of Medicine, University of Oxford). Moreover, I discovered a novel transcriptomic module that is consistently anti-correlated with growth in budding yeast, and elucidated the function of the CMR1 yeast gene in DNA metabolism. Additionally, I participated in identifying patterns of human brain activity during emotional stimuli in collaboration with Professor Elvira Brattico (Aarhus University, Denmark).

Publications and meetings

I published a research monograph book, a book chapter, and many journal articles, I presented my work in various national and international conferences and research meetings, and I delivered different invited talks on the topics of my research interest.

My CV is available here.