Wakil is specialized in mathematical and statistical modelling with a mixed work background in academia and multiple industries such as cancer and genomics, biotechnology, gene therapeutics, energy, and agriculture. Wakil's research interest lies in the development of data-driven mathematical and statistical models that describe the underlying dynamics of discrete/continuum real-world processes. His doctoral research focused on the study of Turing systems of reaction-diffusion type for spatiotemporal pattern formation in nature. His work experience to date provided the opportunity to extend the application of these systems to investigate the dynamics of biochemical species in a number of real-world processes such agricultural fertilizers, dynamics of epigenetic material in stem-cells, diffusion-driven oxygen sensors, modelling the growth of solid tumours, and chemical batteries.
Wakil's work background in a diverse range of industry provided the platform to integrate data-driven models of statistical machine-learning to develop AI-based work-flow systems for medium to large teams of non-quantitative industrial and wet-lab scientists. He has served as a Senior-Data-Scientist within PR&D departments of cancer and gene therapeutic and biotechnology firms where among others he held the responsibility to lead the development and thereby transition from manual processing of data to organization-wide cloud-base and fully automated data storage and centralization infrastructure. He has also served as a data-driven consultant for firms that develop viral vector technologies for gene therapy. Wakil has held the responsibility on trial versions of automation products such as robotics and enterprise software. Moreover he has sourced and delivered department-wide capability enhancement workshops for industrial staff-scientists in the areas of applications of predictive statistical modelling and process characterization.
Wakil has also led the development of innovative data-driven and AI projects with commercial and scientific case-studies using consumer focused solutions that either generated revenue or acquired a deeper understanding of the relevant scientific question. These consisted of using unsupervised clustering algorithms to classify personas for recommendation based product suggestions. Using supervised ML-algorithms he has built with his team predictive pipelines to quantify the prospects of success for users in terms of ranking the available choices relevant to their personalized preference. He has managed the development of data-driven products and solutions that identified sources of recruitment leaks for higher education institutions and competitive analysis for the same. He has worked with clients from higher education institutions across the UK.
At the Institute of Cancer and Genomic Sciences at Birmingham University Wakil was responsible for the development and production of pipelines for NGS data from preparation to the deployment of machine-learning products. This included the application of bioinformatics technologies on all common types of NGS data such as DNase-seq, ChIP-seq and RNA-seq. Wakil supervised the development of full-scale machine-learning pipelines for predicting genome-wide distributions of cis-regulatory elements such as enhancers. The aim was to investigate and thereby identify both the aberrant gene regulatory enhancers and priming elements across the embryonic developmental pathways in stem cells. With the team we were able to build novel data-driven predictive models to simulate spatiotemporal networks and evolution of epigenetic material to study the "central-dogma" as a continuum process and in turn investigate the aberrant differential gene expression pathways that led to Leukaemia.
Wakil has provided industrial consultation in a number of mathematical modelling case studies which required formulation of processes from the first principle in robotics, acoustics, aeronautics, agriculture, energy, genomics, and optimization of medical devices such as oxygen sensors.