• 👩‍🔬 I am a Bioinformatician and Data Scientist interested in developing computational tools and applying statistical methods, and cutting-edge technologies (including machine learning and artificial intelligence) for integrating, managing, analyzing and visualizing high-dimensional data to unravel true associations, hidden patterns, and unknown correlations in big and high dimensional biological data.

• 💞️ I am excited by big, complex and messy data that ends up into beautiful and meaningful visualizations that help us derive actionable insights and new hypotheses for translational research.

• 1 Background

• 2 Research

• 3 Why ML and AI

• 4 Example Projects

I come from an IT background that heavily revolved around computer programming (C++, Java, Python), database management systems (MySQL and PostgreSQL), discrete and computational mathematics, statistics, data and computer networks (CCNA/Cisco instructor as well), network socket programming in Java, information systems (with PHP and MySQL), web services, information and network security, software engineering, Linux and Windows systems administration, business intelligence and data warehousing, and IT project planning and management. I have a Bachelor of Science degree in Information Technology and a Master's degree in Information Technology. My love for Biology drove me into Bioinformatics, a powerful interdisciplinary field that develops computational methods and software tools to support the elucidation of patterns and derivation of inferences and insights from big and complex biological data. I currently hold a data-science driven Master of Science degree in Bioinformatics and working my way towards gaining more experience in machine learning and artificial intelligence 💪.

My previous research, conducted in the Shah Lab of Computational Cancer Biology (in collaboration with the Aparicio Lab), revolved around triple negative breast cancers (TNBC) - the most aggressive, complex, heterogenous and hard to treat form of breast cancer, which unfortunately is more prevalent in younger patients (age < 50 years). I conducted research to stratify TNBCs towards improving our understanding of this complex disease. This work was accomplished by developing and applying computational, statistical and database driven approaches to analyze and visualize large-scale whole genome profiles of samples from TNBC patients; research that discovered for the first time and to the best of our knowledge, five genomic and clinically distinct TNBC subgroups, revealed by unsupervised hierarchical clustering, based on mutation signatures, and somatic mutations (at all scales) in patient genomes. This research resulted into award-winning tools for the management, analysis and visualization of whole-genome profiling data, and showed for the utility of the genome as a potential discriminant biomarker in patient treatment.

Prior to joining the Shah Lab, I conducted my IT master's thesis research in the area of Web Application security, where I developed an algorithm for securing Web Applications from SQL injection attacks.

I later joined the Kobor Lab where I conducted statistical and bioinformatics analyses of high-throughput epigenomics and genotyping data, to facilitate the interpretation of associations between molecular data, the environment, and disease. Thereon, I joined the Dobin Lab (Cold Spring Harbor Laboratory) where I conducted research to investigate reference bias in the estimation of genome-wide alle-specific expression (ASE) from high throughput RNA-seq data.

I am currently placed in the department of surgery, (Porrett Lab, UAB), where I lead, manage, and contribute to existing projects through performing bioinformatics, statistical, and computational analyses of high-throughput single-cell RNA-seq, CITE-seq, and spatial transcriptomics datasets. These projects are largely conducted to support the elucidation of the immune response to transplanted organs.

Current advances in next-generation sequencing (NGS) technologies, have led to the generation of vast amounts of data that have augmented our understanding of human variation and disease. However, the production of these large and high dimensional datasets, coupled with confounding factors, and the heterogeneity of features under investigation, presents significant challenges in unravelling true associations relevant for unravelling molecular mechanisms underpinning disease, and processes underlying disease progression and outcomes. Leveraging the powerful opportunities presented by data science (like ML & AI) in analyzing large and complex high-dimensional data supports the elucidation of causative mechanisms and correlations of complex events at higher precisions.

Please note that since some of these projects are works in progress or not published yet, only abstract snippets have been provided

More project examples can be found on my portfolio