Alper Celik

Data scientist and bioinformatician with a passion for machine learning and data analysis. I enjoy exploring the intersection of biology and technology to uncover insights from complex datasets.

During my Ph.D., I immersed myself in advanced scientific research, tackling complex problems with a focus on data-driven discovery. I have developed data analysis pipelines where there was none. I am the first dry (no wet-lab work) graduate of my lab of 30+ years. My work centered on developing novel machine learning models, to analyze intricate datasets and uncover patterns with significant biological implications. The infrastructure and knowledgebase I have built has led to many publications long after my departure from the lab.

In my role as a senior bioniformatician at SickKids I spent countless hours designing predictive algorithms, to achieve high accuracy and efficiency. This hands-on experience deepened my understanding of how to transform raw data into meaningful insights, grounding my approach in rigorous scientific methodology. From building pipelines to diagnose previously undiagnosible diseases to practically eliminating tedious manual work for injury surveilance systems.

Beyond modeling, I’ve built and optimized data pipelines using tools like snakemake, enabling efficient processing of large-scale datasets. My projects often involved SQL-driven data exploration to identify trends and test hypotheses, ensuring robust and reproducible results. One of my key achievements was developing a scalable framework for real-time data analysis, which significantly improved the speed and reliability of insights for processing clinical notes with 99%+ accuracy. This work wasn’t just about crunching numbers—it was about asking the right questions and letting the data guide the answers.

I’ve also led collaborative efforts, working with diverse teams to integrate data science into broader scientific investigations. Whether it was refining algorithms to predict outcomes in complex systems or mentoring peers on statistical techniques, I focused on bridging the gap between technical execution and scientific inquiry. My contributions have consistently aimed at advancing knowledge, from crafting visualizations that make complex findings accessible to publishing research that pushes the boundaries of data science applications. I’m driven by the challenge of using data to solve tough problems and the satisfaction of seeing those solutions make a tangible impact.