I am a computational biologist with a focus on integrating data science and machine learning approaches to study complex biological systems. My work is centered on computational genomics and protein analysis, particularly the prediction and classification of G protein coupled receptors (GPCRs) across multiple hierarchical levels. I have experience developing and integrating diverse computational methods, including homology-based approaches, classical machine learning models with engineered features, and more recent representation learning techniques.
In addition to methodological development, I have worked on building reproducible bioinformatics workflows and managing large-scale biological datasets. This includes experience with variant analysis pipelines, cloud-based environments, and containerized tools to ensure consistency across computing platforms. I am particularly interested in designing frameworks that combine multimodal data sources, such as genomic, clinical, and behavioral data, to better understand disease risk and progression.
More broadly, I am motivated by creating computational tools that are both robust and interpretable, with an emphasis on practical usability for researchers. I am also committed to training and collaborative work, especially in environments that support reproducible and scalable biomedical research.
