Bioinformatics and nutrition scientist with expertise in DNA methylation, epigenetics, and computational biology. Proficient in R, Python, and machine learning. Strong background in omics data analysis and high-performance computing. Committed to leveraging data-driven insights for advancements in biotech, pharma, and precision medicine. Skilled in research methodologies and passionate about scientific discovery. Demonstrates proficiency in data analysis and laboratory techniques, with the ability to quickly acquire new skills. Excited to apply and further develop analytical and technical skills.
Master's Thesis: Effect of Balanced Energy-Protein supplementation during pregnancy and breastfeeding on infants DNA Methylation profile - MISAME III RCT, 05/25
Investigating the impact of Balanced Energy-Protein supplementation during pregnancy on infant DNA methylation using data from the WHO International Agency for research on Cancer (IARC) Epigenomics group under an approved collaboration.
Developed MICEify, a custom imputation tool, for chromosome-specific MICE imputation.
Analyze Illumina Epic 850k array data and identified epigenetic patterns linked to maternal nutrition.
Developed an image recognition system using Swin Transformer in PyTorch for plant disease detection.
Achieved 97.89% F1-score across four leaf conditions with a mean confidence of 0.9969.
Demonstrated the adaptability of deep learning from plant phenotyping to potential biomedical imaging applications.
Designed an ML pipeline to predict repair outcomes after CRISPR-Cas9 genome edits.
Engineered feature extraction for nucleotide patterns and cut-site contexts.
Utilized LightGBM with bagging, achieving R² = 0.55 for insertion predictions.
Showcased strong ensemble learning techniques for genomic data analysis.