Developed ML models (Python: scikit-learn, NumPy, Pandas) for bacteria-phage interaction prediction and E. coli host assignment. Built and optimized Nextflow-based pipelines containerized with Docker/Singularity for large-scale genomic data processing, automating model training, validation, and testing, with Git for version control. Worked with HPC clusters and cloud computing (Google Collaborative Cloud, CLIMB) for scalable workflows. Applied feature engineering & statistical modelling of high-dimensional biological data to extract key insights on E. coli & phage phylogeny, antimicrobial resistance (AMR), and deconvolute host specificity. Utilized R for analysis & visualization, ensuring output interpretability and actionable insights. Developed a Flask-based intranet web app for automated sequence analysis and integrated ML models into a government food surveillance data platform. Presented research at international conferences (talks & posters) and led industry-focused ML workshops to bridge research with real-world applications.

Developed host attribution models for Salmonella Typhimurium using machine learning, enabling accurate prediction of pathogen origins. Designed benchmarking frameworks to systematically compare ML-based attribution models against traditional epidemiological and genomic methods. Explored different data representations by testing ML models on varied biological data types (e.g., SNPs, k-mers, gene presence/absence) and their combinations to determine optimal predictive strategies. Built a generalizable framework for pathogen host prediction, laying the foundation for later work on E. coli and phage models. Conducted bioinformatics analyses to extract meaningful features from large-scale genomic datasets, integrating sequencing data with ML approaches. Gained expertise in machine learning methodologies, including feature selection, model evaluation, and interpretability techniques, while applying best practices for reproducibility and scalability. Presented research at national and international conferences and led bioinformatics workshops for lab members to help learn & apply bioinformatics tools to their projects.

Unpaid Intership Assistant to owner: Perform basic blood tests Prepare blood and urine samples for further biochemical analysis Key Skills: Follow procedure, Operate relatively complex machinery, Attention to detail, Customer service.