Syngenta - Data Science Intern
Location: Durham, NC
Duration: June 2023 - December 2023
Summer Internship
Worked as a Data Science Intern at Syngenta. Team: Applied Genetics team and assisted Applied Scientists and Data Scientists in their respective Machine Learning, database management, and data visualization tasks.
Transformer Models for Protein Generation
Developed a proof of concept (PoC) using large language models (LLMs) to generate novel protein sequences by conditioning on functional or structural prompts, exploring applications in synthetic biology and protein design.
Clustering of Tomato Species
Implemented HDBSCAN clustering algorithm on 25000 by 25000 genomic similarity data, reduced dimensionality with t-SNE, and created 3D visualizations with Plotly.
Data Analytics & Automation
- Created live Tableau dashboards for reporting, and displaying KPIs to business stakeholders showing the status of various plants in 4 countries.
- Automated and optimized manual data pipeline for raw data processing with Smartsheet (excel) Python and SQL, decreasing processing speed by 55%.