Public Health Data Analytics Student

Duties

Summary

Make an impact while you learn. The Semester of Service Program offers students a volunteer project-based opportunity to support real Federal missions, gaining hands-on experience and career-ready skills. Students must be enrolled at least half-time in an accredited trade school, technical/vocational institute, junior college, college, university, or other accredited educational institution. With this project, you'll use data analytics and machine learning to advance food safety.

Requirements

Qualifications

Applicants will be considered based on their knowledge, skills or abilities related to project needs. Specifically, applicants should have experience working with data handling. and analyses, including proficiency in statistical coding languages such as Python. Applicants with experience using AI tools and machine learning approaches on large, complex databases are preferred, but not required.

PROJECT DESCRIPTION: Salmonella is a serious public health threat, causing nearly 1.3 million infections each year. While most Salmonella cause a mild illness, some are highly virulent, leading to severe illness, hospitalizations and death. Salmonella has accumulated important virulence factors (VFs) that allow them to colonize food animals, survive in harsh environments, and invade human cells. A key challenge is identifying which Salmonella is the most virulent, so we can focus our resources on those most likely to cause severe illnesses, thereby improving public health outcomes. FSIS and FDA test for Salmonella in multiple foods and use whole genome sequencing (WGS) for identification. Data are available for approximately 1million Salmonella isolates in the NIH-National Center for Biotechnology Information (NCBI) Pathogen Detection (PD) Isolate Brower database. Recently, a set of 70 Salmonella virulence genes were added to the NCBI-PD system and all submitted Salmonella isolates are screened for these genes upon submission. As of March 1, 2026, there are over 800,000 isolates with Salmonella VF data included in the PD, including samples from humans, animals, food, and environmental sources.