Pharmacogenomics Data Science Intern: Livestock Genomics

Zoetis, Inc; Kalamazoo (MI); Presencial; USD 44.000 - 55.000; Jornada completa

Descripción de la vacante

Zoetis, Inc. in Kalamazoo, MI, invites applications for a Pharmacogenomics Data Science & Genomic Prediction Intern. This role supports a dairy cattle pharmacogenomics project within PAH VMRD, mining health and genotype data, and defining treatment-response phenotypes for mastitis.

You will work with projection teams to develop proof-of-concept genomic prediction models and gain exposure to GWAS, mixed models, and ML approaches with strong mentorship and cross-functional collaboration.

Formación

• Enrolled in a Master’s or PhD program in Animal Science, Quantitative Genetics, Animal Breeding & Genomics, Bioinformatics, or related field.
• Experience with genomic data analysis, including GWAS and genomic prediction using mixed models.
• Proficiency in programming or statistics environments (R, Python, SAS) for large-scale data manipulation.

Responsabilidades

• Extract, clean, and integrate clinical treatment records from dairy herd management systems and link to genotype data.
• Define and construct treatment-response phenotypes for mastitis and bovine respiratory disease.
• Evaluate SNP panels and sequence data to identify DNA markers for treatment outcomes.
• Develop and test genomic prediction models (GBLUP, BayesR, or ML) and estimate accuracy and heritability.

Conocimientos

Genomic data analysis

Genomic prediction

GWAS

Mixed models

R

Python

SAS

Educación

Master's or PhD in Animal Science/Quantitative Genetics/Animal Breeding & Genomics/Bioinformatics

Herramientas

Dairy Comp 305

Descripción del empleo

Zoetis, Inc. in Kalamazoo, MI, invites applications for a Pharmacogenomics Data Science & Genomic Prediction Intern. This role supports a dairy cattle pharmacogenomics project within PAH VMRD, mining health and genotype data, and defining treatment-response phenotypes for mastitis.

You will work with projection teams to develop proof-of-concept genomic prediction models and gain exposure to GWAS, mixed models, and ML approaches with strong mentorship and cross-functional collaboration.