The Computational Biology and Translation (CBT) Department within Genentech is to use computational approaches spanning from data analytics to the development of new algorithms to identify biological processes affected in human disease and to advance next-generation therapeutics. We work collaboratively across disciplines both within the divisions and also with collaborating labs in Research Biology.
As part of a collaboration between the departments of Bioinformatics and AI/ML within CBT, we are searching for a motivated Summer Intern to work on the visualization of outputs from ML models of regulatory DNA (including attention, ISM, and gradient x input) and to explore how these outputs might be used to better interpret non-coding variants in Genome Wide Association Studies. The candidate will work as part of a team of Summer Interns furthering our efforts to use Machine Learning to better understand the function of the non-coding, regulatory genome and to design synthetic regulatory elements that can be used to advance programs in gene and cell therapy.
This internship is located on-site in South San Francisco, CA
Key responsibilities
- Work directly with research software engineers to develop functional genomics visualization methods compatible with ML models of regulatory sequence
- Train/finetune regulatory models on disease relevant genomics data (primarily single-cell ATAC-seq)
- Contextualize and predict the impact of non-coding variation using ML models
- Participate in talks, journal clubs, and general research laboratory activities
Required education
- Pursuing an undergraduate degree or PhD in Bioengineering, Biochemistry, Molecular Biology or related fields
- Will have completed at least two years of undergraduate coursework at an accredited college/university.
Required skills
- Proficiency in Python and experience with frameworks for Machine Learning inference (e.g. pytorch, lightning)
- Familiarity with fundamental ML concepts and interpretation techniques such as transformers, saliency maps
- Experience with popular Regulatory Genomics models such as "BPnet, Enformer, Borzoi, DeepMEL"
- Previous educational exposure to basic concepts in cell biology and gene expression
- Experience developing interactive Data Visualizations in JavaScript or web based visualization technologies (e.g. d3js or webgl) preferred.
- Knowledge of webGPU is preferred
The expected salary range for this position based on the primary location of San Francisco, CA is $50/hr. Actual pay will be determined based on experience, qualifications, geographic location, and other job-related factors permitted by law. This position also qualifies for paid holiday time off benefits.
#GNE-R&D-Interns-2024
Genentech is an equal opportunity employer, and we embrace the increasingly diverse world around us. Genentech prohibits unlawful discrimination based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin or ancestry, age, disability, marital status and veteran status.