Cooperative, Translational Data Sciences

Company Description

At Biogen, our mission is clear - we are pioneers in neuroscience. Biogen discovers, develops, and delivers worldwide innovative therapies for people living with severe neurological and neurodegenerative diseases. Together, our employees create, commercialize, and manufacture transformative therapies for our patient population.

We at Biogen are committed to building on our culture of inclusion and belonging that reflects the communities in which we operate and the patients who we serve. We are focused on strengthening our foundation to advance our overall Diversity, Equity, and Inclusion (DE&I) strategy and, most importantly, ensuring all our employees feel included.

As an intern or co-op at Biogen, you can anticipate being assigned to a real project, under the guidance of seasoned professionals and subject matter experts who are invested in your career and academic growth. We also ensure that you have ample opportunities to expand your network, learn more about our organization through weekly lunch and learns led by leaders from across the company, and join us for several enjoyable events.

Job Description

Summary

This application is for a 6-month student role from January - June 2024. Resume reviews will start in October 2023.

Our team is Translational Data Sciences. Our goal is to perform high-quality computational analysis on genomics/transcriptomics datasets, standardize NGS data analysis pipelines, and work on cutting-edge computational tools and technologies. We work closely with all discovery teams to perform computational analysis of NGS datasets. These include analysis of DNAseq RNAseq, miRNAseq, snRNAseq to perform target identification, engagement, and assessment.

Position Description

As a co-op, you will:

• Apply cutting-edge deep learning models, such as transformers, for cell type annotation in single-cell RNA-seq data.
• Become familiar with the Biogen servers and datasets.
• Write code in Python/bash to perform tasks.
• Process publicly available scRNAseq datasets using our internal single cell pipeline.
• Attend scheduled team bi-weekly meetings.
• Provide bi-weekly progress updates.

Potential projects may include:

• Explore and implement deep learning models for cell type annotation in single-cell RNAseq data. Current annotation methods struggle with limited marker gene lists and batch effect handling, hindering generalization.
• scBERT, a large-scale transformer model offers advantages: 1) It can learn complex representations from the data without heuristic feature engineering in an unsupervised manner. 2) It can leverage pre-trained models on large datasets and fine-tune with labeled reference data. 3) It can be continually updated for dynamic adaption to new data and knowledge.
• In addition to cell type annotation, the transformer framework can be expanded to a variety of other tasks such as multiomics data integration, analysis of gene-gene interactions, and perturbation response prediction.

Qualifications

• Experience with AI/machine learning methods development or application in biological sciences.
• Experience with computational analysis of single-cell RNA-seq.
• Coding experience in Python, Bash, R, and data visualization tools.

To participate in the Biogen Internship Program, students must meet the following eligibility criteria:

• Legal authorization to work in the U.S.
• Must be at least 18 years of age prior to the scheduled start date.
• Must be currently enrolled in an accredited college or university.

Education

Currently pursuing a PhD in computational biology or a related field.

Additional Information