Job Description

Are you a student currently pursuing a Bachelor's or Master's degree in Biology, Bioinformatics, Data Science, or related majors who wants to make a difference by transforming medicine and improving human health? The Cancer Data Science (CDS) group at the Broad Institute is looking for passionate students to help us accelerate cancer research with data-driven innovation and machine learning. Situated in the Broad's Cancer Program, we design experiments, interpret the results, and present them to the public. Along the way, we develop new statistical tools and machine learning methods, write papers, produce datasets that are used by tens of thousands of researchers around the world, and help guide research and development for applying new technologies to cancer research.

We are looking for co-ops to work on projects such as:

• Identifying metabolic dependencies: CDS works closely with the Cancer Dependency Map () to produce whole genome CRISPR screens in immortalized cancer cell lines and share the results with the global scientific community. Using this resource, cancer researchers can find promising gene targets for new cancer treatments. However, cancer cells in a plastic dish with media pumped full of nutrients to encourage growth might be very different from cancer cells in the human body. The goal of this project is to identify genes that are related to media conditions. This can both save researchers valuable time and effort, as well as reveal new cell biology. In this position, you would explore and analyze our CRISPR data to understand how media is biasing our experiments, then develop statistical and machine learning methods to identify and annotate potential media-related genes.

• Measuring the epithelial to mesenchymal transition in cancer cell lines: The epithelial to mesenchymal transition (EMT) is an important process in cancer progression, enabling cancers to invade surrounding tissue and potentially develop drug resistance. Understanding the spectrum of EMT states in cancer cell line models is critical to discovering and interpreting biomarkers of genetic and drug dependency. The goal of this project is to produce a reliable and clinically relevant measure of EMT from gene expression data. In this position, you would perform exploratory data analysis to identify a strategy for evaluating EMT state, then apply it to important problems in cancer biology using CRISPR data, bulk RNASeq, and single cell RNASeq..

Our ideal candidate will:

• Be proficient in coding (python or R preferred, experienced with pandas, numpy, and/or tidyverse).

• Have some knowledge of data science topics such as probability, statistics and machine learning.

• Possess the ability to engage with and solve unfamiliar problems.

• Have a high level of scientific curiosity.

• Consider themselves a team player and strong communicator.

• Has the ability to work full-time for 4-6 months starting July or August 2024.

Note that while having a background in biology is a plus, it is not required for this role.You will learn the basics of cancer biology through these projects.

More about us:

• We're a nonprofit with our roots in academia, but our work scales to meet the demands of both big tech and our research communities.

• We emphasize transparency, diversity, equity, growth, and work-life balance.

• We're mission-driven - our goal is the advancement of science, and we'd like to think that philosophy drives our collaborative environment.

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status.