"We study cancer, trying to understand how it originates and what makes it lethal. We use data arising from DNA & RNA sequencing, mass-spectrometry, clinical records and images. To analyze them, we develop and apply biostatistical and machine-learning approaches. We try to generate clinically-useful tools, while simultaneously discovering new areas of cancer biology.
The team is a multi-disciplinary group of computer scientists, software engineers, statisticians, biologists, chemists and clinicians. People come to the team with all levels of programming, of statistics and of cancer biology. We're used to training people in the areas they don't know, and have projects suited to all levels of experience.
For software-engineering focused students, typical projects will involve creating dev-ops infrastructure (e.g. CICD), optimizing high-performance code, containerizing software for cloud-based deployment or developing web-services.
For data-science-focused students, projects will involve optimizing ML-based workflows (e.g. hyper-parameter tuning), applied-ML on high-dimensional datasets, or developing new algorithms for quantifying specific features of cancer.
For biology-focused students, projects will involve pre-processing and analyzing high-throughput experimental data, and linking it to fundamental aspects of cancer biology like hypoxia or cell proliferation.
Recent publications from undergrad students in our team include:
Contact Email: firstname.lastname@example.org
CaSB Biological Data Sciences, N/A - no prior experience required. CS32: stacks, queues, lists, algorithm analysis, trees, graphs, searching, sorting, N/A - no prior experience required.
Hours Per Week:
10 or more, 20 or more
Python, R, C++
September 23, 2021