Single-cell RNA-seq (scRNA-seq) offers an unprecedented opportunity to study cancer biology. Cell-type annotation is one of the most critical steps in the analysis workflow. However many challenges remain to be addressed.
The intern is responsible for developing a set of scRNA-seq cell-type annotation methods with explainable machine learning models that are highly accurate at multiple granular levels. The intern will implement, improve, and benchmark a novel method and compare its performance with established annotation methods. The expected deliverable of this internship project is a scRNA-seq cell-type annotation method package that not only offers superior accuracy in annotating cell subpopulations but also provides biologically relevant explanations for the prediction.
We are seeking an intern with a background of Computer Science, Computer Engineering, Bioinformatics, Data Science, Statistics, Biostatistics or other related disciplines with an excellent teamwork spirit and communication skills. The successful candidate must meet the following requirements:
- BSc, MSc, or Ph.D. degree in progress
- Sophomore and above year in college
- Minimum GPA 3.0
And will demonstrate the following skills and experience:
- Fluent with R and Python programming language
- Expertise in machine learning theories and algorithms
- Candidates who are fluent with high-throughput sequencing data analysis workflows (WGS, RNA-seq, scRNA-seq), immunology, and oncology are preferred.