BIO Opportunities

Machine learning methods and web services for big genomics data analytics

by Mindy Shi

The biological data deluge thanks to recent advances in biotechnology, has fundamentally transformed life sciences and biomedical research into a data science frontier. To fully exploit big data in genomics and enable translation of genomic analytics to clinical practice, a number of machine learning methods have been developed toward predictive modeling. This project aims to evaluate widely used machine learning models, including those developed in the lab, for their performance in analyzing large scale genomic data. Students will work with graduate students, postdoctoral researchers and collaborators to develop web portals and conduct model evaluations on simulated and real genomic data. Experiences with web programming and scripting (i.e. Python) are required. Knowledge of statistical software (e.g. R) and machine learning is preferable.