Project:	Testing feasibility of ML methods on various gene studies
Disciplines:	Data Science, Genomics
Mentor:	Ashish Mahabal, Deputy Director, Center for Data Driven Discovery, (PMA), aam@astro.caltech.edu, Phone: 6263954201
Mentor URL:	http://www.astro.caltech.edu/~aam  (opens in new window)
Background:	We are exploring data science methods to investigate the efficacy of different methods on a set of inter-lab studies involving flow cytometry data, microbial strain collection data, cell-line provenance, genome editing inter-lab studies, viral vector reference material etc. The original aims of these studies did not include machine learning, and they often do not have huge data volumes to do purely data-driven studies. Yet, the data are amenable to the use of machine learning.
Description:	The project will involve picking up one or two of the sub areas mentioned above (not all!) and testing the feasibility of ML methods, and if/how scalability will improve results.
References:	Flow cytometry: https://en.wikipedia.org/wiki/Flow_cytometry Viral vectors: https://en.wikipedia.org/wiki/Viral_vector Microbial strains: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4241729/ Cell line provenance: https://pubmed.ncbi.nlm.nih.gov/19003293/ Genome editing: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5131771/
Student Requirements:	Proficiency in python, jupyter notebooks (Google Colab), and git. Conversant with basics of machine learning and statistics, knowledge about linux/unix. Basic biology knowledge and interest in genetics will be a plus. Knowledge about deep learning, GPUs, AWS will also be a bonus. Knowledge of R/Shiny will be a plus.
Programs:	This AO can be done under the following programs:   Program    Available To        SURF    Caltech students only  Click on a program name for program info and application requirements.