High throughput predictive bioenergetics through statistical machine learning for big-data to assess biological responses to environmental stressors
PI: Jayasundara Nishad (Marine Science, UMaine)
Sector: Biology, Data Science
Partners: UMaine
Abstract: The goal of this research is to build a team of undergraduates to integrate biological sciences with big-data statistical approaches to develop a commercializable statistical tool that can predictively compute the capacity of an organism to maintain energy homeostasis when exposed to toxicants and other stressors (e.g., temperature). Once developed, the tool can be used as a predictive toxicity screening method, a critical need as highlighted by the US national toxicology program, especially in their grant solicitations. Undergraduates trained through this project will get direct hands-on experience in method development and experimental design in metabolic research, and big-data analytical methods. These will directly contribute to their further training as scientists and will significantly improve their analytical skills on big-data, a highly sought after attribute in the current job market.