Research Areas: Quantitative Systems Biology, Computational Materials Design, Applied Machine Learning, & Applied Evolutionary Dynamics
Research Areas: Quantitative Systems Biology, Computational Materials Design, Applied Machine Learning, & Applied Evolutionary Dynamics
Welcome to the Srivastava Lab website. Our group primarily focuses on using theoretical and computational methods in novel ways to model and engineer molecular systems, including chemical and biomolecular systems. Modeling approaches we use include traditional mechanistic modeling strategies, including the use of ordinary and partial differential equation-based modeling. Additionally, we use a fair amount of artificial intelligence and machine learning. We have a particular interest in symbolic regression. We also make extremely heavy use of evolutionary algorithms, such as genetic algorithms and genetic programming. Our group has a deep knowledge in areas such as systems biology and metabolic engineering. More recently, we have taken a number of the theoretical and computational frameworks we have developed started applying them towards predicting material properties. All of our efforts are supplemented by experiments carried out either by our lab or by our collaborators.
You can learn more about us at the aptly named about us page.
News
6/22/2020 - We've been fortunate to have been getting a lot of press about our work on COVID-19. There were two nice articles published in UConn Today here and here. Prof. Srivastava was also interviewed by a local NBC news affiliate.
4/14/2020 - Happy to be able to contribute to the effort in dealing with the COVID-19 pandemic. A nice article about our work can be found here.
3/04/2020 - Our recent paper on using machine learning to evaluate how pressure effects methane adsorption by MOFs was selected to be part of the The Journal of Physical Chemistry virtual special issue "Machine Learning in Physical Chemistry."