Computational Chemistry and Modeling Methods

Using data mining and machine learning to enhance computational modeling of enzymatic reactions.

Dr. Qianyi Cheng, assistant professor in the Chemistry Department, has received the Maximizing Investigators' Research Award (MIRA) from NIH National Institute of General Medical Science (NIGMS) for the project “Data Mining and Machine Learning Guided QM/MM and QM-Cluster Modeling of Enzymatic Reactions”. The goal of MIRA is to increase the efficiency of NIGMS funding by providing investigators with greater stability and flexibility, thereby enhancing scientific productivity and the chances for important breakthroughs. In this project, Dr. Cheng and her team will utilize Data Mining (DM) and machine learning (ML) techniques to enhance computational modeling of enzymatic reactions.

Computational chemistry and modeling methods have revolutionized protein structure prediction, drug discovery, and enzyme bioengineering, offering crucial insights into enzymatic reactions and functions at the atomic level. To consistently achieve high throughput and accuracy, methodological best practices are essential, particularly in QM/MM and QM-cluster enzyme modeling. These practices require a deep understanding of biochemical reactions, protein structures, and available computational methods and resources, with effective information extraction and comprehension being key to project success.

With the rapid advancement of large language models (LLMs) and machine learning (ML), Cheng and her team can significantly enhance the ability to extract insights from existing publications. This approach has the potential to expedite the establishment of modeling protocols. By harnessing LLM and ML techniques, the team will develop tools to automatically construct computational modeling protocols, facilitating exploration in biochemical mechanisms, enzymatic reactions, and enzyme/protein engineering.

For more information on this project, contact Cheng at qcheng1@memphis.edu.