Data science techniques in biomolecular force field development

Recent advances in data science are impacting the develop-ment of classical force fields. Here we review some ideas and techniques from data science that have been used in force field development, including database construction, atom typing, and machine learning potentials. We highlight how new tools such as active learning and automatic differentiation are facilitating the generation of target data and the direct fitting with macroscopic observables. Philosophical changes on how force field models should be built and used are also discussed. It's inspiring that more accurate biomolecular force fields can be developed with the aid of data science techniques.

Automated summary

Recent advances in data science have influenced the development of classical force fields. This review examines the use of data science techniques such as database construction, atom typing, and machine learning potentials in force field development. It highlights the effectiveness of new tools like active learning and automatic differentiation in generating target data and fitting with macroscopic observables. The article also discusses philosophical changes in the construction and usage of force field models. It emphasizes the potential for developing more accurate biomolecular force fields using data science techniques.