[16p-K402-1~15] 12.6 Nanobiotechnology

2:45 PM - 3:00 PM JST(5:45 AM - 6:00 AM UTC)

[16p-K402-7] Calculation of quantitative interaction energy from low-cost FMO calculations by machine learning – part 2

〇Ryohei Yoshine¹, Hideo Doi¹, Sota Matsuoka¹, Koji Okuwaki^1,2, Yuji Mochizuki^1,3 (1.Rikkyo Univ., 2.JSOL Corp., 3.Univ. Tokyo.)

Keywords:

Machine Learning,FMO

In recent years, dynamic and statistical interaction analysis considering fluctuations has been performed by combining MD and FMO, but the high computational cost is an issue. Therefore, we have been working on a project to reduce the computational cost by using machine learning to predict the interfragment interaction energy (IFIE) from FMO calculations with high-cost basis sets based on the results of FMO calculations with low-cost basis sets. In this presentation, we will report the results of predicting the interaction energies for the 6-31G* and cc-pVDZ basis sets, based on those of the 3-21G basis set.