[21p-D901-1~19] 12.6 Nanobiotechnology

6:30 PM - 6:45 PM JST(9:30 AM - 9:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[21p-D901-18] Improvement of parameter calculation for FMO-DPD for proteins by machine learning

〇Sota Matsuoka¹, Hideo Doi¹, Koji Okuwaki¹, Ryo Hatada¹, Sojiro Minami¹, Ryosuke Suhara¹, Yusuke Tachino¹, Yuji Mochizuki^1,2 (1.Rikkyo Univ., 2.Univ. Tokyo)

Keywords:

Machine Learning,FMO,DPD

Effective interaction parameters (χ) in dissipative particle dynamics (DPD) simulations can be calculated empirically using FCEWS (FMO-based Chi-parameter Evaluation Workflow System). However, FCEWS has significant usage costs, and reducing these costs is an important issue. Therefore, we attempted to improve the calculation of χ using machine learning, implementing an preprocessing system named pre_fcews. Presently, we have checked the prediction accuracy for Chignolin consisting of 10 amino acid residues.