[2N4-GS-10] AI application

[2N4-GS-10-01] Representation Learning of Protein Structural Dynamics by Time-structured VAE

Toward Extraction of Slow Dynamics

〇Tsuyoshi Ishizone¹, Yasuhiro Matsunaga², Sotaro Fuchigami³, Kazuyuki Nakamura¹ (1. Meiji University, 2. Saitama University, 3. Kyoto University)

Keywords:protein dynamics, variational auto-encoder, autocorrelation, representation learning, Markov state model

Protein structures constantly fluctuate, and dynamics specific to each time scale are known. In particular, time scales from microseconds to seconds are indispensable for obtaining a complete picture of structural dynamics. Several methods have been proposed to represent slow structural dynamics in low dimensions. However, the existing methods cannot capture such slow dynamics that rarely occur. We propose a method that introduces a prior distribution with high autocorrelation so that even rare slow changes can be emphasized. The proposed method can capture even rare slow dynamics in the representation space by promoting sample-wise autocorrelation. Applying the proposed method to simulated protein trajectories shows that the proposed method can represent slow structural dynamics.