Performance Research of Clustering Methods for Detecting State Transition          Trajectories in Hemoglobin

Kei TAKAMI; Yukichi KITAMURA; Masataka NAGAOKA

doi:10.2477/jccj.2021-0014

Letters (Selected Paper)

Performance Research of Clustering Methods for Detecting State Transition Trajectories in Hemoglobin

Kei TAKAMI, Yukichi KITAMURA, Masataka NAGAOKA

Author information

Keywords: Keyword Time-series clustering method, Dynamic time warping distance, Silhouette analysis, Hemoglobin, Allostery regulation

JOURNAL FREE ACCESS FULL-TEXT HTML

2020 Volume 19 Issue 4 Pages 154-157

DOI https://doi.org/10.2477/jccj.2021-0014

Details

Abstract

The time-series clustering method is one of unsupervised machine learning techniques that classify time-series data. In this article, we applied three methods to the clustering analysis for 200 molecular dynamics (MD) trajectories of human adult hemoglobin (HbA), and have reported their clustering performances for detecting the T-R state transition trajectories (Traj_T-R). By compared with their silhouette indices, we have discussed the proper clustering conditions.

Fullsize Image

Corresponding author

Funder information

1.Fund name: Japan Society for the Promotion of Science (JSPS)

2.Fund name: Ministry of Education, Culture, Sports, Science and Technology

3.Fund name: Japan Science and Technology Agency

Register with J-STAGE for free!