k-Means NANI: an improved clustering algorithm for Molecular Dynamics simulations

• Published in: bioRxiv
• Main Authors: Chen, Lexin, Roe, Daniel R, Kochert, Matthew, Simmerling, Carlos, Miranda-Quintana, Ramón Alain
• Format: Journal Article Paper
• Language: English
• Published: United States Cold Spring Harbor Laboratory Press 08.03.2024
• Subjects: Clustering; Protein folding; Stochasticity; k-means; algorithms; clustering; protein folding; conformational analysis; molecular dynamics
• ISSN: 2692-8205; 2692-8205
• DOI: 10.1101/2024.03.07.583975

One of the key challenges of -means clustering is the seed selection or the initial centroid estimation since the clustering result depends heavily on this choice. Alternatives such as -means++ have mitigated this limitation by estimating the centroids using an empirical probability distribution. However, with high-dimensional and complex datasets such as those obtained from molecular simulation, -means++ fails to partition the data in an optimal manner. Furthermore, stochastic elements in all flavors of -means++ will lead to a lack of reproducibility. -means -Ary Natural Initiation (NANI) is presented as an alternative to tackle this challenge by using efficient -ary comparisons to both identify high-density regions in the data and select a diverse set of initial conformations. Centroids generated from NANI are not only representative of the data and different from one another, helping -means to partition the data accurately, but also deterministic, providing consistent cluster populations across replicates. From peptide and protein folding molecular simulations, NANI was able to create compact and well-separated clusters as well as accurately find the metastable states that agree with the literature. NANI can cluster diverse datasets and be used as a standalone tool or as part of our MDANCE clustering package.