@article{Ju2025, 
author = {Zhen Ju and Huiling Zhang and Jingjing Zhang and Wenhui Xi and Dian Huang and Shengzhong Feng and Jintao Meng and Yanjie Wei},
title = {A Comparative Study of Sequence Clustering Algorithms},
year = {2025},
journal = {Big Data Mining and Analytics},
volume = {8},
number = {5},
pages = {1011-1022},
keywords = {performance evaluation, scalability, protein sequence clustering, gene sequence clustering},
url = {https://www.sciopen.com/article/10.26599/BDMA.2025.9020010},
doi = {10.26599/BDMA.2025.9020010},
abstract = {Sequence clustering software is essential in bioinformatics. However, selecting the appropriate one can be challenging due to its diverse algorithms and targeted applications. This paper analyzes and evaluates eight representative softwares (algorithms) in terms of precision, sensitivity, speed, scale of running time, and memory consumption. Furthermore, this paper examines the effects of sequence count, sequence length, identity, thread count, and GPU on the above aspects. Sequence length and identity significantly impact clustering efficiency (speed and memory consumption), with fluctuation amplitudes exceeding an order of magnitude and non-monotonic effects observed. The evaluation results are analyzed and summarized in tables for users’ reference.}
}