Abstract: One of the important tools for analyzing gene expression data is biclustering method. It focuses on finding a subset of genes and a subset of experimental conditions that together exhibit coherent behavior. However, biclustering is a multiple objective local search algorithm. When dealing with gene expression data, the results fall into local optimal area very easily. To overcome this defect and improve the global search ability of the algorithm, this paper proposes a diversity optional quantum particle swarm biclustering algorithm （Diversify - Optional QPSO, DOQPSO）. Firstly, algorithm uses DOQPSO to process genetic data, and then uses the improved greedy iterative FLOC to search for biclustering, in order to achieve the more ideal results. Comparing with FLOC and QPSO, the experimental results show that DOQPSO biclustering algorithm has better global convergence ability, and better clustering effect.

Key words: biclustering, gene expression, Quantum-behaved Particle Swarm Optimization（QPSO）, diversified options, Flexible Overlapped Biclustering（FLOC）

摘要： 双向聚类已成为分析基因表达数据的一种重要工具，可以同时从基因和条件两个方向寻找具有相同表达波动的簇。但双向聚类是一种多目标优化的局部搜索算法，处理繁杂的基因数据时容易陷入局部最优。为提高算法的全局搜索能力，提出了一种多样性选择的量子粒子群双向聚类算法（Diversify-Optional QPSO，DOQPSO）。算法首先采用DOQPSO处理基因数据，然后用改进的FLOC算法进行贪心迭代寻找双向聚类，以求得更为理想的结果。算法通过实验仿真，并与FLOC算法和QPSO算法进行比较，结果证明DOQPSO双向聚类算法具有更好的全局寻优能力，且聚类效果更佳。

关键词: 双向聚类, 基因表达数据, 量子粒子群算法, 多样性选择, FLOC算法