Supplementary data for 'Comparison of sparse biclustering algorithms for gene expression datasets'

<strong>Motivation:</strong> Gene clustering and sample clustering are commonly used to find patterns in gene expression datasets. However, in heterogeneous samples (e.g. different tissues or disease states), genes may cluster differently. Biclustering algorithms aim to solve this issue by performing sample clustering and gene clustering simultaneously. Existing reviews of biclustering algorithms have yet to include a number of more recent algorithms and have based comparisons on simplistic simulated datasets without specific evaluation of biclusters in real datasets, using less robust metrics. <br> <strong>Results:</strong> In this study we compared four classes of sparse biclustering algorithms on a range of simulated and real datasets. In particular we use a knockout mouse RNA-seq dataset to evaluate each algorithm’s ability to simultaneously cluster genes and cluster samples. We found that Bayesian algorithms with strict sparsity constraints had high accuracy on the simulated datasets and didn't require any post-processing, but were considerably slower than other algorithm classes. We assessed whether non-negative matrix factorisation algorithms can be repurposed for biclustering and found that, although the raw output was poor, after using a sparsity-inducing post-processing procedure we introduce, one such algorithm was one of the most highly ranked on real datasets. We also exhibit the limitations of biclustering algorithms by varying the complexity of simulated datasets. The algorithms generally struggled on simulated datasets with a large number of implanted factors, or with a large number of genes. In real datasets, the algorithms rarely returned clusters containing samples from multiple tissues, which highlights the need for further thought in the design and analysis of multi-tissue studies to avoid differences between tissues dominating the analysis. <br> Code to run the analysis is available at https://github.com/nichollskc/biclust_comp, including wrappers for each algorithm, implementations of evaluation metrics, and code to simulate datasets and perform pre- and post-processing.**研究动机：** 基因聚类与样本聚类是挖掘基因表达数据集内在模式的经典手段。但在异质性样本（如不同组织或疾病状态样本）中，基因的聚类模式往往存在差异。双聚类（biclustering）算法旨在通过同时完成样本聚类与基因聚类来解决这一问题。现有双聚类算法综述尚未覆盖大量近年提出的新算法，且其对比实验仅基于简单的模拟数据集，未针对真实数据集的双聚类结果开展专门评估，所采用的评估指标鲁棒性不足。 **研究结果：** 本研究针对四类稀疏双聚类算法，在多组模拟数据集与真实数据集上完成了对比实验。特别地，我们使用基因敲除小鼠（knockout mouse）RNA测序（RNA-seq）数据集，评估各算法同时实现基因聚类与样本聚类的能力。实验结果显示，带有严格稀疏性约束的贝叶斯算法在模拟数据集上准确率较高，且无需额外后处理步骤，但运行速度显著慢于其他类别算法。我们还探究了非负矩阵分解（non-negative matrix factorisation, NMF）算法能否被重新适配至双聚类任务，结果表明，尽管其原始输出效果欠佳，但在应用我们提出的稀疏性诱导后处理流程后，其中一款算法在真实数据集上的表现跻身前列。此外，我们通过调整模拟数据集的复杂程度，展示了双聚类算法的性能局限：当模拟数据集包含大量预设聚类特征或基因数量较多时，各类算法普遍表现不佳。在真实数据集场景中，算法几乎无法返回包含多组织样本的聚类结果，这凸显了在多组织研究的设计与分析阶段需进一步优化，以避免组织间差异主导整个分析过程。 本研究的分析代码已开源至https://github.com/nichollskc/biclust_comp，其中包含各算法的封装脚本、评估指标的实现代码，以及用于模拟数据集生成、预处理与后处理的相关代码。