School of Computing, Clemson University, Clemson, SC, USA.
Proteomics. 2011 Oct;11(19):3845-52. doi: 10.1002/pmic.201100180. Epub 2011 Aug 23.
Identification of genes and pathways involved in diseases and physiological conditions is a major task in systems biology. In this study, we developed a novel non-parameter Ising model to integrate protein-protein interaction network and microarray data for identifying differentially expressed (DE) genes. We also proposed a simulated annealing algorithm to find the optimal configuration of the Ising model. The Ising model was applied to two breast cancer microarray data sets. The results showed that more cancer-related DE sub-networks and genes were identified by the Ising model than those by the Markov random field model. Furthermore, cross-validation experiments showed that DE genes identified by Ising model can improve classification performance compared with DE genes identified by Markov random field model.
鉴定与疾病和生理状况相关的基因和途径是系统生物学的主要任务。在这项研究中，我们开发了一种新的非参数伊辛模型，用于整合蛋白质-蛋白质相互作用网络和微阵列数据，以鉴定差异表达（DE）基因。我们还提出了一种模拟退火算法来找到伊辛模型的最佳配置。伊辛模型应用于两个乳腺癌微阵列数据集。结果表明，伊辛模型比马尔可夫随机场模型鉴定出更多与癌症相关的 DE 亚网络和基因。此外，交叉验证实验表明，伊辛模型鉴定的 DE 基因可以提高分类性能，而不是马尔可夫随机场模型鉴定的 DE 基因。
