In many informational fields, such as biological, environmental, medical, etc., lots of sets of data are created every day. A flexible system biology tool enables to analysis the biology metabolize network in question with efficiency and accuracy. Our work gave a hybrid system based on the deep clustering algorithm, computing the co-regulated genes, also called regulons or co-regulation modules. The experiment results, based on the hypergeometric distribution function scores, showed that the model-based deep clustering (MBDC), was more efficient and accurate than other network functions as ISA, BIMAX, XMOTIFS, QUBIC and QUBIC2. The further study showed that MBDC was not only available in cancer analysis, but also in some bacteria study such as Escherichia coli. MBDC, extends the traditional functions, using both the similar expression patterns and the feedback subset-clusters as the features to identify all the subgroup genes based on the stresses. For each layer in the function, the main purpose is to find: argmax(min(#genes, #stresses))).
|Author||Yu Shang, Qiong Yu, Huansheng Cao, Guoqing Liu, Xiufeng Liu, Hao Wu, Yan Wang, Ying Xu|
|Maintainer||Yu Shang <[email protected]>|
|License||GPL (>= 2)|
|Package repository||View on GitHub|
Install the latest version of this package by entering the following in R:
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.