Use of a graph neural network to the weighted gene co-expression network analysis of Korean native cattle
In the general framework of the weighted gene co-expression network analysis (WGCNA), a hierarchical clustering algorithm is commonly used to module definition. However, hierarchical clustering depends strongly on the topological overlap measure. In other words, this algorithm may assign two genes with low topological overlap to different modules even though their expression patterns are similar. Here, a novel gene module clustering algorithm for WGCNA is proposed. We develop a gene module clustering network (gmcNet), which simultaneously addresses single-level expression and topological overlap measure. The proposed gmcNet includes a "co-expression pattern recognizer" (CEPR) and "module classifier". The CEPR incorporates expression features of single genes into the topological features of co-expressed ones. Given this CEPR-embedded feature, the module classifier computes module assignment probabilities. We validated gmcNet performance using 4,976 genes from 20 native Korean cattle. We observed that the CEPR generates more robust features than single-level expression or topological overlap measure. Given the CEPR-embedded feature, gmcNet achieved the best performance in terms of modularity (0.261) and the differentially expressed signal (27.739) compared with other clustering methods tested. Furthermore, gmcNet detected some interesting biological functionalities for carcass weight, backfat thickness, intramuscular fat, and beef tenderness of Korean native cattle. Therefore, gmcNet is a useful framework for WGCNA module clustering. Author summaryA graph neural network is a good alternative algorithm for WGCNA module clustering. Even though the graph-based learning methods have been widely applied in bioinformatics, most studies on WGCNA did not use graph neural network for module clustering. In addition, existing methods depend on topological overlap measure of gene pairs. This can degrade similarity of expression not only between modules, but also within module. On the other hand, the proposed gmcNet, which works similar to message-passing operation of graph neural network, simultaneously addresses single-level expression and topological overlap measure. We observed the higher performance of gmcNet comparing to existing methods for WGCNA module clustering. To adopt gmcNet as clustering algorithm of WGCNA, it remains future research issues to add noise filtering and optimal k search on gmcNet. This further research will extend our proposed method to be a useful module clustering algorithm in WGCNA. Furthermore, our findings will be of interest to computational biologists since the studies using graph neural networks to WGCNA are still rare.