A kernel-based intuitionistic weight fuzzy k-modes algorithm (KIWFKM) is proposed in this paper which can improve the clustering performance of categorical data. The current FKM algorithm which were proposed by researchers generally have three drawbacks. Firstly, the algorithms were easily limited to the local optimal solution. Secondly, most of algorithms were considering all attributes equally. Thirdly, most algorithms are sensitive to noise data points. So the intuitionistic fuzzy sets (IFS), kernel trick and weight concept are introduced into the objective function which can not only solve the problem of all attributes equally but also improve the robustness to noise. In addition, a coupled DCP (chained tissue-like P system combines DNA genetic rules) system is established which is used for realizing the KIWFKM algorithm (KIWFKM-DCP). The uncertainty and implicit parallelism of the DCP system can help the KIWFKM algorithm jump out of the local optimal solution and find better solution. Finally, we conduct experiments and compare experiment results with six state-of-the-art clustering methods. Experimental results conduct that the KIWFKM-DCP algorithm perform better than the other comparison clustering algorithms.