Identifying DNA N4-methylcytosine (4mC) sites is 1 of great significance in biological research, such as chromatin 2 structure, DNA stability, DNA-protein interaction and controlling 3 gene expression. However, the traditional sequencing technology to 4 identify 4mC sites is very time-consuming. In order to detect 4mC 5 sites, we develop a multi-view learning method for achieving more 6 effectively via merging multiple feature spaces. Furthermore, we 7 think about whether the multi-view learning method can improve 8 the across species classification ability by fusing data of multiple 9 species. In our study, we propose a multi-view Laplacian kernel 10 sparse representation-based classifier, called MvLapKSRC-HSIC. 11 First, we make use of three feature extraction methods (PSTNP, 12 NCP, DPP) to extract the DNA sequence features. MvLapKSRC-13 HSIC uses a kernel sparse representation-based classifier with 14 graph regularization. In order to maintain the independence 15 between various views, we add a multi-view regularization term 16 constructed by Hilbert-Schmidt independence criterion (HSIC).17In the experiments, MvLapKSRC-HSIC is applied on six datasets, 18 so as to compare with other popular methods in single species 19 and cross-species experiments. All experimental results show that 20 MvLapKSRC-HSIC is superior to other outstanding methods on 21 both single species and cross-species. Importantly, MvLapKSRC-22 HSIC can identify a series of potential DNA 4mC sites, which 23 have not yet been experimentally evaluate on multiple species 24 and merit further research. 25 Impact Statement-As an important DNA modification, 4mC 26 plays an important role in DNA replication, expression and other 27 biological processes, so the detection of DNA 4mC sites has always 28 been a research hotspot. In view of the fact that previous studies 29 have neglected the importance of different prior knowledge may 30 be different, they have not chosen the appropriate methods to fuse 31 prior knowledge. Here, we propose a method to predict DNA 4mC 32 sites based on multi-view learning, which effectively integrates 33 different prior knowledge. On the six benchmark data sets, the