The web-server pSuc-Lys used to predict the lysine succinylation in protein. In this study,a new model is proposed for lysine succinylation prediction. Based on a vectorized sequence-coupling model, a protein could be converted to a feature vector.An ensemble learning framework was proposed. The downsampling on negative techiques was used to balance the training dataset. The random forests algorithm was adopted to conduct prediction using each descriptor features and the final result was gotten by integrating all the random forests results via voting.