Recently, a growing body of work has revealed the association between synonymous mutations (SMs) and many genetic diseases. The prioritization and identification of deleterious SMs is one of the most significant challenges in medical genomics. Ensemble learning approaches that combine the prediction results from multiple classification models achieved relative success for improving the prediction in many fields.

In this work, we provided a computational method, EnDSM, which is an accurate method based on the ensemble framework. Benchmarking results on the training and independent test datasets demonstrated that our ensemble model achieved better performance comparing with other state-of-the-art predictors.

EnDSM supports prediction of synonymous mutations in the GRCh37/hg19 assembly of the human genome.
Insert the list of synonymous mutations using the tab separated values format chr, pos, id, ref, alt (maximum 10,000 mutations for 5 column) Example

Please upload the VCF file

Learn more about output

EnDSM, the pre-computed score is available on here.

In this study, 39-dimensional features across four categories were investigated for model construction. The feature list is available on here.

Na Cheng, Huadong Wang, Xi Tang, Tao Zhang, Jie Gui, Chun-Hou Zheng and Junfeng Xia*, An Ensemble Framework for Improving the Prediction of Deleterious Synonymous Mutation, 20xx, doi:xx.
If you have any problem with the website, please contact Junfeng Xia: jfxia@ahu.edu.cn