AUTHOR=Zhao Jiaojiao , Jiang Haoqiang , Zou Guoyang , Lin Qian , Wang Qiang , Liu Jia , Ma Leina 

TITLE=CNNArginineMe: A CNN structure for training models for predicting arginine methylation sites based on the One-Hot encoding of peptide sequence

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.1036862

DOI=10.3389/fgene.2022.1036862

ISSN=1664-8021

ABSTRACT=Methylation is one of the most prominent post-translational modifications on proteins, and protein arginine methylation plays a critical role in numerous cellular processes and regulates many critical cellular functions. Though several model-based arginine methylation site predictors have been reported， the model needs further optimization. In this paper, we propose an approach based on deep learning to predict arginine methylation sites and compare it with other models based on machine learning. Importantly, in side-by-side comparisons with other machines learning arginine methylation site predictors, the deep learning method performs on par or better in AUC (Sn (Sp=0.9) Sn (Sp=0.95)) scoring metrics tested. We obtained 10,923 proteins through model prediction and performed Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis of related genes. In the KEGG analysis, it was found that the arginine methylated protein was significantly enriched in the ALS pathway. CNNArginineMe is freely available at https://github.com/guoyangzou/DeepRme.