HN-CNN: A Heterogeneous Network Based on Convolutional Neural Network for m7 G Site Disease Association Prediction.

Lin Zhang,Hui Liu,Jiani Ma,Jin Chen

doi:10.3389/fgene.2021.655284

Lin Zhang, Hui Liu + Show 2 more

Open Access

https://doi.org/10.3389/fgene.2021.655284

Copy DOI

Abstract

N7-methylguanosine (m7G) is a typical positively charged RNA modification, playing a vital role in transcriptional regulation. m7G can affect the biological processes of mRNA and tRNA and has associations with multiple diseases including cancers. Wet-lab experiments are cost and time ineffective for the identification of disease-related m7G sites. Thus, a heterogeneous network method based on Convolutional Neural Networks (HN-CNN) has been proposed to predict unknown associations between m7G sites and diseases. HN-CNN constructs a heterogeneous network with m7G site similarity, disease similarity, and disease-associated m7G sites to formulate features for m7G site-disease pairs. Next, a convolutional neural network (CNN) obtains multidimensional and irrelevant features prominently. Finally, XGBoost is adopted to predict the association between m7G sites and diseases. The performance of HN-CNN is compared with Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), as well as Gradient Boosting Decision Tree (GBDT) through 10-fold cross-validation. The average AUC of HN-CNN is 0.827, which is superior to others.

Highlights

N7-methylguanosine (m7G) is one of the most abundant modifications present in tRNA, rRNA, and mRNA 5 cap and plays critical roles in regulating RNA processing, metabolism, and function (Malbec et al, 2019)
The internal m7G modification is dynamically regulated under both H2O2 and heat shock treatments, with remarkable accumulations in CDS and 3 UTR regions and functions in promoting mRNA translation efficiency (Malbec et al, 2019). m7G46 methylation of specific tRNA is associated with human mutation and the corresponding yeast mutation, which is m7G modification at position 46 in tRNA
Lin et al (2018) developed m7G methylated tRNA immunoprecipitation sequencing (MeRIP-seq) and tRNA reduction and cleavage sequencing (TRAC-seq) to conform that Mettl1-mediated tRNA m7G modification is essential for the proper expression of neural lineage genes. m7G methyltransferase complex METTL1/WDR4 causes primordial dwarfism and brain malformation

Summary

Introduction

N7-methylguanosine (m7G) is one of the most abundant modifications present in tRNA, rRNA, and mRNA 5 cap and plays critical roles in regulating RNA processing, metabolism, and function (Malbec et al, 2019). The internal m7G modification is dynamically regulated under both H2O2 and heat shock treatments, with remarkable accumulations in CDS and 3 UTR regions and functions in promoting mRNA translation efficiency (Malbec et al, 2019). M7G46 methylation of specific tRNA is associated with human mutation and the corresponding yeast mutation, which is m7G modification at position 46 in tRNA. Reduced m7G46 modification causes a growth deficiency phenotype in yeast, which provides a potential mechanism for primordial dwarfism associated with this lesion (Shaheen et al, 2015). M7G sites and human diseases may show associations (Enroth et al, 2019). The study of disease-associated m7G may reveal the pathogenesis of the disease

Methods

Results

Conclusion