Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Mar 4:12:655284.
doi: 10.3389/fgene.2021.655284. eCollection 2021.

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

Lin Zhang  1   2 , Jin Chen  2 , Jiani Ma  2 , Hui Liu  1   2
Affiliations

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

Lin Zhang et al. Front Genet. .

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.

Keywords: XGBoost; convolutional neural network; diseases; heterogeneous network; m7G sites.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

FIGURE 1
FIGURE 1
Framework of HN-CNN. “Feature Vector Construction” is a heterogeneous network based on feature extraction, which is constructed with similarities and known m7G-disease association. “Feature Extraction Based on CNN” is a CNN-based feature extraction followed by XGBoost. In “XGBoost Classifier,” XGBoost predicts the candidate samples, which chooses the regression classification tree as a base learner.
FIGURE 2
FIGURE 2
Heterogeneous network and feature pair. (A) The heterogeneous network. (B) The demo of s5 and d2. (C) The related matrixes directly.
FIGURE 3
FIGURE 3
The AUCs of HN-CNN and other methods. (A) The AUCs of base classifiers with/without CNN. (B) The AUCs of HN-CNN and base classifiers with CNN.
See this image and copyright information in PMC

References

    1. Bradrick S. S. (2017). Causes and consequences of flavivirus RNA methylation. Front. Microbiol. 8:2374. 10.3389/fmicb.2017.02374 - DOI - PMC - PubMed
    1. Cadieux-Dion M., Andermann E., Lachance-Touchette P., Ansorge O., Meloche C., Barnabe A., et al. (2013). Recurrent mutations in DNAJC5 cause autosomal dominant Kufs disease. Clin. Genet. 83 571–575. 10.1111/cge.12020 - DOI - PubMed
    1. Calvo S. E., Tucker E. J., Compton A. G., Kirby D. M., Crawford G., Burtt N. P., et al. (2010). High-throughput, pooled sequencing identifies mutations in NUBPL and FOXRED1 in human complex I deficiency. Nat. Genet. 42 851–858. 10.1038/ng.659 - DOI - PMC - PubMed
    1. Chance P. F., Cavalier L., Satran D., Pellegrino J. E., Koenig M., Dobyns W. B. (1999). Clinical nosologic and genetic aspects of Joubert and related <KEYWORDS> syndromes. J. Child Neurol. 14 660–666. 10.1177/088307389901401007 - DOI - PubMed
    1. Chang C. C., Lin C. J. (2011). LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2:27. 10.1145/1961189.1961199 - DOI

LinkOut - more resources