i4mC-ROSE, a bioinformatics tool for the identification of DNA N4-methylcytosine sites in the Rosaceae genome

Md Mehedi Hasan; Balachandran Manavalan; Mst Shamima Khatun; Hiroyuki Kurata

doi:10.1016/j.ijbiomac.2019.12.009

i4mC-ROSE, a bioinformatics tool for the identification of DNA N4-methylcytosine sites in the Rosaceae genome

Int J Biol Macromol. 2020 Aug 15:157:752-758. doi: 10.1016/j.ijbiomac.2019.12.009. Epub 2019 Dec 2.

Authors

Md Mehedi Hasan¹, Balachandran Manavalan², Mst Shamima Khatun³, Hiroyuki Kurata⁴

Affiliations

¹ Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Japan Society for the Promotion of Science, 5-3-1 Kojimachi, Chiyoda-ku, Tokyo 102-0083, Japan.
² Department of Physiology, Ajou University School of Medicine, Suwon 443380, Republic of Korea.
³ Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan.
⁴ Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan; Biomedical Informatics R&D Center, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan. Electronic address: kurata@bio.kyutech.ac.jp.

PMID: 31805335
DOI: 10.1016/j.ijbiomac.2019.12.009

Abstract

One of the most important epigenetic modifications is N4-methylcytosine, which regulates many biological processes including DNA replication and chromosome stability. Identification of N4-methylcytosine sites is pivotal to understand specific biological functions. Herein, we developed the first bioinformatics tool called i4mC-ROSE for identifying N4-methylcytosine sites in the genomes of Fragaria vesca and Rosa chinensis in the Rosaceae, which utilizes a random forest classifier with six encoding methods that cover various aspects of DNA sequence information. The i4mC-ROSE predictor achieves area under the curve scores of 0.883 and 0.889 for the two genomes during cross-validation. Moreover, the i4mC-ROSE outperforms other classifiers tested in this study when objectively evaluated on the independent datasets. The proposed i4mC-ROSE tool can serve users' demand for the prediction of 4mC sites in the Rosaceae genome. The i4mC-ROSE predictor and utilized datasets are publicly accessible at http://kurata14.bio.kyutech.ac.jp/i4mC-ROSE/.

Keywords: DNA methylation; Linear regression; Machine learning; N4-methylcytosine site; Sequence encoding.

MeSH terms

Algorithms
Computational Biology / methods*
Cytosine* / metabolism
DNA Methylation*
Databases, Genetic
Epigenesis, Genetic*
Epigenomics / methods*
Genome, Plant*
Machine Learning
ROC Curve
Reproducibility of Results
Rosaceae / genetics*
Web Browser

Substances

Cytosine