iDNA6mA-Rice: A Computational Tool for Detecting N6-Methyladenine Sites in Rice

Abstract

DNA N6-methyladenine (6mA) is a dominant DNA modification form and involved in many biological functions. The accurate genome-wide identification of 6mA sites may increase understanding of its biological functions. Experimental methods for 6mA detection in eukaryotes genome are laborious and expensive. Therefore, it is necessary to develop computational methods to identify 6mA sites on a genomic scale, especially for plant genomes. Based on this consideration, the study aims to develop a machine learning-based method of predicting 6mA sites in the rice genome. We initially used mono-nucleotide binary encoding to formulate positive and negative samples. Subsequently, the machine learning algorithm named Random Forest was utilized to perform the classification for identifying 6mA sites. Our proposed method could produce an area under the receiver operating characteristic curve of 0.964 with an overall accuracy of 0.917, as indicated by the fivefold cross-validation test. Furthermore, an independent dataset was established to assess the generalization ability of our method. Finally, an area under the receiver operating characteristic curve of 0.981 was obtained, suggesting that the proposed method had good performance of predicting 6mA sites in the rice genome. For the convenience of retrieving 6mA sites, on the basis of the computational method, we built a freely accessible web server named iDNA6mA-Rice at .

6mA-RicePred: A Method for Identifying DNA N6-Methyladenine Sites in the Rice Genome Based on Feature Fusion

“…This modification plays important roles in DNA mismatch repair, chromosome replication, cell defense, cell cycle regulation, and transcription . 6mA shows similar properties in eukaryotes and prokaryotes (Hao et al, 2019).…”

“…This algorithm can be understood as a unique representation of nucleotides and can be considered a one hot encoding algorithm. A random DNA sequence with m nucleotides can then be converted into a vector of 4 × m features (Hao et al, 2019;Chen et al, 2019c). The representation of nucleotides is not unique, and the representations of A, T, G, and C are interchangeable.…”

“…There are few computational methods to identify 6mA sites in the rice genome. Proposed methods include i6mA-Pred (Chen et al, 2019a), iDNA6mA-PseKNC (Feng et al, 2019a), MM-6mAPred (Pian et al, 2019), and iDNA6mA-Rice (Hao et al, 2019). i6mA-Pred uses nucleotide chemical property, nucleotide frequency, and SVM to identify 6ma sites.…”

Deep6mA: a deep learning framework for exploring similar patterns in DNA N6-methyladenine sites across different species

“…A benchmark dataset is important to build a reliable prediction model. In this study, for convenience, we use the 6mA-rice-Lv dataset (17,18), including 154,000 positive samples and 154,000 negative samples, to evaluate the proposed method and to compare it with other methods. For each positive sample obtained from GEO, the sequence is 41nt long with the 6mA site locating at the center.…”

“…Zhou et al (2018) found 265,290 of rice 6mA data through a variety of experimental methods, such as HPLC-MS/MS, 6mA immunoprecipitation sequencing and Single Molecule Real-Time (SMRT), which enables us to train complex models for 6mA identification. For example, Lv et al (2019) provided a new random forest model named iDNA6mA-rice based on the reconstructed 154,000 6mA data and 154,000 non-6ma data. iDNA6mA-rice is mainly realized by the random forest algorithm module (RF) based on three feature extraction techniques: K-tuple nucleotide frequency component, mono-nucleotide binary encoding and natural vector.…”