RNA modifications play an important role in actively controlling recently created formation in cellular regulation mechanisms, which link them to gene expression and protein. The RNA modifications have numerous alterations, presenting broad glimpses of RNA's operations and character. The modification process by the TET enzyme oxidation is the crucial change associated with cytosine hydroxymethylation. The effect of CR is an alteration in specific biochemical ways of the organism, such as gene expression and epigenetic alterations. Traditional laboratory systems that identify 5-hydroxymethylcytosine (5hmC) samples are expensive and time-consuming compared to other methods. To address this challenge, the paper proposed XGB5hmC, a machine learning algorithm based on a robust gradient boosting algorithm (XGBoost), with different residue based formulation methods to identify 5hmC samples. Their results were amalgamated, and six different frequency residue based encoding features were fused to form a hybrid vector in order to enhance model discrimination capabilities. In addition, the proposed model incorporates SHAP (Shapley Additive Explanations) based feature selection to demonstrate model interpretability by highlighting the high contributory features. Among the applied machine learning algorithms, the XGBoost ensemble model using the tenfold cross-validation test achieved improved results than existing state-of-the-art models. Our model reported an accuracy of 89.97%, sensitivity of 87.78%, specificity of 94.45%, F1-score of 0.8934%, and MCC of 0.8764%. This study highlights the potential to provide valuable insights for enhancing medical assessment and treatment protocols, representing a significant advancement in RNA modification analysis.
MAIN CONCLUSION: The rice leaf mitochondrial DNA is more methylated compared to the rice grain mitochondrial DNA. The old rice leaf mitochondrial DNA has also a higher methylation level than the young rice leaf mitochondrial DNA. The presence of DNA methylation in rice organelles has not been well characterized. We have previously shown that cytosine methylation of chloroplast DNA is different between leaf and grain, and varies between young and old leaves in rice. However, the variation in cytosine methylation of mitochondrial DNA is still poorly characterized. In this study, we have investigated cytosine methylation of mitochondrial DNA in the rice grain and leaf. Based on CpG, CHG, and CHH methylation analyses, the leaf mitochondrial DNA was found to be more methylated compared to the grain mitochondrial DNA. The methylation of the leaf mitochondrial DNA was also higher in old compared to young leaves. Differences in methylation were observed at different cytosine positions of the mitochondrial DNA between grain and leaf, although there were also positions with a similar level of high methylation in all the tissues examined. The differentially methylated cytosine positions in rice mitochondrial DNA were observed mostly in the intergenic region and in some mitochondrial-specific genes involved in ATP production, transcription, and translation. The functional importance of cytosine methylation in the life cycle of rice mitochondria is still to be determined.
We applied an integrative approach using multiple methods to verify cytosine methylation in the chloroplast DNA of the multicellular brown alga Saccharina japonica. Cytosine DNA methylation is a heritable process which plays important roles in regulating development throughout the life cycle of an organism. Although methylation of nuclear DNA has been studied extensively, little is known about the state and role of DNA methylation in chloroplast genomes, especially in marine algae. Here, we have applied an integrated approach encompassing whole-genome bisulfite sequencing, methylated DNA immunoprecipitation, gene co-expression networks and photophysiological analyses to provide evidence for the role of chloroplast DNA methylation in a marine alga, the multicellular brown alga Saccharina japonica. Although the overall methylation level was relatively low in the chloroplast genome of S. japonica, gametophytes exhibited higher methylation levels than sporophytes. Gene-specific bisulfite-cloning sequencing provided additional evidence for the methylation of key photosynthetic genes. Many of them were highly expressed in sporophytes whereas genes involved in transcription, translation and biosynthesis were strongly expressed in gametophytes. Nucleus-encoded photosynthesis genes were co-expressed with their chloroplast-encoded counterparts potentially contributing to the higher photosynthetic performance in sporophytes compared to gametophytes where these co-expression networks were less pronounced. A nucleus-encoded DNA methyltransferase of the DNMT2 family is assumed to be responsible for the methylation of the chloroplast genome because it is predicted to possess a plastid transit peptide.