2-O-methylation (2OM) is a vital post-transcriptional modification which is formed by a functional group through the attachment of a methyl (-CH3) group to the second position of an aromatic ring hydroxyl group (-OH). It plays an active part in RNA physical configuration stability and the way different RNA molecules interrelate. Further, this modification plays a pivotal role in changing the epigenetic regulation of cellular processes. Previous approaches like mass spectrometry could not fully enhance the identification of RNA-modified sites. Sequence data were useful in the development of measures that meant the use of computationally intelligent system to identify 2OM sites quickly. This research proposed a new novel method of feature extraction and generation from the available sequences, and the feature dimensionality reduction has been done through the incorporation of statistical moments. The final feature vectors were developed and used to train prediction models. The assessment of prediction models was carried out through independent set tests and k-fold cross-validation. Through rigorous testing, the bagging ensemble model outperformed and revealed optimal accuracy scores. A publicly accessible web-based application has been developed which can be accessed via https://2om-pred-webapp.streamlit.app/.

MOTIVATION: 5-Methylcytosine (m5c), a modified cytosine base, arises from adding a methyl group at the 5th carbon position. This modification is a prevalent form of post-transcriptional modification (PTM) found in various types of RNA. Traditional laboratory techniques often fail to provide rapid and accurate identification of m5c sites. However, with the growing accessibility of sequence data, expanding computational models offers a more efficient and reliable approach to m5c site detection. This research focused on creating advanced in-silico methods using ensemble learning techniques. The encoded data was processed through ensemble models, including bagging and boosting techniques. These models were then rigorously evaluated through independent testing and 10-fold cross-validation. RESULTS: Among the models tested, the Bagging ensemble-based predictor, m5C-iEnsem, demonstrated superior performance to existing m5c prediction tools. AVAILABILITY AND IMPLEMENTATION: To further support the research community, m5c-iEnsem has been made available via a user-friendly web server at https://m5c-iensem.streamlit.app/.