1 - 16 of 16 results

SRAMP / Sequence-based RNA Adenosine Methylation site Predictor

A mammalian m6A sites predictor. SRAMP achieves promising performance both in cross-validation tests on its training dataset, and in the rigorous independent tests. Another highlighting trait of this predictor is that only RNA sequences are required when running a prediction and no external -omics data are loaded. With either kind of input sequence, SRAMP achieves competitive performance in both cross-validation tests and rigorous independent benchmarking tests. SRAMP serves as a useful tool to predict m6A modification sites on the RNA sequences of interests.


Identifies N6-methyladenosine (m6A) modification. RNA-MethylPred uses Bi-profile Bayes, dinucleotides composition, and k nearest neighbor (KNN) scores to incorporate it in three feature extractions. It achieved a Matthew’s correlation coefficient (MCC) of 0.29 in a jack-knife test. The tool helps to underling exact molecular mechanisms in physiological and pathological processes. It can differentiate more difficult N6-methyladenosine sites that cannot be readily detected by other m6A predictors.

CAn / CoverageAnalyzer

Allows the visualization and assisted inspection of deep sequencing data in the search for RNA modifications. CAn allows the definition of a highly detailed query, based on combinations of arrest rates and mismatch composition, as well as a Context Sensitive Arrest rate (CSA). A differential visualization tool is particularly useful to compare signatures upon differential chemical treatment, or between wild-type and knockout mutants e.g., of a methyltransferase. CAn combines a data processing pipeline with flexible controls for independent or differential visualization and automated screening for modification candidates based on complex reverse transcription signatures.

iRNAm5C-PseDNC / identify RNA 5-methylcytosine modification sites Pseudo DiNucleotide Composition

Predicts the identifying RNA 5-methylcytosine modification sites. iRNAm5C-PseDNC is a web-server and a predictor developed by incorporating ten types of physical-chemical properties into pseudo dinucleotide composition. To obtain the predicted result with the anticipated success rate, the user have to employ the entire sequence of the query RNA rather than its fragment as an input.


Allows to realize query and prediction of mRNA m6A sites. RNAMethPre serves for studies which concern human, mouse, and mammal. It employs a support vector machine (SVM) methods to build classifiers to predict N6-methyladenosine (m6A) modifications of mammalian mRNA. It is also effective for both full transcript mode and mature mRNA mode. This tool supplies a database of predicted m6A sites as well as experimental m6A sites and peaks across the transcriptome for query and visualization.


Predicts N6-methyladenosine sites in RNA sequences via physical-chemical properties. It was observed via a rigorous jackknife test that, in comparison with the existing predictor for the same purpose, pRNAm-PC achieved remarkably higher success rates in both overall accuracy and stability, indicating that the new predictor will become a useful high-throughput tool for identifying methylation sites in RNA, and that the novel approach can also be used to study many other RNA-related problems and conduct genome analysis.