Introduction
This is the first computational tool for predicting Dihydrouridine (D) sites over mRNA sequences. This modification can serve as a metabolic modulator for various pathological conditions, and its elevated levels in tumors are associated with a series of cancers. Precise identification of D sites on RNA is vital for understanding its biological function. DPred was mainly built upon the additive local self-attention and convolutional neural network architecture.
Table
We have uploaded the S.cerevisiae mRNA sequences. The D-modified mRNAs (positive samples) were derived by the D-seq techniques. All were 41 nt with a uridine in the center (In this study, T denotes uridine according to annotation custom). Users can directly download the CSV file that records this data from the button above the table.
User could click a Index for detailed information which shown below the table.
Tool
Users can input or upload the query sequences in the Fasta format. Results will be presented or downloaded after a while.
The result table shows probability, prediction result, and motif figure(if required).
Model
We displayed a framework figure and a brief introduction of the model. Users can download this model directly from this site.
